[hamradio-commits] [gnss-sdr] 48/149: Updating volk_gnsssdr to the new volk scheme
Carles Fernandez
carles_fernandez-guest at moszumanska.debian.org
Sat Feb 6 19:43:01 UTC 2016
This is an automated email from the git hooks/post-receive script.
carles_fernandez-guest pushed a commit to branch next
in repository gnss-sdr.
commit 24909510e7a5bbb1b7e9a85258563410ae739a7d
Author: Carles Fernandez <carles.fernandez at gmail.com>
Date: Tue Jan 12 20:15:16 2016 +0100
Updating volk_gnsssdr to the new volk scheme
---
.../volk_gnsssdr/CMakeLists.txt | 144 +-
.../volk_gnsssdr_module/volk_gnsssdr/Doxyfile.in | 2364 ++++++++++++++++++++
.../volk_gnsssdr/DoxygenLayout.xml | 196 ++
.../volk_gnsssdr_module/volk_gnsssdr/README.txt | 31 +-
.../volk_gnsssdr/apps/CMakeLists.txt | 29 +-
.../volk_gnsssdr/apps/volk_gnsssdr-config-info.cc | 12 +-
.../volk_gnsssdr/apps/volk_gnsssdr_profile.cc | 474 ++--
.../constants.h => apps/volk_gnsssdr_profile.h} | 32 +-
.../{ => Modules}/CMakeParseArgumentsCopy.cmake | 0
.../volk_gnsssdr/cmake/{ => Modules}/FindORC.cmake | 3 +
.../volk_gnsssdr/cmake/Modules/VolkAddTest.cmake | 205 ++
.../cmake/{ => Modules}/VolkBoost.cmake | 4 +-
.../cmake/Modules/VolkBuildTypes.cmake | 189 ++
.../cmake/{ => Modules}/VolkConfig.cmake | 6 +-
.../cmake/Modules/VolkConfigVersion.cmake.in | 34 +
.../{GrPython.cmake => Modules/VolkPython.cmake} | 4 +-
.../volk_gnsssdr/cmake/Modules/VolkVersion.cmake | 89 +
.../volk_gnsssdr_module/volk_gnsssdr/gen/archs.xml | 36 +-
.../volk_gnsssdr/gen/machines.xml | 15 +-
.../volk_gnsssdr/gen/volk_gnsssdr_machine_defs.py | 2 +-
.../volk_gnsssdr/gen/volk_gnsssdr_tmpl_utils.py | 11 +-
.../volk_gnsssdr/include/volk_gnsssdr/constants.h | 30 +-
.../volk_gnsssdr/volk_gnsssdr_avx_intrinsics.h | 71 +
.../include/volk_gnsssdr/volk_gnsssdr_common.h | 22 +-
.../include/volk_gnsssdr/volk_gnsssdr_complex.h | 1 +
.../include/volk_gnsssdr/volk_gnsssdr_malloc.h | 7 +-
.../include/volk_gnsssdr/volk_gnsssdr_prefs.h | 13 +-
.../volk_gnsssdr/volk_gnsssdr_sse3_intrinsics.h | 65 +
.../volk_gnsssdr/volk_gnsssdr_sse_intrinsics.h | 49 +
.../kernels/CommonMacros/CommonMacros.h | 174 --
.../CommonMacros_16ic_cw_epl_corr_32fc.h | 76 -
.../CommonMacros_8ic_cw_epl_corr_32fc.h | 115 -
.../volk_gnsssdr/kernels/CommonMacros/README.txt | 34 -
.../volk_gnsssdr/kernels/README.txt | 67 -
...sssdr_16sc_magnitude_32f_aligned16_orc_impl.orc | 0
.../asm}/orc/volk_gnsssdr_32f_x2_add_32f.orc | 0
.../orc/volk_gnsssdr_32fc_s32fc_multiply_32fc.orc | 0
.../orc/volk_gnsssdr_32fc_x2_multiply_32fc.orc | 0
.../asm}/orc/volk_gnsssdr_8i_accumulator_s8i.orc | 0
.../asm}/orc/volk_gnsssdr_8i_x2_add_8i.orc | 0
.../asm}/orc/volk_gnsssdr_8ic_conjugate_8ic.orc | 0
.../orc/volk_gnsssdr_8ic_magnitude_squared_8i.orc | 0
.../orc/volk_gnsssdr_8ic_s8ic_multiply_8ic.orc | 0
.../asm}/orc/volk_gnsssdr_8ic_x2_dot_prod_8ic.orc | 0
.../asm}/orc/volk_gnsssdr_8ic_x2_multiply_8ic.orc | 0
.../orc/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.orc | 0
.../asm}/orc/volk_gnsssdr_8u_x2_multiply_8u.orc | 0
.../volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h | 461 ----
...volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h | 1573 -------------
.../volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h | 595 -----
.../volk_gnsssdr/volk_gnsssdr_32fc_convert_16ic.h | 303 ---
.../volk_gnsssdr_32fc_s32f_convert_8ic.h | 240 --
...k_gnsssdr_32fc_s32f_x4_update_local_code_32fc.h | 231 --
.../volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3.h | 455 ----
.../volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5.h | 848 -------
.../volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h | 614 -----
.../volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h | 874 --------
.../volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h | 797 -------
...volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h | 1518 -------------
...volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h | 768 -------
...lk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h | 550 -----
...olk_gnsssdr_s32f_x2_update_local_carrier_32fc.h | 865 -------
.../volk_gnsssdr/lib/CMakeLists.txt | 188 +-
.../volk_gnsssdr/lib/kernel_tests.h | 84 +
.../volk_gnsssdr/lib/qa_16s_add_quad_aligned16.cc | 111 -
.../volk_gnsssdr/lib/qa_16s_add_quad_aligned16.h | 36 -
.../lib/qa_16s_branch_4_state_8_aligned16.cc | 123 -
.../lib/qa_16s_branch_4_state_8_aligned16.h | 36 -
.../lib/qa_16s_permute_and_scalar_add_aligned16.cc | 101 -
.../lib/qa_16s_permute_and_scalar_add_aligned16.h | 36 -
.../lib/qa_16s_quad_max_star_aligned16.cc | 82 -
.../lib/qa_16s_quad_max_star_aligned16.h | 37 -
.../volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.cc | 86 -
.../volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.h | 36 -
.../volk_gnsssdr/lib/qa_32f_index_max_aligned16.cc | 122 -
.../volk_gnsssdr/lib/qa_32f_index_max_aligned16.h | 37 -
.../lib/qa_32fc_index_max_aligned16.cc | 104 -
.../volk_gnsssdr/lib/qa_32fc_index_max_aligned16.h | 36 -
...qa_32fc_power_spectral_density_32f_aligned16.cc | 87 -
.../qa_32fc_power_spectral_density_32f_aligned16.h | 36 -
.../volk_gnsssdr/lib/qa_utils.cc | 859 +++----
.../volk_gnsssdr/lib/qa_utils.h | 129 +-
.../volk_gnsssdr_module/volk_gnsssdr/lib/testqa.cc | 139 +-
.../python/volk_gnsssdr_modtool/CMakeLists.txt | 4 +-
.../volk_gnsssdr_modtool_generate.py | 6 +-
.../volk_gnsssdr/tmpl/volk_gnsssdr.tmpl.h | 1 +
.../volk_gnsssdr/tmpl/volk_gnsssdr_cpu.tmpl.c | 35 +-
src/algorithms/tracking/adapters/CMakeLists.txt | 2 +-
.../tracking/gnuradio_blocks/CMakeLists.txt | 2 +-
src/core/receiver/gnss_block_factory.cc | 38 +-
src/core/system_parameters/rtcm.h | 2 +-
91 files changed, 4617 insertions(+), 13274 deletions(-)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/CMakeLists.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/CMakeLists.txt
index b1218fc..74f20e2 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/CMakeLists.txt
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/CMakeLists.txt
@@ -21,24 +21,38 @@
# Project setup
########################################################################
cmake_minimum_required(VERSION 2.6)
-if(NOT DEFINED CMAKE_BUILD_TYPE)
- set(CMAKE_BUILD_TYPE Release)
-endif()
set(CMAKE_BUILD_TYPE ${CMAKE_BUILD_TYPE} CACHE STRING "Choose build type: None Debug Release RelWithDebInfo MinSizeRel")
project(volk_gnsssdr)
enable_language(CXX)
enable_language(C)
enable_testing()
-set(VERSION 0.1)
-set(LIBVER 0.0.0)
+
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11 -Wall")
+set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c11 -Wall")
option(ENABLE_STRIP "Create a stripped volk_gnsssdr_profile binary (without shared libraries)" OFF)
set(CMAKE_SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}) #allows this to be a sub-project
set(CMAKE_BINARY_DIR ${CMAKE_CURRENT_BINARY_DIR}) #allows this to be a sub-project
-set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake) #location for custom "Modules"
-set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c11")
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
+list(INSERT CMAKE_MODULE_PATH 0 ${CMAKE_CURRENT_SOURCE_DIR}/cmake/Modules) #location for custom "Modules"
+
+include(VolkBuildTypes)
+#select the release build type by default to get optimization flags
+if(NOT CMAKE_BUILD_TYPE)
+ set(CMAKE_BUILD_TYPE "Release")
+ message(STATUS "Build type not specified: defaulting to release.")
+endif()
+VOLK_CHECK_BUILD_TYPE(${CMAKE_BUILD_TYPE})
+set(CMAKE_BUILD_TYPE ${CMAKE_BUILD_TYPE} CACHE STRING "")
+message(STATUS "Build type set to ${CMAKE_BUILD_TYPE}.")
+
+set(VERSION_INFO_MAJOR_VERSION 0)
+set(VERSION_INFO_MINOR_VERSION 0)
+set(VERSION_INFO_MAINT_VERSION 6)
+include(VolkVersion) #setup version info
+
+
+
########################################################################
# Environment setup
@@ -56,7 +70,9 @@ SET(CROSSCOMPILE_MULTILIB ${CROSSCOMPILE_MULTILIB} CACHE STRING "Define \"true\"
########################################################################
# Dependencies setup
########################################################################
-include(GrPython) #sets PYTHON_EXECUTABLE and PYTHON_DASH_B
+
+# Python
+include(VolkPython) #sets PYTHON_EXECUTABLE and PYTHON_DASH_B
VOLK_PYTHON_CHECK_MODULE("python >= 2.5" sys "sys.version.split()[0] >= '2.5'" PYTHON_MIN_VER_FOUND)
VOLK_PYTHON_CHECK_MODULE("Cheetah >= 2.0.0" Cheetah "Cheetah.Version >= '2.0.0'" CHEETAH_FOUND)
@@ -64,10 +80,12 @@ if(NOT PYTHON_MIN_VER_FOUND)
message(FATAL_ERROR "Python 2.5 or greater required to build VOLK_GNSSSDR")
endif()
+# Cheetah
if(NOT CHEETAH_FOUND)
message(FATAL_ERROR "Cheetah templates required to build VOLK_GNSSSDR")
endif()
+# Boost
if(MSVC)
if (NOT DEFINED BOOST_ALL_DYN_LINK)
set(BOOST_ALL_DYN_LINK TRUE)
@@ -79,12 +97,14 @@ if(MSVC)
unset(BOOST_REQUIRED_COMPONENTS) #empty components list for static link
endif(BOOST_ALL_DYN_LINK)
endif(MSVC)
+
include(VolkBoost)
if(NOT Boost_FOUND)
message(FATAL_ERROR "VOLK_GNSSSDR Requires boost to build")
endif()
+# Orc
option(ENABLE_ORC "Enable Orc" True)
if(ENABLE_ORC)
find_package(ORC)
@@ -92,6 +112,25 @@ else(ENABLE_ORC)
message(STATUS "Disabling use of ORC")
endif(ENABLE_ORC)
+
+########################################################################
+# Setup doxygen
+########################################################################
+find_package(Doxygen)
+if(DOXYGEN_FOUND)
+ configure_file(
+ ${CMAKE_SOURCE_DIR}/Doxyfile.in
+ ${CMAKE_BINARY_DIR}/Doxyfile
+ @ONLY)
+
+ add_custom_target(doc
+ ${DOXYGEN_EXECUTABLE} ${CMAKE_BINARY_DIR}/Doxyfile
+ WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
+ COMMENT "Generating documentation with Doxygen" VERBATIM
+ )
+endif(DOXYGEN_FOUND)
+
+
########################################################################
# Setup the package config file
########################################################################
@@ -129,6 +168,8 @@ install(FILES
${CMAKE_SOURCE_DIR}/include/volk_gnsssdr/volk_gnsssdr_prefs.h
${CMAKE_SOURCE_DIR}/include/volk_gnsssdr/volk_gnsssdr_complex.h
${CMAKE_SOURCE_DIR}/include/volk_gnsssdr/volk_gnsssdr_common.h
+ ${CMAKE_SOURCE_DIR}/include/volk_gnsssdr/volk_gnsssdr_avx_intrinsics.h
+ ${CMAKE_SOURCE_DIR}/include/volk_gnsssdr/volk_gnsssdr_sse3_intrinsics.h
${CMAKE_BINARY_DIR}/include/volk_gnsssdr/volk_gnsssdr.h
${CMAKE_BINARY_DIR}/include/volk_gnsssdr/volk_gnsssdr_cpu.h
${CMAKE_BINARY_DIR}/include/volk_gnsssdr/volk_gnsssdr_config_fixed.h
@@ -138,19 +179,6 @@ install(FILES
COMPONENT "volk_gnsssdr_devel"
)
-########################################################################
-# Install cmake search routine for external use
-########################################################################
-
-if(NOT CMAKE_MODULES_DIR)
- set(CMAKE_MODULES_DIR lib${LIB_SUFFIX}/cmake)
-endif(NOT CMAKE_MODULES_DIR)
-
-install(
- FILES ${CMAKE_CURRENT_SOURCE_DIR}/cmake/VolkConfig.cmake
- DESTINATION ${CMAKE_MODULES_DIR}/volk_gnsssdr
- COMPONENT "volk_gnsssdr_devel"
-)
########################################################################
# On Apple only, set install name and use rpath correctly, if not already set
@@ -158,12 +186,12 @@ install(
if(APPLE)
if(NOT CMAKE_INSTALL_NAME_DIR)
set(CMAKE_INSTALL_NAME_DIR
- ${CMAKE_INSTALL_PREFIX}/lib CACHE
+ ${CMAKE_INSTALL_PREFIX}/${VOLK_LIBRARY_DIR} CACHE
PATH "Library Install Name Destination Directory" FORCE)
endif(NOT CMAKE_INSTALL_NAME_DIR)
if(NOT CMAKE_INSTALL_RPATH)
set(CMAKE_INSTALL_RPATH
- ${CMAKE_INSTALL_PREFIX}/lib CACHE
+ ${CMAKE_INSTALL_PREFIX}/${VOLK_LIBRARY_DIR} CACHE
PATH "Library Install RPath" FORCE)
endif(NOT CMAKE_INSTALL_RPATH)
if(NOT CMAKE_BUILD_WITH_INSTALL_RPATH)
@@ -172,6 +200,64 @@ if(APPLE)
endif(NOT CMAKE_BUILD_WITH_INSTALL_RPATH)
endif(APPLE)
+
+########################################################################
+# Create uninstall target
+########################################################################
+configure_file(
+ ${CMAKE_SOURCE_DIR}/cmake/cmake_uninstall.cmake.in
+ ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake
+ at ONLY)
+
+# Only add the target if there isn't one defined already
+if(NOT TARGET uninstall)
+ add_custom_target(uninstall
+ ${CMAKE_COMMAND} -P ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake
+ )
+endif()
+
+
+
+
+########################################################################
+# Install our Cmake modules into $prefix/lib/cmake/volk_gnsssdr
+# See "Package Configuration Files" on page:
+# http://www.cmake.org/Wiki/CMake/Tutorials/Packaging
+########################################################################
+
+configure_file(
+ ${CMAKE_SOURCE_DIR}/cmake/Modules/VolkConfigVersion.cmake.in
+ ${CMAKE_BINARY_DIR}/cmake/Modules/VolkConfigVersion.cmake
+ at ONLY)
+
+
+########################################################################
+# Install cmake search routine for external use
+########################################################################
+
+if(NOT CMAKE_MODULES_DIR)
+ set(CMAKE_MODULES_DIR lib${LIB_SUFFIX}/cmake)
+endif(NOT CMAKE_MODULES_DIR)
+
+install(
+ FILES
+ ${CMAKE_CURRENT_SOURCE_DIR}/cmake/Modules/VolkConfig.cmake
+ ${CMAKE_CURRENT_BINARY_DIR}/cmake/Modules/VolkConfigVersion.cmake
+ DESTINATION ${CMAKE_MODULES_DIR}/volk_gnsssdr
+ COMPONENT "volk_gnsssdr_devel"
+)
+
+########################################################################
+# Option to enable QA testing, on by default
+########################################################################
+OPTION(ENABLE_TESTING "Enable QA testing" ON)
+if(ENABLE_TESTING)
+ message(STATUS "QA Testing is enabled.")
+else()
+ message(STATUS "QA Testing is disabled.")
+endif()
+message(STATUS " Modify using: -DENABLE_TESTING=ON/OFF")
+
########################################################################
# Setup the library
########################################################################
@@ -183,16 +269,6 @@ add_subdirectory(lib)
add_subdirectory(apps)
add_subdirectory(python/volk_gnsssdr_modtool)
-########################################################################
-# Create uninstall target
-########################################################################
-configure_file(
- ${CMAKE_CURRENT_SOURCE_DIR}/cmake/cmake_uninstall.cmake.in
- ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake
- @ONLY)
-
-add_custom_target(uninstall
- COMMAND ${CMAKE_COMMAND} -P ${CMAKE_CURRENT_BINARY_DIR}/cmake_uninstall.cmake)
########################################################################
# Print summary
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/Doxyfile.in b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/Doxyfile.in
new file mode 100644
index 0000000..9e6a066
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/Doxyfile.in
@@ -0,0 +1,2364 @@
+# Doxyfile 1.8.6
+
+# This file describes the settings to be used by the documentation system
+# doxygen (www.doxygen.org) for a project.
+#
+# All text after a double hash (##) is considered a comment and is placed in
+# front of the TAG it is preceding.
+#
+# All text after a single hash (#) is considered a comment and will be ignored.
+# The format is:
+# TAG = value [value, ...]
+# For lists, items can also be appended using:
+# TAG += value [value, ...]
+# Values that contain spaces should be placed between quotes (\" \").
+
+#---------------------------------------------------------------------------
+# Project related configuration options
+#---------------------------------------------------------------------------
+
+# This tag specifies the encoding used for all characters in the config file
+# that follow. The default is UTF-8 which is also the encoding used for all text
+# before the first occurrence of this tag. Doxygen uses libiconv (or the iconv
+# built into libc) for the transcoding. See http://www.gnu.org/software/libiconv
+# for the list of possible encodings.
+# The default value is: UTF-8.
+
+DOXYFILE_ENCODING = UTF-8
+
+# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by
+# double-quotes, unless you are using Doxywizard) that should identify the
+# project for which the documentation is generated. This name is used in the
+# title of most generated pages and in a few other places.
+# The default value is: My Project.
+
+PROJECT_NAME = "Vector Optimized Library of Kernels for GNSS-SDR"
+
+# The PROJECT_NUMBER tag can be used to enter a project or revision number. This
+# could be handy for archiving the generated documentation or if some version
+# control system is used.
+
+PROJECT_NUMBER = @VERSION@
+
+# Using the PROJECT_BRIEF tag one can provide an optional one line description
+# for a project that appears at the top of each page and should give viewer a
+# quick idea about the purpose of the project. Keep the description short.
+
+PROJECT_BRIEF = "Architecture-tuned implementations of math kernels"
+
+# With the PROJECT_LOGO tag one can specify an logo or icon that is included in
+# the documentation. The maximum height of the logo should not exceed 55 pixels
+# and the maximum width should not exceed 200 pixels. Doxygen will copy the logo
+# to the output directory.
+
+PROJECT_LOGO =
+
+# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
+# into which the generated documentation will be written. If a relative path is
+# entered, it will be relative to the location where doxygen was started. If
+# left blank the current directory will be used.
+
+# TODO: configure this to be a special docs directory. nw tried, but running
+# make doc won' create the directory, but with doxygen it will. why?
+
+OUTPUT_DIRECTORY =
+
+# If the CREATE_SUBDIRS tag is set to YES, then doxygen will create 4096 sub-
+# directories (in 2 levels) under the output directory of each output format and
+# will distribute the generated files over these directories. Enabling this
+# option can be useful when feeding doxygen a huge amount of source files, where
+# putting all generated files in the same directory would otherwise causes
+# performance problems for the file system.
+# The default value is: NO.
+
+CREATE_SUBDIRS = NO
+
+# The OUTPUT_LANGUAGE tag is used to specify the language in which all
+# documentation generated by doxygen is written. Doxygen will use this
+# information to generate all constant output in the proper language.
+# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese,
+# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States),
+# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian,
+# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages),
+# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian,
+# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian,
+# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish,
+# Ukrainian and Vietnamese.
+# The default value is: English.
+
+OUTPUT_LANGUAGE = English
+
+# If the BRIEF_MEMBER_DESC tag is set to YES doxygen will include brief member
+# descriptions after the members that are listed in the file and class
+# documentation (similar to Javadoc). Set to NO to disable this.
+# The default value is: YES.
+
+BRIEF_MEMBER_DESC = YES
+
+# If the REPEAT_BRIEF tag is set to YES doxygen will prepend the brief
+# description of a member or function before the detailed description
+#
+# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the
+# brief descriptions will be completely suppressed.
+# The default value is: YES.
+
+REPEAT_BRIEF = YES
+
+# This tag implements a quasi-intelligent brief description abbreviator that is
+# used to form the text in various listings. Each string in this list, if found
+# as the leading text of the brief description, will be stripped from the text
+# and the result, after processing the whole list, is used as the annotated
+# text. Otherwise, the brief description is used as-is. If left blank, the
+# following values are used ($name is automatically replaced with the name of
+# the entity):The $name class, The $name widget, The $name file, is, provides,
+# specifies, contains, represents, a, an and the.
+
+ABBREVIATE_BRIEF = "The $name class" \
+ "The $name widget" \
+ "The $name file" \
+ is \
+ provides \
+ specifies \
+ contains \
+ represents \
+ a \
+ an \
+ the
+
+# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then
+# doxygen will generate a detailed section even if there is only a brief
+# description.
+# The default value is: NO.
+
+ALWAYS_DETAILED_SEC = NO
+
+# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all
+# inherited members of a class in the documentation of that class as if those
+# members were ordinary class members. Constructors, destructors and assignment
+# operators of the base classes will not be shown.
+# The default value is: NO.
+
+INLINE_INHERITED_MEMB = NO
+
+# If the FULL_PATH_NAMES tag is set to YES doxygen will prepend the full path
+# before files name in the file list and in the header files. If set to NO the
+# shortest path that makes the file name unique will be used
+# The default value is: YES.
+
+FULL_PATH_NAMES = YES
+
+# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path.
+# Stripping is only done if one of the specified strings matches the left-hand
+# part of the path. The tag can be used to show relative paths in the file list.
+# If left blank the directory from which doxygen is run is used as the path to
+# strip.
+#
+# Note that you can specify absolute paths here, but also relative paths, which
+# will be relative from the directory where doxygen is started.
+# This tag requires that the tag FULL_PATH_NAMES is set to YES.
+
+STRIP_FROM_PATH =
+
+# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the
+# path mentioned in the documentation of a class, which tells the reader which
+# header file to include in order to use a class. If left blank only the name of
+# the header file containing the class definition is used. Otherwise one should
+# specify the list of include paths that are normally passed to the compiler
+# using the -I flag.
+
+STRIP_FROM_INC_PATH =
+
+# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but
+# less readable) file names. This can be useful is your file systems doesn't
+# support long names like on DOS, Mac, or CD-ROM.
+# The default value is: NO.
+
+SHORT_NAMES = NO
+
+# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the
+# first line (until the first dot) of a Javadoc-style comment as the brief
+# description. If set to NO, the Javadoc-style will behave just like regular Qt-
+# style comments (thus requiring an explicit @brief command for a brief
+# description.)
+# The default value is: NO.
+
+JAVADOC_AUTOBRIEF = NO
+
+# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first
+# line (until the first dot) of a Qt-style comment as the brief description. If
+# set to NO, the Qt-style will behave just like regular Qt-style comments (thus
+# requiring an explicit \brief command for a brief description.)
+# The default value is: NO.
+
+QT_AUTOBRIEF = NO
+
+# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a
+# multi-line C++ special comment block (i.e. a block of //! or /// comments) as
+# a brief description. This used to be the default behavior. The new default is
+# to treat a multi-line C++ comment block as a detailed description. Set this
+# tag to YES if you prefer the old behavior instead.
+#
+# Note that setting this tag to YES also means that rational rose comments are
+# not recognized any more.
+# The default value is: NO.
+
+MULTILINE_CPP_IS_BRIEF = NO
+
+# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the
+# documentation from any documented member that it re-implements.
+# The default value is: YES.
+
+INHERIT_DOCS = YES
+
+# If the SEPARATE_MEMBER_PAGES tag is set to YES, then doxygen will produce a
+# new page for each member. If set to NO, the documentation of a member will be
+# part of the file/class/namespace that contains it.
+# The default value is: NO.
+
+SEPARATE_MEMBER_PAGES = NO
+
+# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen
+# uses this value to replace tabs by spaces in code fragments.
+# Minimum value: 1, maximum value: 16, default value: 4.
+
+TAB_SIZE = 4
+
+# This tag can be used to specify a number of aliases that act as commands in
+# the documentation. An alias has the form:
+# name=value
+# For example adding
+# "sideeffect=@par Side Effects:\n"
+# will allow you to put the command \sideeffect (or @sideeffect) in the
+# documentation, which will result in a user-defined paragraph with heading
+# "Side Effects:". You can put \n's in the value part of an alias to insert
+# newlines.
+
+ALIASES =
+
+# This tag can be used to specify a number of word-keyword mappings (TCL only).
+# A mapping has the form "name=value". For example adding "class=itcl::class"
+# will allow you to use the command class in the itcl::class meaning.
+
+TCL_SUBST =
+
+# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources
+# only. Doxygen will then generate output that is more tailored for C. For
+# instance, some of the names that are used will be different. The list of all
+# members will be omitted, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_FOR_C = YES
+
+# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or
+# Python sources only. Doxygen will then generate output that is more tailored
+# for that language. For instance, namespaces will be presented as packages,
+# qualified scopes will look different, etc.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_JAVA = NO
+
+# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran
+# sources. Doxygen will then generate output that is tailored for Fortran.
+# The default value is: NO.
+
+OPTIMIZE_FOR_FORTRAN = NO
+
+# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL
+# sources. Doxygen will then generate output that is tailored for VHDL.
+# The default value is: NO.
+
+OPTIMIZE_OUTPUT_VHDL = NO
+
+# Doxygen selects the parser to use depending on the extension of the files it
+# parses. With this tag you can assign which parser to use for a given
+# extension. Doxygen has a built-in mapping, but you can override or extend it
+# using this tag. The format is ext=language, where ext is a file extension, and
+# language is one of the parsers supported by doxygen: IDL, Java, Javascript,
+# C#, C, C++, D, PHP, Objective-C, Python, Fortran, VHDL. For instance to make
+# doxygen treat .inc files as Fortran files (default is PHP), and .f files as C
+# (default is Fortran), use: inc=Fortran f=C.
+#
+# Note For files without extension you can use no_extension as a placeholder.
+#
+# Note that for custom extensions you also need to set FILE_PATTERNS otherwise
+# the files are not read by doxygen.
+
+EXTENSION_MAPPING =
+
+# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments
+# according to the Markdown format, which allows for more readable
+# documentation. See http://daringfireball.net/projects/markdown/ for details.
+# The output of markdown processing is further processed by doxygen, so you can
+# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in
+# case of backward compatibilities issues.
+# The default value is: YES.
+
+MARKDOWN_SUPPORT = YES
+
+# When enabled doxygen tries to link words that correspond to documented
+# classes, or namespaces to their corresponding documentation. Such a link can
+# be prevented in individual cases by by putting a % sign in front of the word
+# or globally by setting AUTOLINK_SUPPORT to NO.
+# The default value is: YES.
+
+AUTOLINK_SUPPORT = YES
+
+# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want
+# to include (a tag file for) the STL sources as input, then you should set this
+# tag to YES in order to let doxygen match functions declarations and
+# definitions whose arguments contain STL classes (e.g. func(std::string);
+# versus func(std::string) {}). This also make the inheritance and collaboration
+# diagrams that involve STL classes more complete and accurate.
+# The default value is: NO.
+
+BUILTIN_STL_SUPPORT = NO
+
+# If you use Microsoft's C++/CLI language, you should set this option to YES to
+# enable parsing support.
+# The default value is: NO.
+
+CPP_CLI_SUPPORT = NO
+
+# Set the SIP_SUPPORT tag to YES if your project consists of sip (see:
+# http://www.riverbankcomputing.co.uk/software/sip/intro) sources only. Doxygen
+# will parse them like normal C++ but will assume all classes use public instead
+# of private inheritance when no explicit protection keyword is present.
+# The default value is: NO.
+
+SIP_SUPPORT = NO
+
+# For Microsoft's IDL there are propget and propput attributes to indicate
+# getter and setter methods for a property. Setting this option to YES will make
+# doxygen to replace the get and set methods by a property in the documentation.
+# This will only work if the methods are indeed getting or setting a simple
+# type. If this is not the case, or you want to show the methods anyway, you
+# should set this option to NO.
+# The default value is: YES.
+
+IDL_PROPERTY_SUPPORT = YES
+
+# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC
+# tag is set to YES, then doxygen will reuse the documentation of the first
+# member in the group (if any) for the other members of the group. By default
+# all members of a group must be documented explicitly.
+# The default value is: NO.
+
+DISTRIBUTE_GROUP_DOC = NO
+
+# Set the SUBGROUPING tag to YES to allow class member groups of the same type
+# (for instance a group of public functions) to be put as a subgroup of that
+# type (e.g. under the Public Functions section). Set it to NO to prevent
+# subgrouping. Alternatively, this can be done per class using the
+# \nosubgrouping command.
+# The default value is: YES.
+
+SUBGROUPING = YES
+
+# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions
+# are shown inside the group in which they are included (e.g. using \ingroup)
+# instead of on a separate page (for HTML and Man pages) or section (for LaTeX
+# and RTF).
+#
+# Note that this feature does not work in combination with
+# SEPARATE_MEMBER_PAGES.
+# The default value is: NO.
+
+INLINE_GROUPED_CLASSES = NO
+
+# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions
+# with only public data fields or simple typedef fields will be shown inline in
+# the documentation of the scope in which they are defined (i.e. file,
+# namespace, or group documentation), provided this scope is documented. If set
+# to NO, structs, classes, and unions are shown on a separate page (for HTML and
+# Man pages) or section (for LaTeX and RTF).
+# The default value is: NO.
+
+INLINE_SIMPLE_STRUCTS = NO
+
+# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or
+# enum is documented as struct, union, or enum with the name of the typedef. So
+# typedef struct TypeS {} TypeT, will appear in the documentation as a struct
+# with name TypeT. When disabled the typedef will appear as a member of a file,
+# namespace, or class. And the struct will be named TypeS. This can typically be
+# useful for C code in case the coding convention dictates that all compound
+# types are typedef'ed and only the typedef is referenced, never the tag name.
+# The default value is: NO.
+
+TYPEDEF_HIDES_STRUCT = NO
+
+# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This
+# cache is used to resolve symbols given their name and scope. Since this can be
+# an expensive process and often the same symbol appears multiple times in the
+# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small
+# doxygen will become slower. If the cache is too large, memory is wasted. The
+# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range
+# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536
+# symbols. At the end of a run doxygen will report the cache usage and suggest
+# the optimal cache size from a speed point of view.
+# Minimum value: 0, maximum value: 9, default value: 0.
+
+LOOKUP_CACHE_SIZE = 0
+
+#---------------------------------------------------------------------------
+# Build related configuration options
+#---------------------------------------------------------------------------
+
+# If the EXTRACT_ALL tag is set to YES doxygen will assume all entities in
+# documentation are documented, even if no documentation was available. Private
+# class members and static file members will be hidden unless the
+# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES.
+# Note: This will also disable the warnings about undocumented members that are
+# normally produced when WARNINGS is set to YES.
+# The default value is: NO.
+
+EXTRACT_ALL = YES
+
+# If the EXTRACT_PRIVATE tag is set to YES all private members of a class will
+# be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PRIVATE = NO
+
+# If the EXTRACT_PACKAGE tag is set to YES all members with package or internal
+# scope will be included in the documentation.
+# The default value is: NO.
+
+EXTRACT_PACKAGE = NO
+
+# If the EXTRACT_STATIC tag is set to YES all static members of a file will be
+# included in the documentation.
+# The default value is: NO.
+
+EXTRACT_STATIC = YES
+
+# If the EXTRACT_LOCAL_CLASSES tag is set to YES classes (and structs) defined
+# locally in source files will be included in the documentation. If set to NO
+# only classes defined in header files are included. Does not have any effect
+# for Java sources.
+# The default value is: YES.
+
+EXTRACT_LOCAL_CLASSES = YES
+
+# This flag is only useful for Objective-C code. When set to YES local methods,
+# which are defined in the implementation section but not in the interface are
+# included in the documentation. If set to NO only methods in the interface are
+# included.
+# The default value is: NO.
+
+EXTRACT_LOCAL_METHODS = NO
+
+# If this flag is set to YES, the members of anonymous namespaces will be
+# extracted and appear in the documentation as a namespace called
+# 'anonymous_namespace{file}', where file will be replaced with the base name of
+# the file that contains the anonymous namespace. By default anonymous namespace
+# are hidden.
+# The default value is: NO.
+
+EXTRACT_ANON_NSPACES = NO
+
+# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all
+# undocumented members inside documented classes or files. If set to NO these
+# members will be included in the various overviews, but no documentation
+# section is generated. This option has no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_MEMBERS = YES
+
+# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all
+# undocumented classes that are normally visible in the class hierarchy. If set
+# to NO these classes will be included in the various overviews. This option has
+# no effect if EXTRACT_ALL is enabled.
+# The default value is: NO.
+
+HIDE_UNDOC_CLASSES = YES
+
+# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend
+# (class|struct|union) declarations. If set to NO these declarations will be
+# included in the documentation.
+# The default value is: NO.
+
+HIDE_FRIEND_COMPOUNDS = NO
+
+# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any
+# documentation blocks found inside the body of a function. If set to NO these
+# blocks will be appended to the function's detailed documentation block.
+# The default value is: NO.
+
+HIDE_IN_BODY_DOCS = NO
+
+# The INTERNAL_DOCS tag determines if documentation that is typed after a
+# \internal command is included. If the tag is set to NO then the documentation
+# will be excluded. Set it to YES to include the internal documentation.
+# The default value is: NO.
+
+INTERNAL_DOCS = NO
+
+# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
+# names in lower-case letters. If set to YES upper-case letters are also
+# allowed. This is useful if you have classes or files whose names only differ
+# in case and if your file system supports case sensitive file names. Windows
+# and Mac users are advised to set this option to NO.
+# The default value is: system dependent.
+
+CASE_SENSE_NAMES = NO
+
+# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with
+# their full class and namespace scopes in the documentation. If set to YES the
+# scope will be hidden.
+# The default value is: NO.
+
+HIDE_SCOPE_NAMES = NO
+
+# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of
+# the files that are included by a file in the documentation of that file.
+# The default value is: YES.
+
+SHOW_INCLUDE_FILES = YES
+
+# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each
+# grouped member an include statement to the documentation, telling the reader
+# which file to include in order to use the member.
+# The default value is: NO.
+
+SHOW_GROUPED_MEMB_INC = NO
+
+# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include
+# files with double quotes in the documentation rather than with sharp brackets.
+# The default value is: NO.
+
+FORCE_LOCAL_INCLUDES = NO
+
+# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the
+# documentation for inline members.
+# The default value is: YES.
+
+INLINE_INFO = YES
+
+# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the
+# (detailed) documentation of file and class members alphabetically by member
+# name. If set to NO the members will appear in declaration order.
+# The default value is: YES.
+
+SORT_MEMBER_DOCS = YES
+
+# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief
+# descriptions of file, namespace and class members alphabetically by member
+# name. If set to NO the members will appear in declaration order. Note that
+# this will also influence the order of the classes in the class list.
+# The default value is: NO.
+
+SORT_BRIEF_DOCS = NO
+
+# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the
+# (brief and detailed) documentation of class members so that constructors and
+# destructors are listed first. If set to NO the constructors will appear in the
+# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS.
+# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief
+# member documentation.
+# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting
+# detailed member documentation.
+# The default value is: NO.
+
+SORT_MEMBERS_CTORS_1ST = NO
+
+# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy
+# of group names into alphabetical order. If set to NO the group names will
+# appear in their defined order.
+# The default value is: NO.
+
+SORT_GROUP_NAMES = NO
+
+# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by
+# fully-qualified names, including namespaces. If set to NO, the class list will
+# be sorted only by class name, not including the namespace part.
+# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES.
+# Note: This option applies only to the class list, not to the alphabetical
+# list.
+# The default value is: NO.
+
+SORT_BY_SCOPE_NAME = NO
+
+# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper
+# type resolution of all parameters of a function it will reject a match between
+# the prototype and the implementation of a member function even if there is
+# only one candidate or it is obvious which candidate to choose by doing a
+# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still
+# accept a match between prototype and implementation in such cases.
+# The default value is: NO.
+
+STRICT_PROTO_MATCHING = NO
+
+# The GENERATE_TODOLIST tag can be used to enable ( YES) or disable ( NO) the
+# todo list. This list is created by putting \todo commands in the
+# documentation.
+# The default value is: YES.
+
+GENERATE_TODOLIST = YES
+
+# The GENERATE_TESTLIST tag can be used to enable ( YES) or disable ( NO) the
+# test list. This list is created by putting \test commands in the
+# documentation.
+# The default value is: YES.
+
+GENERATE_TESTLIST = YES
+
+# The GENERATE_BUGLIST tag can be used to enable ( YES) or disable ( NO) the bug
+# list. This list is created by putting \bug commands in the documentation.
+# The default value is: YES.
+
+GENERATE_BUGLIST = YES
+
+# The GENERATE_DEPRECATEDLIST tag can be used to enable ( YES) or disable ( NO)
+# the deprecated list. This list is created by putting \deprecated commands in
+# the documentation.
+# The default value is: YES.
+
+GENERATE_DEPRECATEDLIST= YES
+
+# The ENABLED_SECTIONS tag can be used to enable conditional documentation
+# sections, marked by \if <section_label> ... \endif and \cond <section_label>
+# ... \endcond blocks.
+
+ENABLED_SECTIONS =
+
+# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the
+# initial value of a variable or macro / define can have for it to appear in the
+# documentation. If the initializer consists of more lines than specified here
+# it will be hidden. Use a value of 0 to hide initializers completely. The
+# appearance of the value of individual variables and macros / defines can be
+# controlled using \showinitializer or \hideinitializer command in the
+# documentation regardless of this setting.
+# Minimum value: 0, maximum value: 10000, default value: 30.
+
+MAX_INITIALIZER_LINES = 30
+
+# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at
+# the bottom of the documentation of classes and structs. If set to YES the list
+# will mention the files that were used to generate the documentation.
+# The default value is: YES.
+
+SHOW_USED_FILES = YES
+
+# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This
+# will remove the Files entry from the Quick Index and from the Folder Tree View
+# (if specified).
+# The default value is: YES.
+
+SHOW_FILES = YES
+
+# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces
+# page. This will remove the Namespaces entry from the Quick Index and from the
+# Folder Tree View (if specified).
+# The default value is: YES.
+
+SHOW_NAMESPACES = YES
+
+# The FILE_VERSION_FILTER tag can be used to specify a program or script that
+# doxygen should invoke to get the current version for each file (typically from
+# the version control system). Doxygen will invoke the program by executing (via
+# popen()) the command command input-file, where command is the value of the
+# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided
+# by doxygen. Whatever the program writes to standard output is used as the file
+# version. For an example see the documentation.
+
+FILE_VERSION_FILTER =
+
+# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed
+# by doxygen. The layout file controls the global structure of the generated
+# output files in an output format independent way. To create the layout file
+# that represents doxygen's defaults, run doxygen with the -l option. You can
+# optionally specify a file name after the option, if omitted DoxygenLayout.xml
+# will be used as the name of the layout file.
+#
+# Note that if you run doxygen from a directory containing a file called
+# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE
+# tag is left empty.
+
+LAYOUT_FILE = @CMAKE_SOURCE_DIR@/DoxygenLayout.xml
+
+# The CITE_BIB_FILES tag can be used to specify one or more bib files containing
+# the reference definitions. This must be a list of .bib files. The .bib
+# extension is automatically appended if omitted. This requires the bibtex tool
+# to be installed. See also http://en.wikipedia.org/wiki/BibTeX for more info.
+# For LaTeX the style of the bibliography can be controlled using
+# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the
+# search path. Do not use file names with spaces, bibtex cannot handle them. See
+# also \cite for info how to create references.
+
+CITE_BIB_FILES =
+
+#---------------------------------------------------------------------------
+# Configuration options related to warning and progress messages
+#---------------------------------------------------------------------------
+
+# The QUIET tag can be used to turn on/off the messages that are generated to
+# standard output by doxygen. If QUIET is set to YES this implies that the
+# messages are off.
+# The default value is: NO.
+
+QUIET = NO
+
+# The WARNINGS tag can be used to turn on/off the warning messages that are
+# generated to standard error ( stderr) by doxygen. If WARNINGS is set to YES
+# this implies that the warnings are on.
+#
+# Tip: Turn warnings on while writing the documentation.
+# The default value is: YES.
+
+WARNINGS = YES
+
+# If the WARN_IF_UNDOCUMENTED tag is set to YES, then doxygen will generate
+# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag
+# will automatically be disabled.
+# The default value is: YES.
+
+WARN_IF_UNDOCUMENTED = YES
+
+# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for
+# potential errors in the documentation, such as not documenting some parameters
+# in a documented function, or documenting parameters that don't exist or using
+# markup commands wrongly.
+# The default value is: YES.
+
+WARN_IF_DOC_ERROR = YES
+
+# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that
+# are documented, but have no documentation for their parameters or return
+# value. If set to NO doxygen will only warn about wrong or incomplete parameter
+# documentation, but not about the absence of documentation.
+# The default value is: NO.
+
+WARN_NO_PARAMDOC = NO
+
+# The WARN_FORMAT tag determines the format of the warning messages that doxygen
+# can produce. The string should contain the $file, $line, and $text tags, which
+# will be replaced by the file and line number from which the warning originated
+# and the warning text. Optionally the format may contain $version, which will
+# be replaced by the version of the file (if it could be obtained via
+# FILE_VERSION_FILTER)
+# The default value is: $file:$line: $text.
+
+WARN_FORMAT = "$file:$line: $text"
+
+# The WARN_LOGFILE tag can be used to specify a file to which warning and error
+# messages should be written. If left blank the output is written to standard
+# error (stderr).
+
+WARN_LOGFILE =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the input files
+#---------------------------------------------------------------------------
+
+# The INPUT tag is used to specify the files and/or directories that contain
+# documented source files. You may enter file names like myfile.cpp or
+# directories like /usr/src/myproject. Separate the files or directories with
+# spaces.
+# Note: If this tag is empty the current directory is searched.
+
+INPUT = @CMAKE_SOURCE_DIR@
+
+# This tag can be used to specify the character encoding of the source files
+# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
+# libiconv (or the iconv built into libc) for the transcoding. See the libiconv
+# documentation (see: http://www.gnu.org/software/libiconv) for the list of
+# possible encodings.
+# The default value is: UTF-8.
+
+INPUT_ENCODING = UTF-8
+
+# If the value of the INPUT tag contains directories, you can use the
+# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and
+# *.h) to filter out the source-files in the directories. If left blank the
+# following patterns are tested:*.c, *.cc, *.cxx, *.cpp, *.c++, *.java, *.ii,
+# *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h, *.hh, *.hxx, *.hpp,
+# *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc, *.m, *.markdown,
+# *.md, *.mm, *.dox, *.py, *.f90, *.f, *.for, *.tcl, *.vhd, *.vhdl, *.ucf,
+# *.qsf, *.as and *.js.
+
+FILE_PATTERNS = *.c \
+ *.cc \
+ *.cxx \
+ *.cpp \
+ *.c++ \
+ *.java \
+ *.ii \
+ *.ixx \
+ *.ipp \
+ *.i++ \
+ *.inl \
+ *.idl \
+ *.ddl \
+ *.odl \
+ *.h \
+ *.hh \
+ *.hxx \
+ *.hpp \
+ *.h++ \
+ *.cs \
+ *.d \
+ *.php \
+ *.php4 \
+ *.php5 \
+ *.phtml \
+ *.inc \
+ *.m \
+ *.markdown \
+ *.md \
+ *.mm \
+ *.dox \
+ *.py \
+ *.f90 \
+ *.f \
+ *.for \
+ *.tcl \
+ *.vhd \
+ *.vhdl \
+ *.ucf \
+ *.qsf \
+ *.as \
+ *.js
+
+# The RECURSIVE tag can be used to specify whether or not subdirectories should
+# be searched for input files as well.
+# The default value is: NO.
+
+RECURSIVE = YES
+
+# The EXCLUDE tag can be used to specify files and/or directories that should be
+# excluded from the INPUT source files. This way you can easily exclude a
+# subdirectory from a directory tree whose root is specified with the INPUT tag.
+#
+# Note that relative paths are relative to the directory from which doxygen is
+# run.
+
+EXCLUDE = @CMAKE_BINARY_DIR@
+
+# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or
+# directories that are symbolic links (a Unix file system feature) are excluded
+# from the input.
+# The default value is: NO.
+
+EXCLUDE_SYMLINKS = NO
+
+# If the value of the INPUT tag contains directories, you can use the
+# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude
+# certain files from those directories.
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories for example use the pattern */test/*
+
+EXCLUDE_PATTERNS =
+
+# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
+# (namespaces, classes, functions, etc.) that should be excluded from the
+# output. The symbol name can be a fully qualified name, a word, or if the
+# wildcard * is used, a substring. Examples: ANamespace, AClass,
+# AClass::ANamespace, ANamespace::*Test
+#
+# Note that the wildcards are matched against the file with absolute path, so to
+# exclude all test directories use the pattern */test/*
+
+EXCLUDE_SYMBOLS =
+
+# The EXAMPLE_PATH tag can be used to specify one or more files or directories
+# that contain example code fragments that are included (see the \include
+# command).
+
+EXAMPLE_PATH =
+
+# If the value of the EXAMPLE_PATH tag contains directories, you can use the
+# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
+# *.h) to filter out the source-files in the directories. If left blank all
+# files are included.
+
+EXAMPLE_PATTERNS = *
+
+# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be
+# searched for input files to be used with the \include or \dontinclude commands
+# irrespective of the value of the RECURSIVE tag.
+# The default value is: NO.
+
+EXAMPLE_RECURSIVE = NO
+
+# The IMAGE_PATH tag can be used to specify one or more files or directories
+# that contain images that are to be included in the documentation (see the
+# \image command).
+
+IMAGE_PATH =
+
+# The INPUT_FILTER tag can be used to specify a program that doxygen should
+# invoke to filter for each input file. Doxygen will invoke the filter program
+# by executing (via popen()) the command:
+#
+# <filter> <input-file>
+#
+# where <filter> is the value of the INPUT_FILTER tag, and <input-file> is the
+# name of an input file. Doxygen will then use the output that the filter
+# program writes to standard output. If FILTER_PATTERNS is specified, this tag
+# will be ignored.
+#
+# Note that the filter must not add or remove lines; it is applied before the
+# code is scanned, but not when the output code is generated. If lines are added
+# or removed, the anchors will not be placed correctly.
+
+INPUT_FILTER =
+
+# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern
+# basis. Doxygen will compare the file name with each pattern and apply the
+# filter if there is a match. The filters are a list of the form: pattern=filter
+# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how
+# filters are used. If the FILTER_PATTERNS tag is empty or if none of the
+# patterns match the file name, INPUT_FILTER is applied.
+
+FILTER_PATTERNS =
+
+# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using
+# INPUT_FILTER ) will also be used to filter the input files that are used for
+# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES).
+# The default value is: NO.
+
+FILTER_SOURCE_FILES = NO
+
+# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file
+# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and
+# it is also possible to disable source filtering for a specific pattern using
+# *.ext= (so without naming a filter).
+# This tag requires that the tag FILTER_SOURCE_FILES is set to YES.
+
+FILTER_SOURCE_PATTERNS =
+
+# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that
+# is part of the input, its contents will be placed on the main page
+# (index.html). This can be useful if you have a project on for instance GitHub
+# and want to reuse the introduction page also for the doxygen output.
+
+USE_MDFILE_AS_MAINPAGE =
+
+#---------------------------------------------------------------------------
+# Configuration options related to source browsing
+#---------------------------------------------------------------------------
+
+# If the SOURCE_BROWSER tag is set to YES then a list of source files will be
+# generated. Documented entities will be cross-referenced with these sources.
+#
+# Note: To get rid of all source code in the generated output, make sure that
+# also VERBATIM_HEADERS is set to NO.
+# The default value is: NO.
+
+SOURCE_BROWSER = NO
+
+# Setting the INLINE_SOURCES tag to YES will include the body of functions,
+# classes and enums directly into the documentation.
+# The default value is: NO.
+
+INLINE_SOURCES = NO
+
+# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any
+# special comment blocks from generated source code fragments. Normal C, C++ and
+# Fortran comments will always remain visible.
+# The default value is: YES.
+
+STRIP_CODE_COMMENTS = YES
+
+# If the REFERENCED_BY_RELATION tag is set to YES then for each documented
+# function all documented functions referencing it will be listed.
+# The default value is: NO.
+
+REFERENCED_BY_RELATION = NO
+
+# If the REFERENCES_RELATION tag is set to YES then for each documented function
+# all documented entities called/used by that function will be listed.
+# The default value is: NO.
+
+REFERENCES_RELATION = NO
+
+# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set
+# to YES, then the hyperlinks from functions in REFERENCES_RELATION and
+# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will
+# link to the documentation.
+# The default value is: YES.
+
+REFERENCES_LINK_SOURCE = YES
+
+# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the
+# source code will show a tooltip with additional information such as prototype,
+# brief description and links to the definition and documentation. Since this
+# will make the HTML file larger and loading of large files a bit slower, you
+# can opt to disable this feature.
+# The default value is: YES.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+SOURCE_TOOLTIPS = YES
+
+# If the USE_HTAGS tag is set to YES then the references to source code will
+# point to the HTML generated by the htags(1) tool instead of doxygen built-in
+# source browser. The htags tool is part of GNU's global source tagging system
+# (see http://www.gnu.org/software/global/global.html). You will need version
+# 4.8.6 or higher.
+#
+# To use it do the following:
+# - Install the latest version of global
+# - Enable SOURCE_BROWSER and USE_HTAGS in the config file
+# - Make sure the INPUT points to the root of the source tree
+# - Run doxygen as normal
+#
+# Doxygen will invoke htags (and that will in turn invoke gtags), so these
+# tools must be available from the command line (i.e. in the search path).
+#
+# The result: instead of the source browser generated by doxygen, the links to
+# source code will now point to the output of htags.
+# The default value is: NO.
+# This tag requires that the tag SOURCE_BROWSER is set to YES.
+
+USE_HTAGS = NO
+
+# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a
+# verbatim copy of the header file for each class for which an include is
+# specified. Set to NO to disable this.
+# See also: Section \class.
+# The default value is: YES.
+
+VERBATIM_HEADERS = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to the alphabetical class index
+#---------------------------------------------------------------------------
+
+# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all
+# compounds will be generated. Enable this if the project contains a lot of
+# classes, structs, unions or interfaces.
+# The default value is: YES.
+
+ALPHABETICAL_INDEX = YES
+
+# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in
+# which the alphabetical index list will be split.
+# Minimum value: 1, maximum value: 20, default value: 5.
+# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
+
+COLS_IN_ALPHA_INDEX = 5
+
+# In case all classes in a project start with a common prefix, all classes will
+# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
+# can be used to specify a prefix (or a list of prefixes) that should be ignored
+# while generating the index headers.
+# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
+
+IGNORE_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the HTML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_HTML tag is set to YES doxygen will generate HTML output
+# The default value is: YES.
+
+GENERATE_HTML = YES
+
+# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_OUTPUT = html
+
+# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each
+# generated HTML page (for example: .htm, .php, .asp).
+# The default value is: .html.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FILE_EXTENSION = .html
+
+# The HTML_HEADER tag can be used to specify a user-defined HTML header file for
+# each generated HTML page. If the tag is left blank doxygen will generate a
+# standard header.
+#
+# To get valid HTML the header file that includes any scripts and style sheets
+# that doxygen needs, which is dependent on the configuration options used (e.g.
+# the setting GENERATE_TREEVIEW). It is highly recommended to start with a
+# default header using
+# doxygen -w html new_header.html new_footer.html new_stylesheet.css
+# YourConfigFile
+# and then modify the file new_header.html. See also section "Doxygen usage"
+# for information on how to generate the default header that doxygen normally
+# uses.
+# Note: The header is subject to change so you typically have to regenerate the
+# default header when upgrading to a newer version of doxygen. For a description
+# of the possible markers and block names see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_HEADER =
+
+# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each
+# generated HTML page. If the tag is left blank doxygen will generate a standard
+# footer. See HTML_HEADER for more information on how to generate a default
+# footer and what special commands can be used inside the footer. See also
+# section "Doxygen usage" for information on how to generate the default footer
+# that doxygen normally uses.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_FOOTER =
+
+# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style
+# sheet that is used by each HTML page. It can be used to fine-tune the look of
+# the HTML output. If left blank doxygen will generate a default style sheet.
+# See also section "Doxygen usage" for information on how to generate the style
+# sheet that doxygen normally uses.
+# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as
+# it is more robust and this tag (HTML_STYLESHEET) will in the future become
+# obsolete.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_STYLESHEET =
+
+# The HTML_EXTRA_STYLESHEET tag can be used to specify an additional user-
+# defined cascading style sheet that is included after the standard style sheets
+# created by doxygen. Using this option one can overrule certain style aspects.
+# This is preferred over using HTML_STYLESHEET since it does not replace the
+# standard style sheet and is therefor more robust against future updates.
+# Doxygen will copy the style sheet file to the output directory. For an example
+# see the documentation.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_STYLESHEET =
+
+# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the HTML output directory. Note
+# that these files will be copied to the base HTML output directory. Use the
+# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these
+# files. In the HTML_STYLESHEET file, use the file name only. Also note that the
+# files will be copied as-is; there are no commands or markers available.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_EXTRA_FILES =
+
+# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen
+# will adjust the colors in the stylesheet and background images according to
+# this color. Hue is specified as an angle on a colorwheel, see
+# http://en.wikipedia.org/wiki/Hue for more information. For instance the value
+# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300
+# purple, and 360 is red again.
+# Minimum value: 0, maximum value: 359, default value: 220.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_HUE = 220
+
+# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors
+# in the HTML output. For a value of 0 the output will use grayscales only. A
+# value of 255 will produce the most vivid colors.
+# Minimum value: 0, maximum value: 255, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_SAT = 100
+
+# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the
+# luminance component of the colors in the HTML output. Values below 100
+# gradually make the output lighter, whereas values above 100 make the output
+# darker. The value divided by 100 is the actual gamma applied, so 80 represents
+# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not
+# change the gamma.
+# Minimum value: 40, maximum value: 240, default value: 80.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_COLORSTYLE_GAMMA = 80
+
+# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML
+# page will contain the date and time when the page was generated. Setting this
+# to NO can help when comparing the output of multiple runs.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_TIMESTAMP = NO
+
+# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML
+# documentation will contain sections that can be hidden and shown after the
+# page has loaded.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_DYNAMIC_SECTIONS = NO
+
+# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries
+# shown in the various tree structured indices initially; the user can expand
+# and collapse entries dynamically later on. Doxygen will expand the tree to
+# such a level that at most the specified number of entries are visible (unless
+# a fully collapsed tree already exceeds this amount). So setting the number of
+# entries 1 will produce a full collapsed tree by default. 0 is a special value
+# representing an infinite number of entries and will result in a full expanded
+# tree by default.
+# Minimum value: 0, maximum value: 9999, default value: 100.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+HTML_INDEX_NUM_ENTRIES = 100
+
+# If the GENERATE_DOCSET tag is set to YES, additional index files will be
+# generated that can be used as input for Apple's Xcode 3 integrated development
+# environment (see: http://developer.apple.com/tools/xcode/), introduced with
+# OSX 10.5 (Leopard). To create a documentation set, doxygen will generate a
+# Makefile in the HTML output directory. Running make will produce the docset in
+# that directory and running make install will install the docset in
+# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at
+# startup. See http://developer.apple.com/tools/creatingdocsetswithdoxygen.html
+# for more information.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_DOCSET = NO
+
+# This tag determines the name of the docset feed. A documentation feed provides
+# an umbrella under which multiple documentation sets from a single provider
+# (such as a company or product suite) can be grouped.
+# The default value is: Doxygen generated docs.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_FEEDNAME = "Doxygen generated docs"
+
+# This tag specifies a string that should uniquely identify the documentation
+# set bundle. This should be a reverse domain-name style string, e.g.
+# com.mycompany.MyDocSet. Doxygen will append .docset to the name.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_BUNDLE_ID = org.doxygen.Project
+
+# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify
+# the documentation publisher. This should be a reverse domain-name style
+# string, e.g. com.mycompany.MyDocSet.documentation.
+# The default value is: org.doxygen.Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_ID = org.doxygen.Publisher
+
+# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher.
+# The default value is: Publisher.
+# This tag requires that the tag GENERATE_DOCSET is set to YES.
+
+DOCSET_PUBLISHER_NAME = Publisher
+
+# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
+# additional HTML index files: index.hhp, index.hhc, and index.hhk. The
+# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
+# (see: http://www.microsoft.com/en-us/download/details.aspx?id=21138) on
+# Windows.
+#
+# The HTML Help Workshop contains a compiler that can convert all HTML output
+# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
+# files are now used as the Windows 98 help format, and will replace the old
+# Windows help format (.hlp) on all Windows platforms in the future. Compressed
+# HTML files also contain an index, a table of contents, and you can search for
+# words in the documentation. The HTML workshop also contains a viewer for
+# compressed HTML files.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_HTMLHELP = NO
+
+# The CHM_FILE tag can be used to specify the file name of the resulting .chm
+# file. You can add a path in front of the file if the result should not be
+# written to the html output directory.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_FILE =
+
+# The HHC_LOCATION tag can be used to specify the location (absolute path
+# including file name) of the HTML help compiler ( hhc.exe). If non-empty
+# doxygen will try to run the HTML help compiler on the generated index.hhp.
+# The file has to be specified with full path.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+HHC_LOCATION =
+
+# The GENERATE_CHI flag controls if a separate .chi index file is generated (
+# YES) or that it should be included in the master .chm file ( NO).
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+GENERATE_CHI = NO
+
+# The CHM_INDEX_ENCODING is used to encode HtmlHelp index ( hhk), content ( hhc)
+# and project file content.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+CHM_INDEX_ENCODING =
+
+# The BINARY_TOC flag controls whether a binary table of contents is generated (
+# YES) or a normal table of contents ( NO) in the .chm file.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+BINARY_TOC = NO
+
+# The TOC_EXPAND flag can be set to YES to add extra items for group members to
+# the table of contents of the HTML help documentation and to the tree view.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTMLHELP is set to YES.
+
+TOC_EXPAND = NO
+
+# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and
+# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that
+# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help
+# (.qch) of the generated HTML documentation.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_QHP = NO
+
+# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify
+# the file name of the resulting .qch file. The path specified is relative to
+# the HTML output folder.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QCH_FILE =
+
+# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help
+# Project output. For more information please see Qt Help Project / Namespace
+# (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#namespace).
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_NAMESPACE = org.doxygen.Project
+
+# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt
+# Help Project output. For more information please see Qt Help Project / Virtual
+# Folders (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#virtual-
+# folders).
+# The default value is: doc.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_VIRTUAL_FOLDER = doc
+
+# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom
+# filter to add. For more information please see Qt Help Project / Custom
+# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom-
+# filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_NAME =
+
+# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the
+# custom filter to add. For more information please see Qt Help Project / Custom
+# Filters (see: http://qt-project.org/doc/qt-4.8/qthelpproject.html#custom-
+# filters).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_CUST_FILTER_ATTRS =
+
+# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this
+# project's filter section matches. Qt Help Project / Filter Attributes (see:
+# http://qt-project.org/doc/qt-4.8/qthelpproject.html#filter-attributes).
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHP_SECT_FILTER_ATTRS =
+
+# The QHG_LOCATION tag can be used to specify the location of Qt's
+# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the
+# generated .qhp file.
+# This tag requires that the tag GENERATE_QHP is set to YES.
+
+QHG_LOCATION =
+
+# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be
+# generated, together with the HTML files, they form an Eclipse help plugin. To
+# install this plugin and make it available under the help contents menu in
+# Eclipse, the contents of the directory containing the HTML and XML files needs
+# to be copied into the plugins directory of eclipse. The name of the directory
+# within the plugins directory should be the same as the ECLIPSE_DOC_ID value.
+# After copying Eclipse needs to be restarted before the help appears.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_ECLIPSEHELP = NO
+
+# A unique identifier for the Eclipse help plugin. When installing the plugin
+# the directory name containing the HTML and XML files should also have this
+# name. Each documentation set should have its own identifier.
+# The default value is: org.doxygen.Project.
+# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES.
+
+ECLIPSE_DOC_ID = org.doxygen.Project
+
+# If you want full control over the layout of the generated HTML pages it might
+# be necessary to disable the index and replace it with your own. The
+# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top
+# of each HTML page. A value of NO enables the index and the value YES disables
+# it. Since the tabs in the index contain the same information as the navigation
+# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+DISABLE_INDEX = YES
+
+# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index
+# structure should be generated to display hierarchical information. If the tag
+# value is set to YES, a side panel will be generated containing a tree-like
+# index structure (just like the one that is generated for HTML Help). For this
+# to work a browser that supports JavaScript, DHTML, CSS and frames is required
+# (i.e. any modern browser). Windows users are probably better off using the
+# HTML help feature. Via custom stylesheets (see HTML_EXTRA_STYLESHEET) one can
+# further fine-tune the look of the index. As an example, the default style
+# sheet generated by doxygen has an example that shows how to put an image at
+# the root of the tree instead of the PROJECT_NAME. Since the tree basically has
+# the same information as the tab index, you could consider setting
+# DISABLE_INDEX to YES when enabling this option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+GENERATE_TREEVIEW = YES
+
+# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
+# doxygen will group on one line in the generated HTML documentation.
+#
+# Note that a value of 0 will completely suppress the enum values from appearing
+# in the overview section.
+# Minimum value: 0, maximum value: 20, default value: 4.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+ENUM_VALUES_PER_LINE = 4
+
+# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used
+# to set the initial width (in pixels) of the frame in which the tree is shown.
+# Minimum value: 0, maximum value: 1500, default value: 250.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+TREEVIEW_WIDTH = 250
+
+# When the EXT_LINKS_IN_WINDOW option is set to YES doxygen will open links to
+# external symbols imported via tag files in a separate window.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+EXT_LINKS_IN_WINDOW = NO
+
+# Use this tag to change the font size of LaTeX formulas included as images in
+# the HTML documentation. When you change the font size after a successful
+# doxygen run you need to manually remove any form_*.png images from the HTML
+# output directory to force them to be regenerated.
+# Minimum value: 8, maximum value: 50, default value: 10.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_FONTSIZE = 10
+
+# Use the FORMULA_TRANPARENT tag to determine whether or not the images
+# generated for formulas are transparent PNGs. Transparent PNGs are not
+# supported properly for IE 6.0, but are supported on all modern browsers.
+#
+# Note that when changing this option you need to delete any form_*.png files in
+# the HTML output directory before the changes have effect.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+FORMULA_TRANSPARENT = YES
+
+# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see
+# http://www.mathjax.org) which uses client side Javascript for the rendering
+# instead of using prerendered bitmaps. Use this if you do not have LaTeX
+# installed or if you want to formulas look prettier in the HTML output. When
+# enabled you may also need to install MathJax separately and configure the path
+# to it using the MATHJAX_RELPATH option.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+USE_MATHJAX = NO
+
+# When MathJax is enabled you can set the default output format to be used for
+# the MathJax output. See the MathJax site (see:
+# http://docs.mathjax.org/en/latest/output.html) for more details.
+# Possible values are: HTML-CSS (which is slower, but has the best
+# compatibility), NativeMML (i.e. MathML) and SVG.
+# The default value is: HTML-CSS.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_FORMAT = HTML-CSS
+
+# When MathJax is enabled you need to specify the location relative to the HTML
+# output directory using the MATHJAX_RELPATH option. The destination directory
+# should contain the MathJax.js script. For instance, if the mathjax directory
+# is located at the same level as the HTML output directory, then
+# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax
+# Content Delivery Network so you can quickly see the result without installing
+# MathJax. However, it is strongly recommended to install a local copy of
+# MathJax from http://www.mathjax.org before deployment.
+# The default value is: http://cdn.mathjax.org/mathjax/latest.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest
+
+# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax
+# extension names that should be enabled during MathJax rendering. For example
+# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_EXTENSIONS =
+
+# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces
+# of code that will be used on startup of the MathJax code. See the MathJax site
+# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an
+# example see the documentation.
+# This tag requires that the tag USE_MATHJAX is set to YES.
+
+MATHJAX_CODEFILE =
+
+# When the SEARCHENGINE tag is enabled doxygen will generate a search box for
+# the HTML output. The underlying search engine uses javascript and DHTML and
+# should work on any modern browser. Note that when using HTML help
+# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET)
+# there is already a search function so this one should typically be disabled.
+# For large projects the javascript based search engine can be slow, then
+# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to
+# search using the keyboard; to jump to the search box use <access key> + S
+# (what the <access key> is depends on the OS and browser, but it is typically
+# <CTRL>, <ALT>/<option>, or both). Inside the search box use the <cursor down
+# key> to jump into the search results window, the results can be navigated
+# using the <cursor keys>. Press <Enter> to select an item or <escape> to cancel
+# the search. The filter options can be selected when the cursor is inside the
+# search box by pressing <Shift>+<cursor down>. Also here use the <cursor keys>
+# to select a filter and <Enter> or <escape> to activate or cancel the filter
+# option.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_HTML is set to YES.
+
+SEARCHENGINE = YES
+
+# When the SERVER_BASED_SEARCH tag is enabled the search engine will be
+# implemented using a web server instead of a web client using Javascript. There
+# are two flavours of web server based searching depending on the
+# EXTERNAL_SEARCH setting. When disabled, doxygen will generate a PHP script for
+# searching and an index file used by the script. When EXTERNAL_SEARCH is
+# enabled the indexing and searching needs to be provided by external tools. See
+# the section "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SERVER_BASED_SEARCH = NO
+
+# When EXTERNAL_SEARCH tag is enabled doxygen will no longer generate the PHP
+# script for searching. Instead the search results are written to an XML file
+# which needs to be processed by an external indexer. Doxygen will invoke an
+# external search engine pointed to by the SEARCHENGINE_URL option to obtain the
+# search results.
+#
+# Doxygen ships with an example indexer ( doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see: http://xapian.org/).
+#
+# See the section "External Indexing and Searching" for details.
+# The default value is: NO.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH = NO
+
+# The SEARCHENGINE_URL should point to a search engine hosted by a web server
+# which will return the search results when EXTERNAL_SEARCH is enabled.
+#
+# Doxygen ships with an example indexer ( doxyindexer) and search engine
+# (doxysearch.cgi) which are based on the open source search engine library
+# Xapian (see: http://xapian.org/). See the section "External Indexing and
+# Searching" for details.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHENGINE_URL =
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the unindexed
+# search data is written to a file for indexing by an external tool. With the
+# SEARCHDATA_FILE tag the name of this file can be specified.
+# The default file is: searchdata.xml.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+SEARCHDATA_FILE = searchdata.xml
+
+# When SERVER_BASED_SEARCH and EXTERNAL_SEARCH are both enabled the
+# EXTERNAL_SEARCH_ID tag can be used as an identifier for the project. This is
+# useful in combination with EXTRA_SEARCH_MAPPINGS to search through multiple
+# projects and redirect the results back to the right project.
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTERNAL_SEARCH_ID =
+
+# The EXTRA_SEARCH_MAPPINGS tag can be used to enable searching through doxygen
+# projects other than the one defined by this configuration file, but that are
+# all added to the same external search index. Each project needs to have a
+# unique id set via EXTERNAL_SEARCH_ID. The search mapping then maps the id of
+# to a relative location where the documentation can be found. The format is:
+# EXTRA_SEARCH_MAPPINGS = tagname1=loc1 tagname2=loc2 ...
+# This tag requires that the tag SEARCHENGINE is set to YES.
+
+EXTRA_SEARCH_MAPPINGS =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the LaTeX output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_LATEX tag is set to YES doxygen will generate LaTeX output.
+# The default value is: YES.
+
+GENERATE_LATEX = NO
+
+# The LATEX_OUTPUT tag is used to specify where the LaTeX docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: latex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_OUTPUT = latex
+
+# The LATEX_CMD_NAME tag can be used to specify the LaTeX command name to be
+# invoked.
+#
+# Note that when enabling USE_PDFLATEX this option is only used for generating
+# bitmaps for formulas in the HTML output, but not in the Makefile that is
+# written to the output directory.
+# The default file is: latex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_CMD_NAME = latex
+
+# The MAKEINDEX_CMD_NAME tag can be used to specify the command name to generate
+# index for LaTeX.
+# The default file is: makeindex.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+MAKEINDEX_CMD_NAME = makeindex
+
+# If the COMPACT_LATEX tag is set to YES doxygen generates more compact LaTeX
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+COMPACT_LATEX = NO
+
+# The PAPER_TYPE tag can be used to set the paper type that is used by the
+# printer.
+# Possible values are: a4 (210 x 297 mm), letter (8.5 x 11 inches), legal (8.5 x
+# 14 inches) and executive (7.25 x 10.5 inches).
+# The default value is: a4.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PAPER_TYPE = a4
+
+# The EXTRA_PACKAGES tag can be used to specify one or more LaTeX package names
+# that should be included in the LaTeX output. To get the times font for
+# instance you can specify
+# EXTRA_PACKAGES=times
+# If left blank no extra packages will be included.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+EXTRA_PACKAGES =
+
+# The LATEX_HEADER tag can be used to specify a personal LaTeX header for the
+# generated LaTeX document. The header should contain everything until the first
+# chapter. If it is left blank doxygen will generate a standard header. See
+# section "Doxygen usage" for information on how to let doxygen write the
+# default header to a separate file.
+#
+# Note: Only use a user-defined header if you know what you are doing! The
+# following commands have a special meaning inside the header: $title,
+# $datetime, $date, $doxygenversion, $projectname, $projectnumber. Doxygen will
+# replace them by respectively the title of the page, the current date and time,
+# only the current date, the version number of doxygen, the project name (see
+# PROJECT_NAME), or the project number (see PROJECT_NUMBER).
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HEADER =
+
+# The LATEX_FOOTER tag can be used to specify a personal LaTeX footer for the
+# generated LaTeX document. The footer should contain everything after the last
+# chapter. If it is left blank doxygen will generate a standard footer.
+#
+# Note: Only use a user-defined footer if you know what you are doing!
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_FOOTER =
+
+# The LATEX_EXTRA_FILES tag can be used to specify one or more extra images or
+# other source files which should be copied to the LATEX_OUTPUT output
+# directory. Note that the files will be copied as-is; there are no commands or
+# markers available.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_EXTRA_FILES =
+
+# If the PDF_HYPERLINKS tag is set to YES, the LaTeX that is generated is
+# prepared for conversion to PDF (using ps2pdf or pdflatex). The PDF file will
+# contain links (just like the HTML output) instead of page references. This
+# makes the output suitable for online browsing using a PDF viewer.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+PDF_HYPERLINKS = YES
+
+# If the LATEX_PDFLATEX tag is set to YES, doxygen will use pdflatex to generate
+# the PDF file directly from the LaTeX files. Set this option to YES to get a
+# higher quality PDF documentation.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+USE_PDFLATEX = YES
+
+# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \batchmode
+# command to the generated LaTeX files. This will instruct LaTeX to keep running
+# if errors occur, instead of asking the user for help. This option is also used
+# when generating formulas in HTML.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BATCHMODE = NO
+
+# If the LATEX_HIDE_INDICES tag is set to YES then doxygen will not include the
+# index chapters (such as File Index, Compound Index, etc.) in the output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_HIDE_INDICES = NO
+
+# If the LATEX_SOURCE_CODE tag is set to YES then doxygen will include source
+# code with syntax highlighting in the LaTeX output.
+#
+# Note that which sources are shown also depends on other settings such as
+# SOURCE_BROWSER.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_SOURCE_CODE = NO
+
+# The LATEX_BIB_STYLE tag can be used to specify the style to use for the
+# bibliography, e.g. plainnat, or ieeetr. See
+# http://en.wikipedia.org/wiki/BibTeX and \cite for more info.
+# The default value is: plain.
+# This tag requires that the tag GENERATE_LATEX is set to YES.
+
+LATEX_BIB_STYLE = plain
+
+#---------------------------------------------------------------------------
+# Configuration options related to the RTF output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_RTF tag is set to YES doxygen will generate RTF output. The
+# RTF output is optimized for Word 97 and may not look too pretty with other RTF
+# readers/editors.
+# The default value is: NO.
+
+GENERATE_RTF = NO
+
+# The RTF_OUTPUT tag is used to specify where the RTF docs will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: rtf.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_OUTPUT = rtf
+
+# If the COMPACT_RTF tag is set to YES doxygen generates more compact RTF
+# documents. This may be useful for small projects and may help to save some
+# trees in general.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+COMPACT_RTF = NO
+
+# If the RTF_HYPERLINKS tag is set to YES, the RTF that is generated will
+# contain hyperlink fields. The RTF file will contain links (just like the HTML
+# output) instead of page references. This makes the output suitable for online
+# browsing using Word or some other Word compatible readers that support those
+# fields.
+#
+# Note: WordPad (write) and others do not support links.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_HYPERLINKS = NO
+
+# Load stylesheet definitions from file. Syntax is similar to doxygen's config
+# file, i.e. a series of assignments. You only have to provide replacements,
+# missing definitions are set to their default value.
+#
+# See also section "Doxygen usage" for information on how to generate the
+# default style sheet that doxygen normally uses.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_STYLESHEET_FILE =
+
+# Set optional variables used in the generation of an RTF document. Syntax is
+# similar to doxygen's config file. A template extensions file can be generated
+# using doxygen -e rtf extensionFile.
+# This tag requires that the tag GENERATE_RTF is set to YES.
+
+RTF_EXTENSIONS_FILE =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the man page output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_MAN tag is set to YES doxygen will generate man pages for
+# classes and files.
+# The default value is: NO.
+
+GENERATE_MAN = NO
+
+# The MAN_OUTPUT tag is used to specify where the man pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it. A directory man3 will be created inside the directory specified by
+# MAN_OUTPUT.
+# The default directory is: man.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_OUTPUT = man
+
+# The MAN_EXTENSION tag determines the extension that is added to the generated
+# man pages. In case the manual section does not start with a number, the number
+# 3 is prepended. The dot (.) at the beginning of the MAN_EXTENSION tag is
+# optional.
+# The default value is: .3.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_EXTENSION = .3
+
+# If the MAN_LINKS tag is set to YES and doxygen generates man output, then it
+# will generate one additional man file for each entity documented in the real
+# man page(s). These additional files only source the real man page, but without
+# them the man command would be unable to find the correct page.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_MAN is set to YES.
+
+MAN_LINKS = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the XML output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_XML tag is set to YES doxygen will generate an XML file that
+# captures the structure of the code including all documentation.
+# The default value is: NO.
+
+GENERATE_XML = NO
+
+# The XML_OUTPUT tag is used to specify where the XML pages will be put. If a
+# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of
+# it.
+# The default directory is: xml.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_OUTPUT = xml
+
+# The XML_SCHEMA tag can be used to specify a XML schema, which can be used by a
+# validating XML parser to check the syntax of the XML files.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_SCHEMA =
+
+# The XML_DTD tag can be used to specify a XML DTD, which can be used by a
+# validating XML parser to check the syntax of the XML files.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_DTD =
+
+# If the XML_PROGRAMLISTING tag is set to YES doxygen will dump the program
+# listings (including syntax highlighting and cross-referencing information) to
+# the XML output. Note that enabling this will significantly increase the size
+# of the XML output.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_XML is set to YES.
+
+XML_PROGRAMLISTING = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to the DOCBOOK output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_DOCBOOK tag is set to YES doxygen will generate Docbook files
+# that can be used to generate PDF.
+# The default value is: NO.
+
+GENERATE_DOCBOOK = NO
+
+# The DOCBOOK_OUTPUT tag is used to specify where the Docbook pages will be put.
+# If a relative path is entered the value of OUTPUT_DIRECTORY will be put in
+# front of it.
+# The default directory is: docbook.
+# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
+
+DOCBOOK_OUTPUT = docbook
+
+#---------------------------------------------------------------------------
+# Configuration options for the AutoGen Definitions output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_AUTOGEN_DEF tag is set to YES doxygen will generate an AutoGen
+# Definitions (see http://autogen.sf.net) file that captures the structure of
+# the code including all documentation. Note that this feature is still
+# experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_AUTOGEN_DEF = NO
+
+#---------------------------------------------------------------------------
+# Configuration options related to the Perl module output
+#---------------------------------------------------------------------------
+
+# If the GENERATE_PERLMOD tag is set to YES doxygen will generate a Perl module
+# file that captures the structure of the code including all documentation.
+#
+# Note that this feature is still experimental and incomplete at the moment.
+# The default value is: NO.
+
+GENERATE_PERLMOD = NO
+
+# If the PERLMOD_LATEX tag is set to YES doxygen will generate the necessary
+# Makefile rules, Perl scripts and LaTeX code to be able to generate PDF and DVI
+# output from the Perl module output.
+# The default value is: NO.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_LATEX = NO
+
+# If the PERLMOD_PRETTY tag is set to YES the Perl module output will be nicely
+# formatted so it can be parsed by a human reader. This is useful if you want to
+# understand what is going on. On the other hand, if this tag is set to NO the
+# size of the Perl module output will be much smaller and Perl will parse it
+# just the same.
+# The default value is: YES.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_PRETTY = YES
+
+# The names of the make variables in the generated doxyrules.make file are
+# prefixed with the string contained in PERLMOD_MAKEVAR_PREFIX. This is useful
+# so different doxyrules.make files included by the same Makefile don't
+# overwrite each other's variables.
+# This tag requires that the tag GENERATE_PERLMOD is set to YES.
+
+PERLMOD_MAKEVAR_PREFIX =
+
+#---------------------------------------------------------------------------
+# Configuration options related to the preprocessor
+#---------------------------------------------------------------------------
+
+# If the ENABLE_PREPROCESSING tag is set to YES doxygen will evaluate all
+# C-preprocessor directives found in the sources and include files.
+# The default value is: YES.
+
+ENABLE_PREPROCESSING = YES
+
+# If the MACRO_EXPANSION tag is set to YES doxygen will expand all macro names
+# in the source code. If set to NO only conditional compilation will be
+# performed. Macro expansion can be done in a controlled way by setting
+# EXPAND_ONLY_PREDEF to YES.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+MACRO_EXPANSION = NO
+
+# If the EXPAND_ONLY_PREDEF and MACRO_EXPANSION tags are both set to YES then
+# the macro expansion is limited to the macros specified with the PREDEFINED and
+# EXPAND_AS_DEFINED tags.
+# The default value is: NO.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_ONLY_PREDEF = NO
+
+# If the SEARCH_INCLUDES tag is set to YES the includes files in the
+# INCLUDE_PATH will be searched if a #include is found.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SEARCH_INCLUDES = YES
+
+# The INCLUDE_PATH tag can be used to specify one or more directories that
+# contain include files that are not input files but should be processed by the
+# preprocessor.
+# This tag requires that the tag SEARCH_INCLUDES is set to YES.
+
+INCLUDE_PATH =
+
+# You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
+# patterns (like *.h and *.hpp) to filter out the header-files in the
+# directories. If left blank, the patterns specified with FILE_PATTERNS will be
+# used.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+INCLUDE_FILE_PATTERNS =
+
+# The PREDEFINED tag can be used to specify one or more macro names that are
+# defined before the preprocessor is started (similar to the -D option of e.g.
+# gcc). The argument of the tag is a list of macros of the form: name or
+# name=definition (no spaces). If the definition and the "=" are omitted, "=1"
+# is assumed. To prevent a macro definition from being undefined via #undef or
+# recursively expanded use the := operator instead of the = operator.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+PREDEFINED = LV_HAVE_GENERIC \
+ LV_HAVE_SSE \
+ LV_HAVE_SSE2 \
+ LV_HAVE_NEON \
+ LV_HAVE_AVX \
+ LV_HAVE_SSE4_2 \
+ LV_HAVE_SSE3 \
+ LV_HAVE_SSSE3
+
+# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this
+# tag can be used to specify a list of macro names that should be expanded. The
+# macro definition that is found in the sources will be used. Use the PREDEFINED
+# tag if you want to use a different macro definition that overrules the
+# definition found in the source code.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+EXPAND_AS_DEFINED =
+
+# If the SKIP_FUNCTION_MACROS tag is set to YES then doxygen's preprocessor will
+# remove all refrences to function-like macros that are alone on a line, have an
+# all uppercase name, and do not end with a semicolon. Such function macros are
+# typically used for boiler-plate code, and will confuse the parser if not
+# removed.
+# The default value is: YES.
+# This tag requires that the tag ENABLE_PREPROCESSING is set to YES.
+
+SKIP_FUNCTION_MACROS = YES
+
+#---------------------------------------------------------------------------
+# Configuration options related to external references
+#---------------------------------------------------------------------------
+
+# The TAGFILES tag can be used to specify one or more tag files. For each tag
+# file the location of the external documentation should be added. The format of
+# a tag file without this location is as follows:
+# TAGFILES = file1 file2 ...
+# Adding location for the tag files is done as follows:
+# TAGFILES = file1=loc1 "file2 = loc2" ...
+# where loc1 and loc2 can be relative or absolute paths or URLs. See the
+# section "Linking to external documentation" for more information about the use
+# of tag files.
+# Note: Each tag file must have an unique name (where the name does NOT include
+# the path). If a tag file is not located in the directory in which doxygen is
+# run, you must also specify the path to the tagfile here.
+
+TAGFILES =
+
+# When a file name is specified after GENERATE_TAGFILE, doxygen will create a
+# tag file that is based on the input files it reads. See section "Linking to
+# external documentation" for more information about the usage of tag files.
+
+GENERATE_TAGFILE =
+
+# If the ALLEXTERNALS tag is set to YES all external class will be listed in the
+# class index. If set to NO only the inherited external classes will be listed.
+# The default value is: NO.
+
+ALLEXTERNALS = NO
+
+# If the EXTERNAL_GROUPS tag is set to YES all external groups will be listed in
+# the modules index. If set to NO, only the current project's groups will be
+# listed.
+# The default value is: YES.
+
+EXTERNAL_GROUPS = YES
+
+# If the EXTERNAL_PAGES tag is set to YES all external pages will be listed in
+# the related pages index. If set to NO, only the current project's pages will
+# be listed.
+# The default value is: YES.
+
+EXTERNAL_PAGES = YES
+
+# The PERL_PATH should be the absolute path and name of the perl script
+# interpreter (i.e. the result of 'which perl').
+# The default file (with absolute path) is: /usr/bin/perl.
+
+PERL_PATH = /usr/bin/perl
+
+#---------------------------------------------------------------------------
+# Configuration options related to the dot tool
+#---------------------------------------------------------------------------
+
+# If the CLASS_DIAGRAMS tag is set to YES doxygen will generate a class diagram
+# (in HTML and LaTeX) for classes with base or super classes. Setting the tag to
+# NO turns the diagrams off. Note that this option also works with HAVE_DOT
+# disabled, but it is recommended to install and use dot, since it yields more
+# powerful graphs.
+# The default value is: YES.
+
+CLASS_DIAGRAMS = NO
+
+# You can define message sequence charts within doxygen comments using the \msc
+# command. Doxygen will then run the mscgen tool (see:
+# http://www.mcternan.me.uk/mscgen/)) to produce the chart and insert it in the
+# documentation. The MSCGEN_PATH tag allows you to specify the directory where
+# the mscgen tool resides. If left empty the tool is assumed to be found in the
+# default search path.
+
+MSCGEN_PATH =
+
+# You can include diagrams made with dia in doxygen documentation. Doxygen will
+# then run dia to produce the diagram and insert it in the documentation. The
+# DIA_PATH tag allows you to specify the directory where the dia binary resides.
+# If left empty dia is assumed to be found in the default search path.
+
+DIA_PATH =
+
+# If set to YES, the inheritance and collaboration graphs will hide inheritance
+# and usage relations if the target is undocumented or is not a class.
+# The default value is: YES.
+
+HIDE_UNDOC_RELATIONS = YES
+
+# If you set the HAVE_DOT tag to YES then doxygen will assume the dot tool is
+# available from the path. This tool is part of Graphviz (see:
+# http://www.graphviz.org/), a graph visualization toolkit from AT&T and Lucent
+# Bell Labs. The other options in this section have no effect if this option is
+# set to NO
+# The default value is: NO.
+
+HAVE_DOT = NO
+
+# The DOT_NUM_THREADS specifies the number of dot invocations doxygen is allowed
+# to run in parallel. When set to 0 doxygen will base this on the number of
+# processors available in the system. You can set it explicitly to a value
+# larger than 0 to get control over the balance between CPU load and processing
+# speed.
+# Minimum value: 0, maximum value: 32, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_NUM_THREADS = 0
+
+# When you want a differently looking font n the dot files that doxygen
+# generates you can specify the font name using DOT_FONTNAME. You need to make
+# sure dot is able to find the font, which can be done by putting it in a
+# standard location or by setting the DOTFONTPATH environment variable or by
+# setting DOT_FONTPATH to the directory containing the font.
+# The default value is: Helvetica.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTNAME = Helvetica
+
+# The DOT_FONTSIZE tag can be used to set the size (in points) of the font of
+# dot graphs.
+# Minimum value: 4, maximum value: 24, default value: 10.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTSIZE = 10
+
+# By default doxygen will tell dot to use the default font as specified with
+# DOT_FONTNAME. If you specify a different font using DOT_FONTNAME you can set
+# the path where dot can find it using this tag.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_FONTPATH =
+
+# If the CLASS_GRAPH tag is set to YES then doxygen will generate a graph for
+# each documented class showing the direct and indirect inheritance relations.
+# Setting this tag to YES will force the CLASS_DIAGRAMS tag to NO.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CLASS_GRAPH = YES
+
+# If the COLLABORATION_GRAPH tag is set to YES then doxygen will generate a
+# graph for each documented class showing the direct and indirect implementation
+# dependencies (inheritance, containment, and class references variables) of the
+# class with other documented classes.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+COLLABORATION_GRAPH = YES
+
+# If the GROUP_GRAPHS tag is set to YES then doxygen will generate a graph for
+# groups, showing the direct groups dependencies.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GROUP_GRAPHS = YES
+
+# If the UML_LOOK tag is set to YES doxygen will generate inheritance and
+# collaboration diagrams in a style similar to the OMG's Unified Modeling
+# Language.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+UML_LOOK = NO
+
+# If the UML_LOOK tag is enabled, the fields and methods are shown inside the
+# class node. If there are many fields or methods and many nodes the graph may
+# become too big to be useful. The UML_LIMIT_NUM_FIELDS threshold limits the
+# number of items for each type to make the size more manageable. Set this to 0
+# for no limit. Note that the threshold may be exceeded by 50% before the limit
+# is enforced. So when you set the threshold to 10, up to 15 fields may appear,
+# but if the number exceeds 15, the total amount of fields shown is limited to
+# 10.
+# Minimum value: 0, maximum value: 100, default value: 10.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+UML_LIMIT_NUM_FIELDS = 10
+
+# If the TEMPLATE_RELATIONS tag is set to YES then the inheritance and
+# collaboration graphs will show the relations between templates and their
+# instances.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+TEMPLATE_RELATIONS = NO
+
+# If the INCLUDE_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are set to
+# YES then doxygen will generate a graph for each documented file showing the
+# direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDE_GRAPH = YES
+
+# If the INCLUDED_BY_GRAPH, ENABLE_PREPROCESSING and SEARCH_INCLUDES tags are
+# set to YES then doxygen will generate a graph for each documented file showing
+# the direct and indirect include dependencies of the file with other documented
+# files.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INCLUDED_BY_GRAPH = YES
+
+# If the CALL_GRAPH tag is set to YES then doxygen will generate a call
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable call graphs for selected
+# functions only using the \callgraph command.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALL_GRAPH = NO
+
+# If the CALLER_GRAPH tag is set to YES then doxygen will generate a caller
+# dependency graph for every global function or class method.
+#
+# Note that enabling this option will significantly increase the time of a run.
+# So in most cases it will be better to enable caller graphs for selected
+# functions only using the \callergraph command.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+CALLER_GRAPH = NO
+
+# If the GRAPHICAL_HIERARCHY tag is set to YES then doxygen will graphical
+# hierarchy of all classes instead of a textual one.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GRAPHICAL_HIERARCHY = YES
+
+# If the DIRECTORY_GRAPH tag is set to YES then doxygen will show the
+# dependencies a directory has on other directories in a graphical way. The
+# dependency relations are determined by the #include relations between the
+# files in the directories.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DIRECTORY_GRAPH = YES
+
+# The DOT_IMAGE_FORMAT tag can be used to set the image format of the images
+# generated by dot.
+# Note: If you choose svg you need to set HTML_FILE_EXTENSION to xhtml in order
+# to make the SVG files visible in IE 9+ (other browsers do not have this
+# requirement).
+# Possible values are: png, jpg, gif and svg.
+# The default value is: png.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_IMAGE_FORMAT = png
+
+# If DOT_IMAGE_FORMAT is set to svg, then this option can be set to YES to
+# enable generation of interactive SVG images that allow zooming and panning.
+#
+# Note that this requires a modern browser other than Internet Explorer. Tested
+# and working are Firefox, Chrome, Safari, and Opera.
+# Note: For IE 9+ you need to set HTML_FILE_EXTENSION to xhtml in order to make
+# the SVG files visible. Older versions of IE do not have SVG support.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+INTERACTIVE_SVG = NO
+
+# The DOT_PATH tag can be used to specify the path where the dot tool can be
+# found. If left blank, it is assumed the dot tool can be found in the path.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_PATH =
+
+# The DOTFILE_DIRS tag can be used to specify one or more directories that
+# contain dot files that are included in the documentation (see the \dotfile
+# command).
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOTFILE_DIRS =
+
+# The MSCFILE_DIRS tag can be used to specify one or more directories that
+# contain msc files that are included in the documentation (see the \mscfile
+# command).
+
+MSCFILE_DIRS =
+
+# The DIAFILE_DIRS tag can be used to specify one or more directories that
+# contain dia files that are included in the documentation (see the \diafile
+# command).
+
+DIAFILE_DIRS =
+
+# The DOT_GRAPH_MAX_NODES tag can be used to set the maximum number of nodes
+# that will be shown in the graph. If the number of nodes in a graph becomes
+# larger than this value, doxygen will truncate the graph, which is visualized
+# by representing a node as a red box. Note that doxygen if the number of direct
+# children of the root node in a graph is already larger than
+# DOT_GRAPH_MAX_NODES then the graph will not be shown at all. Also note that
+# the size of a graph can be further restricted by MAX_DOT_GRAPH_DEPTH.
+# Minimum value: 0, maximum value: 10000, default value: 50.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_GRAPH_MAX_NODES = 50
+
+# The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the graphs
+# generated by dot. A depth value of 3 means that only nodes reachable from the
+# root by following a path via at most 3 edges will be shown. Nodes that lay
+# further from the root node will be omitted. Note that setting this option to 1
+# or 2 may greatly reduce the computation time needed for large code bases. Also
+# note that the size of a graph can be further restricted by
+# DOT_GRAPH_MAX_NODES. Using a depth of 0 means no depth restriction.
+# Minimum value: 0, maximum value: 1000, default value: 0.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+MAX_DOT_GRAPH_DEPTH = 0
+
+# Set the DOT_TRANSPARENT tag to YES to generate images with a transparent
+# background. This is disabled by default, because dot on Windows does not seem
+# to support this out of the box.
+#
+# Warning: Depending on the platform used, enabling this option may lead to
+# badly anti-aliased labels on the edges of a graph (i.e. they become hard to
+# read).
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_TRANSPARENT = NO
+
+# Set the DOT_MULTI_TARGETS tag to YES allow dot to generate multiple output
+# files in one run (i.e. multiple -o and -T options on the command line). This
+# makes dot run faster, but since only newer versions of dot (>1.8.10) support
+# this, this feature is disabled by default.
+# The default value is: NO.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_MULTI_TARGETS = NO
+
+# If the GENERATE_LEGEND tag is set to YES doxygen will generate a legend page
+# explaining the meaning of the various boxes and arrows in the dot generated
+# graphs.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+GENERATE_LEGEND = YES
+
+# If the DOT_CLEANUP tag is set to YES doxygen will remove the intermediate dot
+# files that are used to generate the various graphs.
+# The default value is: YES.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_CLEANUP = YES
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/DoxygenLayout.xml b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/DoxygenLayout.xml
new file mode 100644
index 0000000..c4336e6
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/DoxygenLayout.xml
@@ -0,0 +1,196 @@
+<doxygenlayout version="1.0">
+ <!-- Generated by doxygen 1.8.6 -->
+ <!-- Navigation index tabs for HTML output -->
+ <navindex>
+ <tab type="mainpage" visible="yes" title=""/>
+ <tab type="pages" visible="yes" title="" intro=""/>
+ <tab type="modules" visible="yes" title="" intro=""/>
+ <!--
+ <tab type="namespaces" visible="yes" title="">
+ <tab type="namespacelist" visible="yes" title="" intro=""/>
+ <tab type="namespacemembers" visible="yes" title="" intro=""/>
+ </tab>
+ <tab type="classes" visible="yes" title="">
+ <tab type="classlist" visible="yes" title="" intro=""/>
+ <tab type="classindex" visible="$ALPHABETICAL_INDEX" title=""/>
+ <tab type="hierarchy" visible="yes" title="" intro=""/>
+ <tab type="classmembers" visible="yes" title="" intro=""/>
+ </tab>
+ -->
+ <tab type="files" visible="yes" title="">
+ <tab type="filelist" visible="yes" title="" intro=""/>
+ <tab type="globals" visible="yes" title="" intro=""/>
+ </tab>
+ <tab type="examples" visible="yes" title="" intro=""/>
+ </navindex>
+
+ <!-- Layout definition for a class page -->
+ <class>
+ <briefdescription visible="yes"/>
+ <includes visible="$SHOW_INCLUDE_FILES"/>
+ <inheritancegraph visible="$CLASS_GRAPH"/>
+ <collaborationgraph visible="$COLLABORATION_GRAPH"/>
+ <memberdecl>
+ <nestedclasses visible="yes" title=""/>
+ <publictypes title=""/>
+ <services title=""/>
+ <interfaces title=""/>
+ <publicslots title=""/>
+ <signals title=""/>
+ <publicmethods title=""/>
+ <publicstaticmethods title=""/>
+ <publicattributes title=""/>
+ <publicstaticattributes title=""/>
+ <protectedtypes title=""/>
+ <protectedslots title=""/>
+ <protectedmethods title=""/>
+ <protectedstaticmethods title=""/>
+ <protectedattributes title=""/>
+ <protectedstaticattributes title=""/>
+ <packagetypes title=""/>
+ <packagemethods title=""/>
+ <packagestaticmethods title=""/>
+ <packageattributes title=""/>
+ <packagestaticattributes title=""/>
+ <properties title=""/>
+ <events title=""/>
+ <privatetypes title=""/>
+ <privateslots title=""/>
+ <privatemethods title=""/>
+ <privatestaticmethods title=""/>
+ <privateattributes title=""/>
+ <privatestaticattributes title=""/>
+ <friends title=""/>
+ <related title="" subtitle=""/>
+ <membergroups visible="yes"/>
+ </memberdecl>
+ <detaileddescription title=""/>
+ <memberdef>
+ <inlineclasses title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <services title=""/>
+ <interfaces title=""/>
+ <constructors title=""/>
+ <functions title=""/>
+ <related title=""/>
+ <variables title=""/>
+ <properties title=""/>
+ <events title=""/>
+ </memberdef>
+ <allmemberslink visible="yes"/>
+ <usedfiles visible="$SHOW_USED_FILES"/>
+ <authorsection visible="yes"/>
+ </class>
+
+ <!-- Layout definition for a namespace page -->
+ <namespace>
+ <briefdescription visible="yes"/>
+ <memberdecl>
+ <nestednamespaces visible="yes" title=""/>
+ <constantgroups visible="yes" title=""/>
+ <classes visible="yes" title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ <membergroups visible="yes"/>
+ </memberdecl>
+ <detaileddescription title=""/>
+ <memberdef>
+ <inlineclasses title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ </memberdef>
+ <authorsection visible="yes"/>
+ </namespace>
+
+ <!-- Layout definition for a file page -->
+ <file>
+ <briefdescription visible="yes"/>
+ <includes visible="$SHOW_INCLUDE_FILES"/>
+ <includegraph visible="$INCLUDE_GRAPH"/>
+ <includedbygraph visible="$INCLUDED_BY_GRAPH"/>
+ <sourcelink visible="yes"/>
+ <memberdecl>
+ <classes visible="yes" title=""/>
+ <namespaces visible="yes" title=""/>
+ <constantgroups visible="yes" title=""/>
+ <defines title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ <membergroups visible="yes"/>
+ </memberdecl>
+ <detaileddescription title=""/>
+ <memberdef>
+ <inlineclasses title=""/>
+ <defines title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ </memberdef>
+ <authorsection/>
+ </file>
+
+ <!-- Layout definition for a group page -->
+ <group>
+ <briefdescription visible="yes"/>
+ <groupgraph visible="$GROUP_GRAPHS"/>
+ <memberdecl>
+ <nestedgroups visible="yes" title=""/>
+ <dirs visible="yes" title=""/>
+ <files visible="yes" title=""/>
+ <namespaces visible="yes" title=""/>
+ <classes visible="yes" title=""/>
+ <defines title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <enumvalues title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ <signals title=""/>
+ <publicslots title=""/>
+ <protectedslots title=""/>
+ <privateslots title=""/>
+ <events title=""/>
+ <properties title=""/>
+ <friends title=""/>
+ <membergroups visible="yes"/>
+ </memberdecl>
+ <detaileddescription title=""/>
+ <memberdef>
+ <pagedocs/>
+ <inlineclasses title=""/>
+ <defines title=""/>
+ <typedefs title=""/>
+ <enums title=""/>
+ <enumvalues title=""/>
+ <functions title=""/>
+ <variables title=""/>
+ <signals title=""/>
+ <publicslots title=""/>
+ <protectedslots title=""/>
+ <privateslots title=""/>
+ <events title=""/>
+ <properties title=""/>
+ <friends title=""/>
+ </memberdef>
+ <authorsection visible="yes"/>
+ </group>
+
+ <!-- Layout definition for a directory page -->
+ <directory>
+ <briefdescription visible="yes"/>
+ <directorygraph visible="yes"/>
+ <memberdecl>
+ <dirs visible="yes"/>
+ <files visible="yes"/>
+ </memberdecl>
+ <detaileddescription title=""/>
+ </directory>
+</doxygenlayout>
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/README.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/README.txt
index 9a36297..faff363 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/README.txt
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/README.txt
@@ -1,20 +1,21 @@
+This is VOLK_GNSSSDR, the Vector Optimized Library of Kernels for GNSS-SDR
-########################################################################
-# Adding proto-kernels to the module
-########################################################################
-
1) Add your proto-kernels inside the kernels/ folder, and the ORC implementations inside the orc/ folder. Add the macros implementations inside the /kernels/CommonMacros folder. (those folders are found in the root of the volk_gnsssdr module)
-
2) Add one profiling line for each of the proto-kernels inside the /apps/volk_gnsssdr_profile.cc file.
-3) Add one test line for each of the proto-kernels inside the /lib/testqa.cc file.
########################################################################
-# Modifications to allow profiling of some proto-kernels with special parameters
-########################################################################
Some of the proto-kernels that GNSS-SDR needs are not supported by the profiling environment of the volk_gnsssdr module. In order to profile them some modifications need to be done to two files:
1) src/algorithms/libs/volk_gnsssdr/lib/qa_utils.cc At the first part of this file there are defined the parameters supported by the environment. The number after run_cast_test indicates the total number of parameters passed to the proto-kernel (input +output parameters). The other part indicates the type of the data passed. Inside func(....) you will need to add the same number of buffs[ ] that the one specified after run_cast_test.
+Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
-2) src/algorithms/libs/volk_gnsssdr/lib/qa_utils.h In the header you will need to add typedefs for the new definitions made in the .cc file. Take care: you will need to add the same number of void * that the one specified after run_cast_test.
+This file is part of GNSS-SDR.
-3) To be able to use volk_gnsssdr and default volk functions at the same time in the same file, it is required to add the template files that volk_gnsssdr module uses at build time to generate some headers.
-The files are found inside tmpl/:
volk_gnsssdr.tmpl.h
-volk_gnsssdr_typedefs.tmpl.h
-volk_gnsssdr_machines.tmpl.h
-volk_gnsssdr_cpu.tmpl.h
-volk_gnsssdr_config_fixed.tmpl.h
+GNSS-SDR is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+GNSS-SDR is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+
\ No newline at end of file
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/CMakeLists.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/CMakeLists.txt
index 1adcc4e..7778a80 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/CMakeLists.txt
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/CMakeLists.txt
@@ -20,8 +20,6 @@
########################################################################
# Setup profiler
########################################################################
-if(Boost_FOUND)
-
if(MSVC)
include_directories(${CMAKE_SOURCE_DIR}/cmake/msvc)
endif(MSVC)
@@ -36,21 +34,26 @@ include_directories(
${Boost_INCLUDE_DIRS}
)
-
if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(Clang_required_link "c++")
elseif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
set(Clang_required_link "")
endif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+
# MAKE volk_gnsssdr_profile
add_executable(volk_gnsssdr_profile
${CMAKE_CURRENT_SOURCE_DIR}/volk_gnsssdr_profile.cc
${CMAKE_SOURCE_DIR}/lib/qa_utils.cc
)
-target_link_libraries(volk_gnsssdr_profile volk_gnsssdr ${Boost_LIBRARIES} ${Clang_required_link})
-add_dependencies(volk_gnsssdr_profile volk_gnsssdr)
+if(ORC_FOUND)
+ set(orc_lib ${ORC_LIBRARIES})
+elseif(ORC_FOUND)
+ set(orc_lib "")
+endif(ORC_FOUND)
+
+target_link_libraries(volk_gnsssdr_profile volk_gnsssdr ${Boost_LIBRARIES} ${Clang_required_link} ${orc_lib})
if(ENABLE_STRIP)
if(CMAKE_COMPILER_IS_GNUCXX AND NOT WIN32)
@@ -59,6 +62,7 @@ if(ENABLE_STRIP)
endif(CMAKE_COMPILER_IS_GNUCXX AND NOT WIN32)
endif(ENABLE_STRIP)
+
install(
TARGETS volk_gnsssdr_profile
DESTINATION bin
@@ -67,13 +71,12 @@ install(
# MAKE volk_gnsssdr-config-info
add_executable(volk_gnsssdr-config-info volk_gnsssdr-config-info.cc)
-target_link_libraries(volk_gnsssdr-config-info volk_gnsssdr ${Boost_LIBRARIES} ${Clang_required_link})
-add_dependencies(volk_gnsssdr-config-info volk_gnsssdr)
-install(
- TARGETS volk_gnsssdr-config-info
- DESTINATION bin
- COMPONENT "volk_gnsssdr"
-)
+target_link_libraries(volk_gnsssdr-config-info volk_gnsssdr ${Boost_LIBRARIES} ${Clang_required_link} ${orc_lib})
+
+#install(
+# TARGETS volk_gnsssdr-config-info
+# DESTINATION bin
+# COMPONENT "volk_gnsssdr"
+#)
-endif(Boost_FOUND)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr-config-info.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr-config-info.cc
index 74ef2df..ab1da03 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr-config-info.cc
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr-config-info.cc
@@ -1,4 +1,3 @@
-/* -*- c++ -*- */
/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
*
* This file is part of GNSS-SDR.
@@ -21,11 +20,10 @@
#include <config.h>
#endif
-#include <iostream>
-#include <boost/program_options.hpp>
-#include "volk_gnsssdr/constants.h"
+#include <volk_gnsssdr/constants.h>
#include "volk_gnsssdr/volk_gnsssdr.h"
-
+#include <boost/program_options.hpp>
+#include <iostream>
namespace po = boost::program_options;
@@ -38,7 +36,6 @@ main(int argc, char **argv)
desc.add_options()
("help,h", "print help message")
("prefix", "print VOLK installation prefix")
- ("builddate", "print VOLK build date (RFC2822 format)")
("cc", "print VOLK C compiler version")
("cflags", "print VOLK CFLAGS")
("all-machines", "print VOLK machines built into library")
@@ -65,9 +62,6 @@ main(int argc, char **argv)
if(vm.count("prefix"))
std::cout << volk_gnsssdr_prefix() << std::endl;
- if(vm.count("builddate"))
- std::cout << volk_gnsssdr_build_date() << std::endl;
-
if(vm.count("version"))
std::cout << volk_gnsssdr_version() << std::endl;
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.cc
index 260dd8d..cdd37f7 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.cc
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.cc
@@ -1,4 +1,3 @@
-/* -*- c++ -*- */
/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
*
* This file is part of GNSS-SDR.
@@ -17,217 +16,334 @@
* along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <sys/stat.h>
-#include <sys/types.h>
+#include "qa_utils.h"
+#include "kernel_tests.h"
+#include "volk_gnsssdr_profile.h"
+
+#include <volk_gnsssdr/volk_gnsssdr.h>
+#include <volk_gnsssdr/volk_gnsssdr_prefs.h>
+
#include <ciso646>
-#include <iostream>
-#include <fstream>
#include <vector>
-#include <boost/foreach.hpp>
#include <boost/filesystem.hpp>
#include <boost/program_options.hpp>
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <volk_gnsssdr/volk_gnsssdr_prefs.h>
-#include "qa_utils.h"
+#include <boost/xpressive/xpressive.hpp>
+#include <iostream>
+#include <fstream>
+#include <sys/stat.h>
+#include <sys/types.h>
namespace fs = boost::filesystem;
-void write_json(std::ofstream &json_file, std::vector<volk_gnsssdr_test_results_t> results)
-{
- json_file << "{" << std::endl;
- json_file << " \"volk_tests\": [" << std::endl;
- size_t len = results.size();
- size_t i = 0;
- BOOST_FOREACH(volk_gnsssdr_test_results_t &result, results) {
- json_file << " {" << std::endl;
- json_file << " \"name\": \"" << result.name << "\"," << std::endl;
- json_file << " \"vlen\": " << result.vlen << "," << std::endl;
- json_file << " \"iter\": " << result.iter << "," << std::endl;
- json_file << " \"best_arch_a\": \"" << result.best_arch_a
- << "\"," << std::endl;
- json_file << " \"best_arch_u\": \"" << result.best_arch_u
- << "\"," << std::endl;
- json_file << " \"results\": {" << std::endl;
- size_t results_len = result.results.size();
- size_t ri = 0;
- typedef std::pair<std::string, volk_gnsssdr_test_time_t> tpair;
- BOOST_FOREACH(tpair pair, result.results)
- {
- volk_gnsssdr_test_time_t time = pair.second;
- json_file << " \"" << time.name << "\": {" << std::endl;
- json_file << " \"name\": \"" << time.name << "\"," << std::endl;
- json_file << " \"time\": " << time.time << "," << std::endl;
- json_file << " \"units\": \"" << time.units << "\"" << std::endl;
- json_file << " }" ;
- if(ri+1 != results_len)
- {
- json_file << ",";
- }
- json_file << std::endl;
- ri++;
- }
- json_file << " }" << std::endl;
- json_file << " }";
- if(i+1 != len)
- {
- json_file << ",";
- }
- json_file << std::endl;
- i++;
- }
- json_file << " ]" << std::endl;
- json_file << "}" << std::endl;
-}
-
-int main(int argc, char *argv[])
-{
+int main(int argc, char *argv[]) {
// Adding program options
boost::program_options::options_description desc("Options");
desc.add_options()
- ("help,h", "Print help messages")
- ("benchmark,b",
- boost::program_options::value<bool>()->default_value( false )
- ->implicit_value( true ),
- "Run all kernels (benchmark mode)")
- ("tests-regex,R",
- boost::program_options::value<std::string>(),
- "Run tests matching regular expression.")
- ("json,j",
- boost::program_options::value<std::string>(),
- "JSON output file")
- ;
+ ("help,h", "Print help messages")
+ ("benchmark,b",
+ boost::program_options::value<bool>()->default_value( false )
+ ->implicit_value( true ),
+ "Run all kernels (benchmark mode)")
+ ("tol,t",
+ boost::program_options::value<float>()->default_value( 1e-6 ),
+ "Set the default error tolerance for tests")
+ ("vlen,v",
+ boost::program_options::value<int>()->default_value( 131071 ),
+ "Set the default vector length for tests") // default is a mersenne prime
+ ("iter,i",
+ boost::program_options::value<int>()->default_value( 1987 ),
+ "Set the default number of test iterations per kernel")
+ ("tests-regex,R",
+ boost::program_options::value<std::string>(),
+ "Run tests matching regular expression.")
+ ("update,u",
+ boost::program_options::value<bool>()->default_value( false )
+ ->implicit_value( true ),
+ "Run only kernels missing from config; use -R to further restrict the candidates")
+ ("dry-run,n",
+ boost::program_options::value<bool>()->default_value( false )
+ ->implicit_value( true ),
+ "Dry run. Respect other options, but don't write to file")
+ ("json,j",
+ boost::program_options::value<std::string>(),
+ "JSON output file")
+ ;
// Handle the options that were given
boost::program_options::variables_map vm;
bool benchmark_mode;
std::string kernel_regex;
- bool store_results = true;
std::ofstream json_file;
+ float def_tol;
+ lv_32fc_t def_scalar;
+ int def_iter;
+ int def_vlen;
+ bool def_benchmark_mode;
+ std::string def_kernel_regex;
+ bool update_mode = false;
+ bool dry_run = false;
+ // Handle the provided options
try {
- boost::program_options::store(boost::program_options::parse_command_line(argc, argv, desc), vm);
- boost::program_options::notify(vm);
- benchmark_mode = vm.count("benchmark")?vm["benchmark"].as<bool>():false;
- if ( vm.count("tests-regex" ) )
- {
- kernel_regex = vm["tests-regex"].as<std::string>();
- store_results = false;
- std::cout << "Warning: using a regexp will not save results to a config" << std::endl;
- }
- else
- {
- kernel_regex = ".*";
- store_results = true;
- }
- } catch (boost::program_options::error& error)
- {
- std::cerr << "Error: " << error.what() << std::endl << std::endl;
- std::cerr << desc << std::endl;
- return 1;
- }
- /** --help option
- */
- if ( vm.count("help") )
- {
- std::cout << "The GNSS-SDR VOLK profiler." << std::endl
- << desc << std::endl;
- return 0;
+ boost::program_options::store(boost::program_options::parse_command_line(argc, argv, desc), vm);
+ boost::program_options::notify(vm);
+ benchmark_mode = vm.count("benchmark")?vm["benchmark"].as<bool>():false;
+ if ( vm.count("tests-regex" ) ) {
+ kernel_regex = vm["tests-regex"].as<std::string>();
+ }
+ else {
+ kernel_regex = ".*";
}
- if ( vm.count("json") )
- {
- json_file.open( vm["json"].as<std::string>().c_str() );
+ def_tol = vm["tol"].as<float>();
+ def_scalar = 327.0;
+ def_vlen = vm["vlen"].as<int>();
+ def_iter = vm["iter"].as<int>();
+ def_benchmark_mode = benchmark_mode;
+ def_kernel_regex = kernel_regex;
+ update_mode = vm["update"].as<bool>();
+ dry_run = vm["dry-run"].as<bool>();
+ }
+ catch (boost::program_options::error& error) {
+ std::cerr << "Error: " << error.what() << std::endl << std::endl;
+ std::cerr << desc << std::endl;
+ return 1;
+ }
+
+ /** --help option */
+ if ( vm.count("help") ) {
+ std::cout << "The VOLK profiler." << std::endl
+ << desc << std::endl;
+ return 0;
+ }
+
+ if ( vm.count("json") ) {
+ std::string filename;
+ try {
+ filename = vm["json"].as<std::string>();
}
+ catch (boost::bad_any_cast& error) {
+ std::cerr << error.what() << std::endl;
+ return 1;
+ }
+ json_file.open( filename.c_str() );
+ }
+ volk_gnsssdr_test_params_t test_params(def_tol, def_scalar, def_vlen, def_iter,
+ def_benchmark_mode, def_kernel_regex);
// Run tests
std::vector<volk_gnsssdr_test_results_t> results;
+ if(update_mode) {
+ read_results(&results);
+ }
- //VOLK_PROFILE(volk_gnsssdr_16i_x5_add_quad_16i_x4, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_16i_branch_4_state_8, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_16i_max_star_16i, 0, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_16i_max_star_horizontal_16i, 0, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_16i_permute_and_scalar_add, 1e-4, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_16i_x4_quad_max_star_16i, 1e-4, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32fc_x2_conjugate_dot_prod_32fc, 1e-4, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32fc_s32f_x2_power_spectral_density_32f, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32f_s32f_32f_fm_detect_32f, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32u_popcnt, 0, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_64u_popcnt, 0, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32fc_s32fc_multiply_32fc, 1e-4, lv_32fc_t(1.0, 0.5), 204602, 1000, &results, benchmark_mode, kernel_regex);
-
- //GNSS-SDR PROTO-KERNELS
- //lv_32fc_t sfv = lv_cmake((float)1, (float)2);
- //example: VOLK_PROFILE(volk_gnsssdr_8ic_s8ic_multiply_8ic, 1e-4, sfv, 204602, 1000, &results, benchmark_mode, kernel_regex);
-
- //CAN NOT BE TESTED YET BECAUSE VOLK MODULE DOES NOT SUPPORT IT:
- //VOLK_PROFILE(volk_gnsssdr_s32f_x2_update_local_carrier_32fc, 1e-4, 0, 16007, 1, &results, benchmark_mode, kernel_regex);
- //VOLK_PROFILE(volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc, 1e-4, 0, 7, 1, &results, benchmark_mode, kernel_regex);
-
- VOLK_PROFILE(volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
-
- VOLK_PROFILE(volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
-
- VOLK_PROFILE(volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
-
- VOLK_PROFILE(volk_gnsssdr_32fc_convert_16ic, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_32fc_convert_8ic, 1e-4, 0, 16000, 250, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_32fc_s32f_convert_8ic, 1e-4, 5, 16000, 250, &results, benchmark_mode, kernel_regex);
-
- VOLK_PROFILE(volk_gnsssdr_8i_accumulator_s8i, 1e-4, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8i_index_max_16u, 3, 0, 204602, 5000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8i_max_s8i, 3, 0, 204602, 5000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8i_x2_add_8i, 1e-4, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_conjugate_8ic, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_magnitude_squared_8i, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_s8ic_multiply_8ic, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_x2_dot_prod_8ic, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8ic_x2_multiply_8ic, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_8u_x2_multiply_8u, 1e-4, 0, 204602, 1000, &results, benchmark_mode, kernel_regex);
- VOLK_PROFILE(volk_gnsssdr_64f_accumulator_64f, 1e-4, 0, 16000, 1000, &results, benchmark_mode, kernel_regex);
- // Until we can update the config on a kernel by kernel basis
- // do not overwrite volk_config when using a regex.
- if(store_results)
- {
- char path[1024];
- volk_gnsssdr_get_config_path(path);
-
- const fs::path config_path(path);
-
- if (not fs::exists(config_path.branch_path()))
- {
- std::cout << "Creating " << config_path.branch_path() << "..." << std::endl;
- fs::create_directories(config_path.branch_path());
+ // Initialize the list of tests
+ // the default test parameters come from options
+ std::vector<volk_gnsssdr_test_case_t> test_cases = init_test_list(test_params);
+ boost::xpressive::sregex kernel_expression;
+ try {
+ kernel_expression = boost::xpressive::sregex::compile(kernel_regex);
+ }
+ catch (boost::xpressive::regex_error& error) {
+ std::cerr << "Error occured while compiling regex" << std::endl << std::endl;
+ return 1;
+ }
+
+ // Iteratate through list of tests running each one
+ for(unsigned int ii = 0; ii < test_cases.size(); ++ii) {
+ bool regex_match = true;
+
+ volk_gnsssdr_test_case_t test_case = test_cases[ii];
+ // if the kernel name matches regex then do the test
+ if(boost::xpressive::regex_search(test_case.name(), kernel_expression)) {
+ regex_match = true;
+ }
+ else {
+ regex_match = false;
+ }
+
+ // if we are in update mode check if we've already got results
+ // if we have any, then no need to test that kernel
+ bool update = true;
+ if(update_mode) {
+ for(unsigned int jj=0; jj < results.size(); ++jj) {
+ if(results[jj].name == test_case.name() ||
+ results[jj].name == test_case.puppet_master_name()) {
+ update = false;
+ break;
}
+ }
+ }
+
+ if( regex_match && update ) {
+ try {
+ run_volk_gnsssdr_tests(test_case.desc(), test_case.kernel_ptr(), test_case.name(),
+ test_case.test_parameters(), &results, test_case.puppet_master_name());
+ }
+ catch (std::string error) {
+ std::cerr << "Caught Exception in 'run_volk_gnsssdr_tests': " << error << std::endl;
+ }
+
+ }
+ }
+
+
+ // Output results according to provided options
+ if(vm.count("json")) {
+ write_json(json_file, results);
+ json_file.close();
+ }
+
+ if(!dry_run) {
+ write_results(&results, false);
+ }
+ else {
+ std::cout << "Warning: this was a dry-run. Config not generated" << std::endl;
+ }
+}
+
+void read_results(std::vector<volk_gnsssdr_test_results_t> *results)
+{
+ char path[1024];
+ volk_gnsssdr_get_config_path(path);
+ const fs::path config_path(path);
+
+ if(fs::exists(config_path)) {
+ // a config exists and we are reading results from it
+ std::ifstream config(config_path.string().c_str());
+ char config_line[256];
+ while(config.getline(config_line, 255)) {
+ // tokenize the input line by kernel_name unaligned aligned
+ // then push back in the results vector with fields filled in
+
+ std::vector<std::string> single_kernel_result;
+ std::string config_str(config_line);
+ std::size_t str_size = config_str.size();
+ std::size_t found = 1;
- std::cout << "Writing " << config_path << "..." << std::endl;
- std::ofstream config(config_path.string().c_str());
- if(!config.is_open())
- { //either we don't have write access or we don't have the dir yet
- std::cout << "Error opening file " << config_path << std::endl;
+ found = config_str.find(" ");
+ // Split line by spaces
+ while(found && found < str_size) {
+ found = config_str.find(" ");
+ // kernel names MUST be less than 128 chars, which is
+ // a length restricted by volk_gnsssdr/volk_gnsssdr_prefs.c
+ // on the last token in the parsed string we won't find a space
+ // so make sure we copy at most 128 chars.
+ if(found > 127) {
+ found = 127;
}
+ str_size = config_str.size();
+ char buffer[128];
+ config_str.copy(buffer, found + 1, 0);
+ buffer[found] = '\0';
+ single_kernel_result.push_back(std::string(buffer));
+ config_str.erase(0, found+1);
+ }
+
+ if(single_kernel_result.size() == 3) {
+ volk_gnsssdr_test_results_t kernel_result;
+ kernel_result.name = std::string(single_kernel_result[0]);
+ kernel_result.config_name = std::string(single_kernel_result[0]);
+ kernel_result.best_arch_u = std::string(single_kernel_result[1]);
+ kernel_result.best_arch_a = std::string(single_kernel_result[2]);
+ results->push_back(kernel_result);
+ }
+ }
+ }
+
+}
+
+void write_results(const std::vector<volk_gnsssdr_test_results_t> *results, bool update_result)
+{
+ char path[1024];
+ volk_gnsssdr_get_config_path(path);
+
+ const fs::path config_path(path);
+
+ // Until we can update the config on a kernel by kernel basis
+ // do not overwrite volk_gnsssdr_config when using a regex.
+ if (not fs::exists(config_path.branch_path()))
+ {
+ std::cout << "Creating " << config_path.branch_path() << "..." << std::endl;
+ fs::create_directories(config_path.branch_path());
+ }
- config << " # this file is generated by volk_gnsssdr_profile.\n # the function name is followed by the preferred architecture.\n";
+ std::ofstream config;
+ if(update_result) {
+ std::cout << "Updating " << config_path << "..." << std::endl;
+ config.open(config_path.string().c_str(), std::ofstream::app);
+ if (!config.is_open()) { //either we don't have write access or we don't have the dir yet
+ std::cout << "Error opening file " << config_path << std::endl;
+ }
+ }
+ else {
+ std::cout << "Writing " << config_path << "..." << std::endl;
+ config.open(config_path.string().c_str());
+ if (!config.is_open()) { //either we don't have write access or we don't have the dir yet
+ std::cout << "Error opening file " << config_path << std::endl;
+ }
+
+ config << "\
+#this file is generated by volk_gnsssdr_profile.\n\
+#the function name is followed by the preferred architecture.\n\
+";
+ }
+
+ std::vector<volk_gnsssdr_test_results_t>::const_iterator profile_results;
+ for(profile_results = results->begin(); profile_results != results->end(); ++profile_results) {
+ config << profile_results->config_name << " "
+ << profile_results->best_arch_a << " "
+ << profile_results->best_arch_u << std::endl;
+ }
+ config.close();
+}
+
+void write_json(std::ofstream &json_file, std::vector<volk_gnsssdr_test_results_t> results)
+{
+ json_file << "{" << std::endl;
+ json_file << " \"volk_gnsssdr_tests\": [" << std::endl;
+ size_t len = results.size();
+ size_t i = 0;
+ std::vector<volk_gnsssdr_test_results_t>::iterator result;
+ for(result = results.begin(); result != results.end(); ++result) {
+ json_file << " {" << std::endl;
+ json_file << " \"name\": \"" << result->name << "\"," << std::endl;
+ json_file << " \"vlen\": " << (int)(result->vlen) << "," << std::endl;
+ json_file << " \"iter\": " << result->iter << "," << std::endl;
+ json_file << " \"best_arch_a\": \"" << result->best_arch_a
+ << "\"," << std::endl;
+ json_file << " \"best_arch_u\": \"" << result->best_arch_u
+ << "\"," << std::endl;
+ json_file << " \"results\": {" << std::endl;
+ size_t results_len = result->results.size();
+ size_t ri = 0;
- BOOST_FOREACH(volk_gnsssdr_test_results_t result, results)
- {
- config << result.config_name << " "
- << result.best_arch_a << " "
- << result.best_arch_u << std::endl;
+ std::map<std::string, volk_gnsssdr_test_time_t>::iterator kernel_time_pair;
+ for(kernel_time_pair = result->results.begin(); kernel_time_pair != result->results.end(); ++kernel_time_pair) {
+ volk_gnsssdr_test_time_t time = kernel_time_pair->second;
+ json_file << " \"" << time.name << "\": {" << std::endl;
+ json_file << " \"name\": \"" << time.name << "\"," << std::endl;
+ json_file << " \"time\": " << time.time << "," << std::endl;
+ json_file << " \"units\": \"" << time.units << "\"" << std::endl;
+ json_file << " }" ;
+ if(ri+1 != results_len) {
+ json_file << ",";
}
- config.close();
+ json_file << std::endl;
+ ri++;
}
- else
- {
- std::cout << "Warning: config not generated" << std::endl;
+ json_file << " }" << std::endl;
+ json_file << " }";
+ if(i+1 != len) {
+ json_file << ",";
}
+ json_file << std::endl;
+ i++;
+ }
+ json_file << " ]" << std::endl;
+ json_file << "}" << std::endl;
}
+
+
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.h
similarity index 50%
copy from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h
copy to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.h
index c0beb4a..357b02f 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/apps/volk_gnsssdr_profile.h
@@ -1,9 +1,13 @@
/*!
- * \file constants.h
- * \brief volk_gnsssdr constants
- * \author Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
+ * \file volk_gnsssdr_profile.h
+ * \author Carles Fernandez-Prades, 2015. cfernandez(at)cttc.es
*
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ * -------------------------------------------------------------------------
+ *
+ * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ *
+ * GNSS-SDR is a software defined Global Navigation
+ * Satellite Systems receiver
*
* This file is part of GNSS-SDR.
*
@@ -19,22 +23,12 @@
*
* You should have received a copy of the GNU General Public License
* along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * -------------------------------------------------------------------------
*/
-#ifndef GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H
-#define GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H
-
-#include <volk_gnsssdr/volk_gnsssdr_common.h>
-
-__VOLK_DECL_BEGIN
-
-VOLK_API char* volk_gnsssdr_prefix();
-VOLK_API char* volk_gnsssdr_build_date();
-VOLK_API char* volk_gnsssdr_version();
-VOLK_API char* volk_gnsssdr_c_compiler();
-VOLK_API char* volk_gnsssdr_compiler_flags();
-VOLK_API char* volk_gnsssdr_available_machines();
-__VOLK_DECL_END
-#endif /* GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H */
+void read_results(std::vector<volk_gnsssdr_test_results_t> *results);
+void write_results(const std::vector<volk_gnsssdr_test_results_t> *results, bool update_result);
+void write_json(std::ofstream &json_file, std::vector<volk_gnsssdr_test_results_t> results);
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/CMakeParseArgumentsCopy.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/CMakeParseArgumentsCopy.cmake
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/CMakeParseArgumentsCopy.cmake
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/CMakeParseArgumentsCopy.cmake
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/FindORC.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/FindORC.cmake
similarity index 99%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/FindORC.cmake
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/FindORC.cmake
index de13b7f..f21513f 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/FindORC.cmake
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/FindORC.cmake
@@ -1,6 +1,9 @@
FIND_PACKAGE(PkgConfig)
PKG_CHECK_MODULES(PC_ORC "orc-0.4 > 0.4.11")
+
+
+
FIND_PROGRAM(ORCC_EXECUTABLE orcc
HINTS ${PC_ORC_TOOLSDIR}
PATHS ${ORC_ROOT}/bin ${CMAKE_INSTALL_PREFIX}/bin)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkAddTest.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkAddTest.cmake
new file mode 100644
index 0000000..28f08d3
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkAddTest.cmake
@@ -0,0 +1,205 @@
+# Copyright 2015 Free Software Foundation, Inc.
+#
+# This file is part of Volk
+#
+# Volk is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# Volk is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
+# License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Volk; see the file COPYING. If not, write to the Free
+# Software Foundation, Inc., 51 Franklin Street, Boston, MA
+# 02110-1301, USA.
+
+if(DEFINED __INCLUDED_VOLK_ADD_TEST)
+ return()
+endif()
+set(__INCLUDED_VOLK_ADD_TEST TRUE)
+
+########################################################################
+# Add a unit test and setup the environment for it.
+# Encloses ADD_TEST, with additional functionality to create a shell
+# script that sets the environment to gain access to in-build binaries
+# properly. The following variables are used to pass in settings:
+#
+# NAME - the test name
+# SOURCES - sources for the test
+# TARGET_DEPS - build target dependencies (e.g., libraries)
+# EXTRA_LIB_DIRS - other directories for the library path
+# ENVIRONS - other environment key/value pairs
+# ARGS - arguments for the test
+########################################################################
+function(VOLK_ADD_TEST test_name)
+
+ #parse the arguments for component names
+ include(CMakeParseArgumentsCopy)
+ CMAKE_PARSE_ARGUMENTS(VOLK_TEST "" "" "SOURCES;TARGET_DEPS;EXTRA_LIB_DIRS;ENVIRONS;ARGS" ${ARGN})
+
+ #set the initial environs to use
+ set(environs ${VOLK_TEST_ENVIRONS})
+
+ #create the initial library path
+ file(TO_NATIVE_PATH "${VOLK_TEST_EXTRA_LIB_DIRS}" libpath)
+
+ #set the source directory, which is mostly FYI
+ file(TO_NATIVE_PATH ${CMAKE_CURRENT_SOURCE_DIR} srcdir)
+ list(APPEND environs "srcdir=\"${srcdir}\"")
+
+ #http://www.cmake.org/pipermail/cmake/2009-May/029464.html
+ #Replaced this add test + set environs code with the shell script generation.
+ #Its nicer to be able to manually run the shell script to diagnose problems.
+ if(UNIX)
+ if(APPLE)
+ set(LD_PATH_VAR "DYLD_LIBRARY_PATH")
+ else()
+ set(LD_PATH_VAR "LD_LIBRARY_PATH")
+ endif()
+
+ #create a list of target directories to be determined by the
+ #"add_test" command, via the $<FOO:BAR> operator; make sure the
+ #test's directory is first, since it ($1) is prepended to PATH.
+ unset(TARGET_DIR_LIST)
+ foreach(target ${test_name} ${VOLK_TEST_TARGET_DEPS})
+ list(APPEND TARGET_DIR_LIST "\$<TARGET_FILE_DIR:${target}>")
+ endforeach()
+
+ #augment the PATH to start with the directory of the test
+ set(binpath "\"$1:\$PATH\"")
+ list(APPEND environs "PATH=${binpath}")
+
+ #set the shell to use
+ if(CMAKE_CROSSCOMPILING)
+ set(SHELL "/bin/sh")
+ else()
+ find_program(SHELL sh)
+ endif()
+
+ #check to see if the shell supports "$*" expansion with IFS
+ if(NOT TESTED_SHELL_SUPPORTS_IFS)
+ set(TESTED_SHELL_SUPPORTS_IFS TRUE CACHE BOOL "")
+ set(sh_file ${CMAKE_CURRENT_BINARY_DIR}/ifs_test.sh)
+ file(WRITE ${sh_file} "#!${SHELL}\n")
+ file(APPEND ${sh_file} "export IFS=:\n")
+ file(APPEND ${sh_file} "echo \"$*\"\n")
+ #make the shell file executable
+ execute_process(COMMAND chmod +x ${sh_file})
+
+ #execute the shell script
+ execute_process(COMMAND ${sh_file} "a" "b" "c"
+ OUTPUT_VARIABLE output OUTPUT_STRIP_TRAILING_WHITESPACE
+ )
+
+ #check the output to see if it is correct
+ string(COMPARE EQUAL ${output} "a:b:c" SHELL_SUPPORTS_IFS)
+ set(SHELL_SUPPORTS_IFS ${SHELL_SUPPORTS_IFS} CACHE BOOL
+ "Set this value to TRUE if the shell supports IFS argument expansion"
+ )
+ endif()
+ unset(testlibpath)
+ if(SHELL_SUPPORTS_IFS)
+ #"$*" expands in the shell into a list of all of the arguments
+ #to the shell script, concatenated using the character provided
+ #in ${IFS}.
+ list(APPEND testlibpath "$*")
+ else()
+ #shell does not support IFS expansion; use a loop instead
+ list(APPEND testlibpath "\${LL}")
+ endif()
+
+ #finally: add in the current library path variable
+ list(INSERT libpath 0 ${testlibpath})
+ list(APPEND libpath "$${LD_PATH_VAR}")
+
+ #replace list separator with the path separator
+ string(REPLACE ";" ":" libpath "${libpath}")
+ list(APPEND environs "${LD_PATH_VAR}=\"${libpath}\"")
+
+ #generate a shell script file that sets the environment and runs the test
+ set(sh_file ${CMAKE_CURRENT_BINARY_DIR}/${test_name}_test.sh)
+ file(WRITE ${sh_file} "#!${SHELL}\n")
+ if(SHELL_SUPPORTS_IFS)
+ file(APPEND ${sh_file} "export IFS=:\n")
+ else()
+ file(APPEND ${sh_file} "LL=\"$1\" && for tf in \"\$@\"; do LL=\"\${LL}:\${tf}\"; done\n")
+ endif()
+
+ #each line sets an environment variable
+ foreach(environ ${environs})
+ file(APPEND ${sh_file} "export ${environ}\n")
+ endforeach(environ)
+
+ #redo the test args to have a space between each
+ string(REPLACE ";" " " VOLK_TEST_ARGS "${VOLK_TEST_ARGS}")
+
+ #finally: append the test name to execute
+ file(APPEND ${sh_file} ${test_name} " " ${VOLK_TEST_ARGS} "\n")
+
+ #make the shell file executable
+ execute_process(COMMAND chmod +x ${sh_file})
+
+ add_executable(${test_name} ${VOLK_TEST_SOURCES})
+ target_link_libraries(${test_name} ${VOLK_TEST_TARGET_DEPS})
+
+ #add the shell file as the test to execute;
+ #use the form that allows for $<FOO:BAR> substitutions,
+ #then combine the script arguments inside the script.
+ add_test(NAME qa_${test_name}
+ COMMAND ${SHELL} ${sh_file} ${TARGET_DIR_LIST}
+ )
+
+ endif(UNIX)
+
+ if(WIN32)
+ #In the land of windows, all libraries must be in the PATH. Since
+ #the dependent libraries are not yet installed, we must manually
+ #set them in the PATH to run tests. The following appends the
+ #path of a target dependency.
+ #
+ #NOTE: get_target_property LOCATION is being deprecated as of
+ #CMake 3.2.0, which just prints a warning & notes that this
+ #functionality will be removed in the future. Leave it here for
+ #now until someone can figure out how to do this in Windows.
+ foreach(target ${test_name} ${VOLK_TEST_TARGET_DEPS})
+ get_target_property(location ${target} LOCATION)
+ if(location)
+ get_filename_component(path ${location} PATH)
+ string(REGEX REPLACE "\\$\\(.*\\)" ${CMAKE_BUILD_TYPE} path ${path})
+ list(APPEND libpath ${path})
+ endif(location)
+ endforeach(target)
+
+ list(APPEND libpath ${DLL_PATHS} "%PATH%")
+
+ #replace list separator with the path separator (escaped)
+ string(REPLACE ";" "\\;" libpath "${libpath}")
+ list(APPEND environs "PATH=${libpath}")
+
+ #generate a bat file that sets the environment and runs the test
+ set(bat_file ${CMAKE_CURRENT_BINARY_DIR}/${test_name}_test.bat)
+ file(WRITE ${bat_file} "@echo off\n")
+
+ #each line sets an environment variable
+ foreach(environ ${environs})
+ file(APPEND ${bat_file} "SET ${environ}\n")
+ endforeach(environ)
+
+ #redo the test args to have a space between each
+ string(REPLACE ";" " " VOLK_TEST_ARGS "${VOLK_TEST_ARGS}")
+
+ #finally: append the test name to execute
+ file(APPEND ${bat_file} ${test_name} " " ${VOLK_TEST_ARGS} "\n")
+ file(APPEND ${bat_file} "\n")
+
+ add_executable(${test_name} ${VOLK_TEST_SOURCES})
+ target_link_libraries(${test_name} ${VOLK_TEST_TARGET_DEPS})
+
+ add_test(${test_name} ${bat_file})
+ endif(WIN32)
+
+endfunction(VOLK_ADD_TEST)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkBoost.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBoost.cmake
similarity index 97%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkBoost.cmake
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBoost.cmake
index 318820e..9afa9f8 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkBoost.cmake
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBoost.cmake
@@ -86,7 +86,7 @@ set(Boost_NOGO_VERSIONS
)
foreach(ver ${Boost_NOGO_VERSIONS})
- if(${Boost_VERSION} EQUAL ${ver})
+ if("${Boost_VERSION}" STREQUAL "${ver}")
if(NOT ENABLE_BAD_BOOST)
MESSAGE(STATUS "WARNING: Found a known bad version of Boost (v${Boost_VERSION}). Disabling.")
set(Boost_FOUND FALSE)
@@ -94,5 +94,5 @@ foreach(ver ${Boost_NOGO_VERSIONS})
MESSAGE(STATUS "WARNING: Found a known bad version of Boost (v${Boost_VERSION}). Continuing anyway.")
set(Boost_FOUND TRUE)
endif(NOT ENABLE_BAD_BOOST)
- endif(${Boost_VERSION} EQUAL ${ver})
+ endif("${Boost_VERSION}" STREQUAL "${ver}")
endforeach(ver)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBuildTypes.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBuildTypes.cmake
new file mode 100644
index 0000000..345415e
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkBuildTypes.cmake
@@ -0,0 +1,189 @@
+# Copyright 2014 Free Software Foundation, Inc.
+#
+# This file is part of VOLK
+#
+# VOLK is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# VOLK is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with GNU Radio; see the file COPYING. If not, write to
+# the Free Software Foundation, Inc., 51 Franklin Street,
+# Boston, MA 02110-1301, USA.
+
+if(DEFINED __INCLUDED_VOLK_BUILD_TYPES_CMAKE)
+ return()
+endif()
+set(__INCLUDED_VOLK_BUILD_TYPES_CMAKE TRUE)
+
+# Standard CMake Build Types and their basic CFLAGS:
+# - None: nothing set
+# - Debug: -O2 -g
+# - Release: -O3
+# - RelWithDebInfo: -O3 -g
+# - MinSizeRel: -Os
+
+# Addtional Build Types, defined below:
+# - NoOptWithASM: -O0 -g -save-temps
+# - O2WithASM: -O2 -g -save-temps
+# - O3WithASM: -O3 -g -save-temps
+# - DebugParanoid -O0 -g -Werror
+
+# Defines the list of acceptable cmake build types. When adding a new
+# build type below, make sure to add it to this list.
+list(APPEND AVAIL_BUILDTYPES
+ None Debug Release RelWithDebInfo MinSizeRel
+ DebugParanoid NoOptWithASM O2WithASM O3WithASM
+)
+
+########################################################################
+# VOLK_CHECK_BUILD_TYPE(build type)
+#
+# Use this to check that the build type set in CMAKE_BUILD_TYPE on the
+# commandline is one of the valid build types used by this project. It
+# checks the value set in the cmake interface against the list of
+# known build types in AVAIL_BUILDTYPES. If the build type is found,
+# the function exits immediately. If nothing is found by the end of
+# checking all available build types, we exit with an error and list
+# the avialable build types.
+########################################################################
+function(VOLK_CHECK_BUILD_TYPE settype)
+ STRING(TOUPPER ${settype} _settype)
+ foreach(btype ${AVAIL_BUILDTYPES})
+ STRING(TOUPPER ${btype} _btype)
+ if(${_settype} STREQUAL ${_btype})
+ return() # found it; exit cleanly
+ endif(${_settype} STREQUAL ${_btype})
+ endforeach(btype)
+ # Build type not found; error out
+ message(FATAL_ERROR "Build type '${settype}' not valid, must be one of: ${AVAIL_BUILDTYPES}")
+endfunction(VOLK_CHECK_BUILD_TYPE)
+
+########################################################################
+# For GCC and Clang, we can set a build type:
+#
+# -DCMAKE_BUILD_TYPE=DebugParanoid
+#
+# This type uses no optimization (-O0), outputs debug symbols (-g), warns
+# on everything, and stops on warnings.
+# NOTE: This is not defined on Windows systems.
+########################################################################
+if(NOT WIN32)
+ SET(CMAKE_CXX_FLAGS_DEBUGPARANOID "-Wall -Wextra -g -O0" CACHE STRING
+ "Flags used by the C++ compiler during DebugParanoid builds." FORCE)
+ SET(CMAKE_C_FLAGS_DEBUGPARANOID "-Wall -Wextra -g -O0" CACHE STRING
+ "Flags used by the C compiler during DebugParanoid builds." FORCE)
+ SET(CMAKE_EXE_LINKER_FLAGS_DEBUGPARANOID
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used for linking binaries during NoOptWithASM builds." FORCE)
+ SET(CMAKE_SHARED_LINKER_FLAGS_DEBUGPARANOID
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used by the shared lib linker during NoOptWithASM builds." FORCE)
+
+ MARK_AS_ADVANCED(
+ CMAKE_CXX_FLAGS_DEBUGPARANOID
+ CMAKE_C_FLAGS_DEBUGPARANOID
+ CMAKE_EXE_LINKER_FLAGS_DEBUGPARANOID
+ CMAKE_SHARED_LINKER_DEBUGPARANOID)
+endif(NOT WIN32)
+
+
+########################################################################
+# For GCC and Clang, we can set a build type:
+#
+# -DCMAKE_BUILD_TYPE=NoOptWithASM
+#
+# This type uses no optimization (-O0), outputs debug symbols (-g) and
+# outputs all intermediary files the build system produces, including
+# all assembly (.s) files. Look in the build directory for these
+# files.
+# NOTE: This is not defined on Windows systems.
+########################################################################
+if(NOT WIN32)
+ SET(CMAKE_CXX_FLAGS_NOOPTWITHASM "-save-temps -g -O0" CACHE STRING
+ "Flags used by the C++ compiler during NoOptWithASM builds." FORCE)
+ SET(CMAKE_C_FLAGS_NOOPTWITHASM "-save-temps -g -O0" CACHE STRING
+ "Flags used by the C compiler during NoOptWithASM builds." FORCE)
+ SET(CMAKE_EXE_LINKER_FLAGS_NOOPTWITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used for linking binaries during NoOptWithASM builds." FORCE)
+ SET(CMAKE_SHARED_LINKER_FLAGS_NOOPTWITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used by the shared lib linker during NoOptWithASM builds." FORCE)
+
+ MARK_AS_ADVANCED(
+ CMAKE_CXX_FLAGS_NOOPTWITHASM
+ CMAKE_C_FLAGS_NOOPTWITHASM
+ CMAKE_EXE_LINKER_FLAGS_NOOPTWITHASM
+ CMAKE_SHARED_LINKER_FLAGS_NOOPTWITHASM)
+endif(NOT WIN32)
+
+
+########################################################################
+# For GCC and Clang, we can set a build type:
+#
+# -DCMAKE_BUILD_TYPE=O2WithASM
+#
+# This type uses level 2 optimization (-O2), outputs debug symbols
+# (-g) and outputs all intermediary files the build system produces,
+# including all assembly (.s) files. Look in the build directory for
+# these files.
+# NOTE: This is not defined on Windows systems.
+########################################################################
+
+if(NOT WIN32)
+ SET(CMAKE_CXX_FLAGS_O2WITHASM "-save-temps -g -O2" CACHE STRING
+ "Flags used by the C++ compiler during O2WithASM builds." FORCE)
+ SET(CMAKE_C_FLAGS_O2WITHASM "-save-temps -g -O2" CACHE STRING
+ "Flags used by the C compiler during O2WithASM builds." FORCE)
+ SET(CMAKE_EXE_LINKER_FLAGS_O2WITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used for linking binaries during O2WithASM builds." FORCE)
+ SET(CMAKE_SHARED_LINKER_FLAGS_O2WITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used by the shared lib linker during O2WithASM builds." FORCE)
+
+ MARK_AS_ADVANCED(
+ CMAKE_CXX_FLAGS_O2WITHASM
+ CMAKE_C_FLAGS_O2WITHASM
+ CMAKE_EXE_LINKER_FLAGS_O2WITHASM
+ CMAKE_SHARED_LINKER_FLAGS_O2WITHASM)
+endif(NOT WIN32)
+
+
+########################################################################
+# For GCC and Clang, we can set a build type:
+#
+# -DCMAKE_BUILD_TYPE=O3WithASM
+#
+# This type uses level 3 optimization (-O3), outputs debug symbols
+# (-g) and outputs all intermediary files the build system produces,
+# including all assembly (.s) files. Look in the build directory for
+# these files.
+# NOTE: This is not defined on Windows systems.
+########################################################################
+
+if(NOT WIN32)
+ SET(CMAKE_CXX_FLAGS_O3WITHASM "-save-temps -g -O3" CACHE STRING
+ "Flags used by the C++ compiler during O3WithASM builds." FORCE)
+ SET(CMAKE_C_FLAGS_O3WITHASM "-save-temps -g -O3" CACHE STRING
+ "Flags used by the C compiler during O3WithASM builds." FORCE)
+ SET(CMAKE_EXE_LINKER_FLAGS_O3WITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used for linking binaries during O3WithASM builds." FORCE)
+ SET(CMAKE_SHARED_LINKER_FLAGS_O3WITHASM
+ "-Wl,--warn-unresolved-symbols,--warn-once" CACHE STRING
+ "Flags used by the shared lib linker during O3WithASM builds." FORCE)
+
+ MARK_AS_ADVANCED(
+ CMAKE_CXX_FLAGS_O3WITHASM
+ CMAKE_C_FLAGS_O3WITHASM
+ CMAKE_EXE_LINKER_FLAGS_O3WITHASM
+ CMAKE_SHARED_LINKER_FLAGS_O3WITHASM)
+endif(NOT WIN32)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkConfig.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfig.cmake
similarity index 80%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkConfig.cmake
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfig.cmake
index 7d58b19..d1bda33 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/VolkConfig.cmake
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfig.cmake
@@ -1,9 +1,9 @@
INCLUDE(FindPkgConfig)
-PKG_CHECK_MODULES(PC_VOLK volk_gnsssdr)
+PKG_CHECK_MODULES(PC_VOLK volk_gnsssdr_module)
FIND_PATH(
VOLK_INCLUDE_DIRS
- NAMES volk_gnsssdr/volk_gnsssdr.h
+ NAMES volk_gnsssdr_module/volk_gnsssdr_module.h
HINTS $ENV{VOLK_DIR}/include
${PC_VOLK_INCLUDEDIR}
PATHS /usr/local/include
@@ -12,7 +12,7 @@ FIND_PATH(
FIND_LIBRARY(
VOLK_LIBRARIES
- NAMES volk_gnsssdr
+ NAMES volk_gnsssdr_module
HINTS $ENV{VOLK_DIR}/lib
${PC_VOLK_LIBDIR}
PATHS /usr/local/lib
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfigVersion.cmake.in b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfigVersion.cmake.in
new file mode 100644
index 0000000..265daeb
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkConfigVersion.cmake.in
@@ -0,0 +1,34 @@
+# Copyright 2014 Free Software Foundation, Inc.
+#
+# This file is part of VOLK.
+#
+# VOLK is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# VOLK is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with VOLK; see the file COPYING. If not, write to
+# the Free Software Foundation, Inc., 51 Franklin Street,
+# Boston, MA 02110-1301, USA.
+
+set(MAJOR_VERSION @VERSION_INFO_MAJOR_VERSION@)
+set(MINOR_VERSION @VERSION_INFO_MINOR_VERSION@)
+set(MAINT_VERSION @VERSION_INFO_MAINT_VERSION@)
+
+set(PACKAGE_VERSION
+ ${MAJOR_VERSION}.${MINOR_VERSION}.${MAINT_VERSION})
+
+if(${PACKAGE_FIND_VERSION_MAJOR} EQUAL ${MAJOR_VERSION})
+ if(${PACKAGE_FIND_VERSION_MINOR} EQUAL ${MINOR_VERSION})
+ if(NOT ${PACKAGE_FIND_VERSION_PATCH} GREATER ${MAINT_VERSION})
+ set(PACKAGE_VERSION_EXACT 1) # exact match for API version
+ set(PACKAGE_VERSION_COMPATIBLE 1) # compat for minor/patch version
+ endif(NOT ${PACKAGE_FIND_VERSION_PATCH} GREATER ${MINOR_VERSION})
+ endif(${PACKAGE_FIND_VERSION_MINOR} EQUAL ${API_COMPAT})
+endif(${PACKAGE_FIND_VERSION_MAJOR} EQUAL ${MAJOR_VERSION})
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/GrPython.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkPython.cmake
similarity index 99%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/GrPython.cmake
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkPython.cmake
index b8eaba2..6657440 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/GrPython.cmake
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkPython.cmake
@@ -71,7 +71,7 @@ endif(PYTHON_EXECUTABLE)
# - have the result variable to set
########################################################################
macro(VOLK_PYTHON_CHECK_MODULE desc mod cmd have)
- #message(STATUS "")
+ message(STATUS "")
message(STATUS "Python checking for ${desc}")
execute_process(
COMMAND ${PYTHON_EXECUTABLE} -c "
@@ -97,11 +97,13 @@ endmacro(VOLK_PYTHON_CHECK_MODULE)
########################################################################
# Sets the python installation directory VOLK_PYTHON_DIR
########################################################################
+if(NOT DEFINED VOLK_PYTHON_DIR)
execute_process(COMMAND ${PYTHON_EXECUTABLE} -c "
from distutils import sysconfig
print sysconfig.get_python_lib(plat_specific=True, prefix='')
" OUTPUT_VARIABLE VOLK_PYTHON_DIR OUTPUT_STRIP_TRAILING_WHITESPACE
)
+endif()
file(TO_CMAKE_PATH ${VOLK_PYTHON_DIR} VOLK_PYTHON_DIR)
########################################################################
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkVersion.cmake b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkVersion.cmake
new file mode 100644
index 0000000..6add61c
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/cmake/Modules/VolkVersion.cmake
@@ -0,0 +1,89 @@
+# Copyright 2014 Free Software Foundation, Inc.
+#
+# This file is part of VOLK.
+#
+# VOLK is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3, or (at your option)
+# any later version.
+#
+# VOLK is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with VOLK; see the file COPYING. If not, write to
+# the Free Software Foundation, Inc., 51 Franklin Street,
+# Boston, MA 02110-1301, USA.
+
+if(DEFINED __INCLUDED_VOLK_VERSION_CMAKE)
+ return()
+endif()
+set(__INCLUDED_VOLK_VERSION_CMAKE TRUE)
+
+#eventually, replace version.sh and fill in the variables below
+set(MAJOR_VERSION ${VERSION_INFO_MAJOR_VERSION})
+set(MINOR_VERSION ${VERSION_INFO_MINOR_VERSION})
+set(MAINT_VERSION ${VERSION_INFO_MAINT_VERSION})
+
+########################################################################
+# Extract the version string from git describe.
+########################################################################
+find_package(Git)
+
+if(GIT_FOUND AND EXISTS ${CMAKE_SOURCE_DIR}/.git)
+ message(STATUS "Extracting version information from git describe...")
+ execute_process(
+ COMMAND ${GIT_EXECUTABLE} describe --always --abbrev=8 --long
+ OUTPUT_VARIABLE GIT_DESCRIBE OUTPUT_STRIP_TRAILING_WHITESPACE
+ WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
+ )
+else()
+ if(NOT VOLK_GIT_COUNT)
+ set(VOLK_GIT_COUNT "0")
+ endif()
+
+ if(NOT VOLK_GIT_HASH)
+ set(VOLK_GIT_HASH "unknown")
+ endif()
+
+ set(GIT_DESCRIBE "v${MAJOR_VERSION}.${MINOR_VERSION}-${VOLK_GIT_COUNT}-${VOLK_GIT_HASH}")
+endif()
+
+########################################################################
+# Use the logic below to set the version constants
+########################################################################
+if("${MINOR_VERSION}" STREQUAL "git")
+ # VERSION: 1.0git-xxx-gxxxxxxxx
+ # DOCVER: 1.0git
+ # LIBVER: 1.0git
+ set(VERSION "${GIT_DESCRIBE}")
+ set(DOCVER "${MAJOR_VERSION}.0${MINOR_VERSION}")
+ set(LIBVER "${MAJOR_VERSION}.0${MINOR_VERSION}")
+ set(RC_MINOR_VERSION "0")
+ set(RC_MAINT_VERSION "0")
+elseif("${MAINT_VERSION}" STREQUAL "git")
+ # VERSION: 1.xgit-xxx-gxxxxxxxx
+ # DOCVER: 1.xgit
+ # LIBVER: 1.xgit
+ set(VERSION "${GIT_DESCRIBE}")
+ set(DOCVER "${MAJOR_VERSION}.${MINOR_VERSION}${MAINT_VERSION}")
+ set(LIBVER "${MAJOR_VERSION}.${MINOR_VERSION}${MAINT_VERSION}")
+ math(EXPR RC_MINOR_VERSION "${MINOR_VERSION} - 1")
+ set(RC_MAINT_VERSION "0")
+else()
+ # This is a numbered release.
+ # VERSION: 1.1{.x}
+ # DOCVER: 1.1{.x}
+ # LIBVER: 1.1{.x}
+ if("${MAINT_VERSION}" STREQUAL "0")
+ set(VERSION "${MAJOR_VERSION}.${MINOR_VERSION}")
+ else()
+ set(VERSION "${MAJOR_VERSION}.${MINOR_VERSION}.${MAINT_VERSION}")
+ endif()
+ set(DOCVER "${VERSION}")
+ set(LIBVER "${VERSION}")
+ set(RC_MINOR_VERSION ${MINOR_VERSION})
+ set(RC_MAINT_VERSION ${MAINT_VERSION})
+endif()
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/archs.xml b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/archs.xml
index e570fe5..33888a7 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/archs.xml
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/archs.xml
@@ -4,12 +4,6 @@
<arch name="generic"> <!-- name is required-->
</arch>
-<arch name="altivec">
- <flag compiler="gnu">-maltivec</flag>
- <alignment>16</alignment>
- <check name="has_ppc"></check>
-</arch>
-
<arch name="softfp">
<flag compiler="gnu">-mfloat-abi=softfp</flag>
</arch>
@@ -87,6 +81,16 @@
<alignment>8</alignment>
</arch>
+<arch name="fma">
+ <check name="cpuid_x86_bit">
+ <param>2</param>
+ <param>0x00000001</param>
+ <param>12</param>
+ </check>
+ <flag compiler="gnu">-mfma</flag>
+ <alignment>32</alignment>
+</arch>
+
<arch name="sse">
<check name="cpuid_x86_bit">
<param>3</param>
@@ -201,4 +205,24 @@
<alignment>32</alignment>
</arch>
+<arch name="avx2">
+ <check name="cpuid_count_x86_bit">
+ <param>7</param>
+ <param>0</param>
+ <param>1</param>
+ <param>5</param>
+ </check>
+ <!-- check to make sure that xgetbv is enabled in OS -->
+ <check name="cpuid_x86_bit">
+ <param>2</param>
+ <param>0x00000001</param>
+ <param>27</param>
+ </check>
+ <!-- check to see that the OS has enabled AVX2 -->
+ <check name="get_avx2_enabled"></check>
+ <flag compiler="gnu">-mavx2</flag>
+ <flag compiler="msvc">/arch:AVX2</flag>
+ <alignment>32</alignment>
+</arch>
+
</grammar>
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/machines.xml b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/machines.xml
index 357bf75..0b7fd54 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/machines.xml
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/machines.xml
@@ -4,16 +4,6 @@
<archs>generic orc|</archs>
</machine>
-<!--
-<machine name="mmx">
-<archs>generic 32|64 mmx orc|</archs>
-</machine>
-
-<machine name="sse">
-<archs>generic 32|64| mmx| sse orc|</archs>
-</machine>
--->
-
<machine name="neon">
<archs>generic neon softfp|hardfp orc|</archs>
</machine>
@@ -48,8 +38,9 @@
<archs>generic 32|64| mmx| sse sse2 sse3 ssse3 sse4_1 sse4_2 popcount avx orc|</archs>
</machine>
-<machine name="altivec">
-<archs>generic altivec</archs>
+<!-- trailing | bar means generate without either for MSVC -->
+<machine name="avx2">
+<archs>generic 32|64| mmx| sse sse2 sse3 ssse3 sse4_1 sse4_2 popcount avx fma avx2 orc|</archs>
</machine>
</grammar>
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_machine_defs.py b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_machine_defs.py
index e5b167e..7833b0a 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_machine_defs.py
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_machine_defs.py
@@ -34,7 +34,7 @@ class machine_class:
self.archs.append(arch)
self.arch_names.append(arch_name)
self.alignment = max(map(lambda a: a.alignment, self.archs))
-
+
def __repr__(self): return self.name
def register_machine(name, archs):
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_tmpl_utils.py b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_tmpl_utils.py
index 48dae0e..3373877 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_tmpl_utils.py
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/gen/volk_gnsssdr_tmpl_utils.py
@@ -53,10 +53,10 @@ def __parse_tmpl(_tmpl, **kwargs):
defs.update(kwargs)
_tmpl = __escape_pre_processor(_tmpl)
_tmpl = """
-
-/* this file was generated by volk_gnsssdr template utils, do not edit! */
-
-""" + _tmpl
+
+ /* this file was generated by volk_gnsssdr template utils, do not edit! */
+
+ """ + _tmpl
return str(Template.Template(_tmpl, defs))
def main():
@@ -64,9 +64,10 @@ def main():
parser.add_option('--input', type='string')
parser.add_option('--output', type='string')
(opts, args) = parser.parse_args()
-
+
output = __parse_tmpl(open(opts.input).read(), args=args)
if opts.output: open(opts.output, 'w').write(output)
else: print output
if __name__ == '__main__': main()
+
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h
index c0beb4a..4c4194c 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/constants.h
@@ -1,35 +1,33 @@
-/*!
- * \file constants.h
- * \brief volk_gnsssdr constants
- * \author Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
+/* -*- c++ -*- */
+/*
+ * Copyright 2006,2009,2013 Free Software Foundation, Inc.
*
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ * This file is part of GNU Radio
*
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
+ * GNU Radio is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
+ * the Free Software Foundation; either version 3, or (at your option)
+ * any later version.
*
- * GNSS-SDR is distributed in the hope that it will be useful,
+ * GNU Radio is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ * along with GNU Radio; see the file COPYING. If not, write to
+ * the Free Software Foundation, Inc., 51 Franklin Street,
+ * Boston, MA 02110-1301, USA.
*/
-#ifndef GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H
-#define GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H
+#ifndef INCLUDED_VOLK_GNSSSDR_CONSTANTS_H
+#define INCLUDED_VOLK_GNSSSDR_CONSTANTS_H
#include <volk_gnsssdr/volk_gnsssdr_common.h>
__VOLK_DECL_BEGIN
VOLK_API char* volk_gnsssdr_prefix();
-VOLK_API char* volk_gnsssdr_build_date();
VOLK_API char* volk_gnsssdr_version();
VOLK_API char* volk_gnsssdr_c_compiler();
VOLK_API char* volk_gnsssdr_compiler_flags();
@@ -37,4 +35,4 @@ VOLK_API char* volk_gnsssdr_available_machines();
__VOLK_DECL_END
-#endif /* GNSS_SDR_VOLK_GNSSSDR_CONSTANTS_H */
+#endif /* INCLUDED_VOLK_GNSSSDR_CONSTANTS_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_avx_intrinsics.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_avx_intrinsics.h
new file mode 100644
index 0000000..c5f8ab8
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_avx_intrinsics.h
@@ -0,0 +1,71 @@
+/*!
+ * \file volk_gnsssdr_avx_intrinsics.h
+ * \author Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
+ *
+ * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ *
+ * This file is part of GNSS-SDR.
+ *
+ * GNSS-SDR is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GNSS-SDR is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * This file is intended to hold AVX intrinsics of intrinsics.
+ * They should be used in VOLK kernels to avoid copy-pasta.
+ */
+
+#ifndef INCLUDE_VOLK_VOLK_AVX_INTRINSICS_H_
+#define INCLUDE_VOLK_VOLK_AVX_INTRINSICS_H_
+#include <immintrin.h>
+
+static inline __m256
+_mm256_complexmul_ps(__m256 x, __m256 y)
+{
+ __m256 yl, yh, tmp1, tmp2;
+ yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr ...
+ yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di ...
+ tmp1 = _mm256_mul_ps(x, yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr ...
+ x = _mm256_shuffle_ps(x, x, 0xB1); // Re-arrange x to be ai,ar,bi,br ...
+ tmp2 = _mm256_mul_ps(x, yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
+ return _mm256_addsub_ps(tmp1, tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
+}
+
+static inline __m256
+_mm256_conjugate_ps(__m256 x){
+ const __m256 conjugator = _mm256_setr_ps(0, -0.f, 0, -0.f, 0, -0.f, 0, -0.f);
+ return _mm256_xor_ps(x, conjugator); // conjugate y
+}
+
+static inline __m256
+_mm256_complexconjugatemul_ps(__m256 x, __m256 y){
+ y = _mm256_conjugate_ps(y);
+ return _mm256_complexmul_ps(x, y);
+}
+
+static inline __m256
+_mm256_magnitudesquared_ps(__m256 cplxValue1, __m256 cplxValue2){
+ __m256 complex1, complex2;
+ cplxValue1 = _mm256_mul_ps(cplxValue1, cplxValue1); // Square the values
+ cplxValue2 = _mm256_mul_ps(cplxValue2, cplxValue2); // Square the Values
+ complex1 = _mm256_permute2f128_ps(cplxValue1, cplxValue2, 0x20);
+ complex2 = _mm256_permute2f128_ps(cplxValue1, cplxValue2, 0x31);
+ return _mm256_hadd_ps(complex1, complex2); // Add the I2 and Q2 values
+}
+
+static inline __m256
+_mm256_magnitude_ps(__m256 cplxValue1, __m256 cplxValue2){
+ return _mm256_sqrt_ps(_mm256_magnitudesquared_ps(cplxValue1, cplxValue2));
+}
+
+#endif /* INCLUDE_VOLK_VOLK_AVX_INTRINSICS_H_ */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_common.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_common.h
index fd45803..3e217de 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_common.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_common.h
@@ -91,14 +91,11 @@
#include <inttypes.h>
#ifdef LV_HAVE_SSE
-#include <xmmintrin.h>
-#endif
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
+#include <x86intrin.h>
#endif
union bit128{
+ uint8_t i8[16];
uint16_t i16[8];
uint32_t i[4];
float f[4];
@@ -114,6 +111,21 @@ union bit128{
#endif
};
+union bit256{
+ uint8_t i8[32];
+ uint16_t i16[16];
+ uint32_t i[8];
+ float f[8];
+ double d[4];
+
+ #ifdef LV_HAVE_AVX
+ __m256 float_vec;
+ __m256i int_vec;
+ __m256d double_vec;
+ #endif
+};
+
#define bit128_p(x) ((union bit128 *)(x))
+#define bit256_p(x) ((union bit256 *)(x))
#endif /* INCLUDED_LIBVOLK_COMMON_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_complex.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_complex.h
index d788cf1..ea97a38 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_complex.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_complex.h
@@ -109,6 +109,7 @@ typedef double complex lv_64fc_t;
#endif /* __cplusplus */
+
#endif /* INCLUDED_VOLK_COMPLEX_H */
#endif /* INCLUDE_VOLK_COMPLEX_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_malloc.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_malloc.h
index e371b07..6909434 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_malloc.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_malloc.h
@@ -25,9 +25,8 @@
#ifndef INCLUDED_VOLK_MALLOC_H
#define INCLUDED_VOLK_MALLOC_H
+#include <volk_gnsssdr/volk_gnsssdr_common.h>
#include <stdlib.h>
-#include "volk_gnsssdr/volk_gnsssdr_common.h"
-
__VOLK_DECL_BEGIN
@@ -39,7 +38,7 @@ __VOLK_DECL_BEGIN
* memory that are guaranteed to be on an alignment, VOLK handles this
* itself. The volk_gnsssdr_malloc function behaves like malloc in that it
* returns a pointer to the allocated memory. However, it also takes
- * in an alignment specification, which is usually something like 16 or
+ * in an alignment specfication, which is usually something like 16 or
* 32 to ensure that the aligned memory is located on a particular
* byte boundary for use with SIMD.
*
@@ -60,7 +59,7 @@ VOLK_API void *volk_gnsssdr_malloc(size_t size, size_t alignment);
/*!
* \brief Free's memory allocated by volk_gnsssdr_malloc.
- * \param aptr The aligned pointer allocated by volk_gnsssdr_malloc.
+ * \param aptr The aligned pointer allocaed by volk_gnsssdr_malloc.
*/
VOLK_API void volk_gnsssdr_free(void *aptr);
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_prefs.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_prefs.h
index a09d042..cb97d19 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_prefs.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_prefs.h
@@ -37,14 +37,15 @@ typedef struct volk_gnsssdr_arch_pref
char impl_u[128]; //best unaligned impl
} volk_gnsssdr_arch_pref_t;
-/*!
- * \brief get path to volk_gnsssdr_config profiling info
- */
+////////////////////////////////////////////////////////////////////////
+// get path to volk_gnsssdr_config profiling info;
+// returns \0 in the argument on failure.
+////////////////////////////////////////////////////////////////////////
VOLK_API void volk_gnsssdr_get_config_path(char *);
-/*!
- * \brief load prefs into global prefs struct
- */
+////////////////////////////////////////////////////////////////////////
+// load prefs into global prefs struct
+////////////////////////////////////////////////////////////////////////
VOLK_API size_t volk_gnsssdr_load_preferences(volk_gnsssdr_arch_pref_t **);
__VOLK_DECL_END
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse3_intrinsics.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse3_intrinsics.h
new file mode 100644
index 0000000..ff11458
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse3_intrinsics.h
@@ -0,0 +1,65 @@
+/*!
+ * \file volk_gnsssdr_sse3_intrinsics.h
+ * \author Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
+ *
+ * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ *
+ * This file is part of GNSS-SDR.
+ *
+ * GNSS-SDR is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GNSS-SDR is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+
+/*
+ * This file is intended to hold SSE3 intrinsics of intrinsics.
+ * They should be used in VOLK kernels to avoid copy-pasta.
+ */
+
+#ifndef INCLUDE_VOLK_VOLK_SSE3_INTRINSICS_H_
+#define INCLUDE_VOLK_VOLK_SSE3_INTRINSICS_H_
+#include <pmmintrin.h>
+
+static inline __m128
+_mm_complexmul_ps(__m128 x, __m128 y)
+{
+ __m128 yl, yh, tmp1, tmp2;
+ yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
+ yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
+ tmp1 = _mm_mul_ps(x, yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
+ x = _mm_shuffle_ps(x, x, 0xB1); // Re-arrange x to be ai,ar,bi,br
+ tmp2 = _mm_mul_ps(x, yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
+ return _mm_addsub_ps(tmp1, tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
+}
+
+static inline __m128
+_mm_complexconjugatemul_ps(__m128 x, __m128 y)
+{
+ const __m128 conjugator = _mm_setr_ps(0, -0.f, 0, -0.f);
+ y = _mm_xor_ps(y, conjugator); // conjugate y
+ return _mm_complexmul_ps(x, y);
+}
+
+static inline __m128
+_mm_magnitudesquared_ps_sse3(__m128 cplxValue1, __m128 cplxValue2){
+ cplxValue1 = _mm_mul_ps(cplxValue1, cplxValue1); // Square the values
+ cplxValue2 = _mm_mul_ps(cplxValue2, cplxValue2); // Square the Values
+ return _mm_hadd_ps(cplxValue1, cplxValue2); // Add the I2 and Q2 values
+}
+
+static inline __m128
+_mm_magnitude_ps_sse3(__m128 cplxValue1, __m128 cplxValue2){
+ return _mm_sqrt_ps(_mm_magnitudesquared_ps_sse3(cplxValue1, cplxValue2));
+}
+
+#endif /* INCLUDE_VOLK_VOLK_SSE3_INTRINSICS_H_ */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse_intrinsics.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse_intrinsics.h
new file mode 100644
index 0000000..ea423d8
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/include/volk_gnsssdr/volk_gnsssdr_sse_intrinsics.h
@@ -0,0 +1,49 @@
+/*!
+ * \file volk_gnsssdr_sse_intrinsics.h
+ * \author Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
+ *
+ * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ *
+ * This file is part of GNSS-SDR.
+ *
+ * GNSS-SDR is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GNSS-SDR is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * This file is intended to hold SSE intrinsics of intrinsics.
+ * They should be used in VOLK kernels to avoid copy-pasta.
+ */
+
+#ifndef INCLUDE_VOLK_VOLK_SSE_INTRINSICS_H_
+#define INCLUDE_VOLK_VOLK_SSE_INTRINSICS_H_
+#include <xmmintrin.h>
+
+static inline __m128
+_mm_magnitudesquared_ps(__m128 cplxValue1, __m128 cplxValue2){
+ __m128 iValue, qValue;
+ // Arrange in i1i2i3i4 format
+ iValue = _mm_shuffle_ps(cplxValue1, cplxValue2, _MM_SHUFFLE(2,0,2,0));
+ // Arrange in q1q2q3q4 format
+ qValue = _mm_shuffle_ps(cplxValue1, cplxValue2, _MM_SHUFFLE(3,1,3,1));
+ iValue = _mm_mul_ps(iValue, iValue); // Square the I values
+ qValue = _mm_mul_ps(qValue, qValue); // Square the Q Values
+ return _mm_add_ps(iValue, qValue); // Add the I2 and Q2 values
+}
+
+static inline __m128
+_mm_magnitude_ps(__m128 cplxValue1, __m128 cplxValue2){
+ return _mm_sqrt_ps(_mm_magnitudesquared_ps(cplxValue1, cplxValue2));
+}
+
+#endif /* INCLUDE_VOLK_VOLK_SSE_INTRINSICS_H_ */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros.h
deleted file mode 100644
index 37ab562..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros.h
+++ /dev/null
@@ -1,174 +0,0 @@
-/*!
- * \file CommonMacros.h
- * \brief Common macros used inside the volk protokernels.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-#ifndef INCLUDED_gnsssdr_CommonMacros_u_H
-#define INCLUDED_gnsssdr_CommonMacros_u_H
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for U_SSE4_1
- */
-
- #ifndef CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1
- #define CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(input1, input2, real, imag)\
- imag = _mm_srli_si128 (input1, 2);\
- imag = _mm_blend_epi16 (input2, imag, 85);\
- real = _mm_slli_si128 (input2, 2);\
- real = _mm_blend_epi16 (real, input1, 85);
- #endif /* CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1 */
-
- #ifndef CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1
- #define CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(input, input_i_1, input_i_2, output_i32, output_ps)\
- input_i_1 = _mm_cvtepi16_epi32(input);\
- input = _mm_srli_si128 (input, 8);\
- input_i_2 = _mm_cvtepi16_epi32(input);\
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);\
- output_ps = _mm_cvtepi32_ps(output_i32);
- #endif /* CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1 */
-
- #ifndef CM_8IC_CONVERT_AND_ACC_32FC_U_SSE4_1
- #define CM_8IC_CONVERT_AND_ACC_32FC_U_SSE4_1(input, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)\
- input_i_1 = _mm_cvtepi8_epi32(input);\
- input = _mm_srli_si128 (input, 4);\
- input_i_2 = _mm_cvtepi8_epi32(input);\
- input = _mm_srli_si128 (input, 4);\
- output_i32_1 = _mm_add_epi32 (input_i_1, input_i_2);\
- input_i_1 = _mm_cvtepi8_epi32(input);\
- input = _mm_srli_si128 (input, 4);\
- input_i_2 = _mm_cvtepi8_epi32(input);\
- input = _mm_srli_si128 (input, 4);\
- output_i32_2 = _mm_add_epi32 (input_i_1, input_i_2);\
- output_i32 = _mm_add_epi32 (output_i32_1, output_i32_2);\
- output_ps = _mm_cvtepi32_ps(output_i32);
- #endif /* CM_8IC_CONVERT_AND_ACC_32FC_U_SSE4_1 */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_SSE2
- /*!
- \brief Macros for U_SSE2
- */
-
- #ifdef LV_HAVE_SSSE3
- /*!
- \brief Macros for U_SSSE3
- */
-
- #ifndef CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3
- #define CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, x, check_sign_sequence, rearrange_sequence, y_aux, x_abs, real_output, imag_output)\
- y_aux = _mm_sign_epi8 (y, x);\
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);\
- real_output = _mm_maddubs_epi16 (x_abs, y_aux);\
- \
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);\
- y_aux = _mm_sign_epi8 (y_aux, x);\
- imag_output = _mm_maddubs_epi16 (x_abs, y_aux);
- #endif /* CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3 */
-
- #endif /* LV_HAVE_SSSE3 */
-
- #ifndef CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2
- #define CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)\
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);\
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);\
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);\
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);\
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);\
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
- #endif /* CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2 */
-
- #ifndef CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2
- #define CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(input, mult1, real, imag)\
- imag = _mm_srli_si128 (input, 1);\
- imag = _mm_and_si128 (imag, mult1);\
- real = _mm_and_si128 (input, mult1);
- #endif /* CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2 */
-
- #ifndef CM_8IC_CONVERT_AND_ACC_32FC_U_SSE2
- #define CM_8IC_CONVERT_AND_ACC_32FC_U_SSE2(input, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)\
- input_i_1 = _mm_unpacklo_epi8(_mm_setzero_si128(), input);\
- input_i_2 = _mm_unpacklo_epi16(_mm_setzero_si128(), input_i_1);\
- input_i_1 = _mm_unpackhi_epi16(_mm_setzero_si128(), input_i_1);\
- input_i_1 = _mm_srai_epi32(input_i_1, 24);\
- input_i_2 = _mm_srai_epi32(input_i_2, 24);\
- output_i32 = _mm_add_epi32(input_i_1, input_i_2);\
- output_ps_1 = _mm_cvtepi32_ps(output_i32);\
- \
- input_i_1 = _mm_unpackhi_epi8(_mm_setzero_si128(), input);\
- input_i_2 = _mm_unpacklo_epi16(_mm_setzero_si128(), input_i_1);\
- input_i_1 = _mm_unpackhi_epi16(_mm_setzero_si128(), input_i_1);\
- input_i_1 = _mm_srai_epi32(input_i_1, 24);\
- input_i_2 = _mm_srai_epi32(input_i_2, 24);\
- output_i32 = _mm_add_epi32(input_i_1, input_i_2);\
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
- #endif /* CM_8IC_CONVERT_AND_ACC_32FC_U_SSE2 */
-
- #ifndef CM_8IC_CONTROLMINUS128_8IC_U_SSE2
- #define CM_8IC_CONTROLMINUS128_8IC_U_SSE2(y, minus128, minus128control)\
- minus128control = _mm_cmpeq_epi8 (y, minus128);\
- y = _mm_sub_epi8 (y, minus128control);
- #endif /* CM_8IC_CONTROLMINUS128_8IC_U_SSE2 */
-
- #endif /* LV_HAVE_SSE2 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for U_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_CommonMacros_a_H
-#define INCLUDED_gnsssdr_CommonMacros_a_H
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for A_SSE4_1
- */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_SSE2
- /*!
- \brief Macros for U_SSE2
- */
-
- #endif /* LV_HAVE_SSE2 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for A_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h
deleted file mode 100644
index 0716f2b..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/*!
- * \file CommonMacros_16ic_cw_corr_32fc.h
- * \brief Common macros used inside the 16ic_cw_corr_32fc volk protokernels.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-#ifndef INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_u_H
-#define INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_u_H
-#include "CommonMacros/CommonMacros.h"
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for U_SSE4_1
- */
-
- #ifndef CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1
- #define CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)\
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)\
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
- #endif /* CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1 */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for U_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_a_H
-#define INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_a_H
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for A_SSE4_1
- */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for A_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_16ic_cw_corr_32fc_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h
deleted file mode 100644
index a3e319d..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h
+++ /dev/null
@@ -1,115 +0,0 @@
-/*!
- * \file CommonMacros_8ic_cw_corr_32fc.h
- * \brief Common macros used inside the 8ic_cw_corr_32fc volk protokernels.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_u_H
-#define INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_u_H
-#include "CommonMacros/CommonMacros.h"
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for U_SSE4_1
- */
-
- #ifndef CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1
- #define CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)\
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)\
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)\
- \
- imag_output = _mm_slli_si128 (imag_output, 1);\
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);\
- \
- CM_8IC_CONVERT_AND_ACC_32FC_U_SSE4_1(output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
- #endif /* CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1 */
-
- #ifndef CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1
- #define CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)\
- CM_8IC_CONTROLMINUS128_8IC_U_SSE2(y, minus128, minus128control)\
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
- #endif /* CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1 */
-
- #ifndef CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1
- #define CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)\
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)\
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
- #endif /* CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1 */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_SSE2
- /*!
- \brief Macros for U_SSE2
- */
-
- #ifndef CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2
- #define CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)\
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)\
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)\
- \
- real_output = _mm_and_si128 (real_output, mult1);\
- imag_output = _mm_and_si128 (imag_output, mult1);\
- imag_output = _mm_slli_si128 (imag_output, 1);\
- output = _mm_or_si128 (real_output, imag_output);\
- \
- CM_8IC_CONVERT_AND_ACC_32FC_U_SSE2(output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
- #endif /* CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2 */
-
- #endif /* LV_HAVE_SSE2 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for U_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_a_H
-#define INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_a_H
-
- #ifdef LV_HAVE_SSE4_1
- /*!
- \brief Macros for A_SSE4_1
- */
-
- #endif /* LV_HAVE_SSE4_1 */
-
- #ifdef LV_HAVE_GENERIC
- /*!
- \brief Macros for A_GENERIC
- */
-
- #endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_CommonMacros_8ic_cw_corr_32fc_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/README.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/README.txt
deleted file mode 100644
index 7c2d8d9..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/CommonMacros/README.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-####################################################################
-Common Macros inside volk_gnsssdr module
-####################################################################
-
-First of all, sorry for making you need to read this: macros are evil, they can not be debugged, you do not know where the errors come from, syntax is annoying.. BUT this is the only way I found that allows to share one piece of code between various proto-kernels without performance penalties.
-Inline functions have been tested, and they introduce a really small time penalty, but it becomes huge because of long loops, with thousands of samples.
-
-####################################################################
-Syntax
-####################################################################
-
-In order to allow better understanding of the code we created the macros with a specific syntax:
-
-1) Inside CommonMacros.h you will find macros for common operations. we will explain the syntax with an example:
-
-example: CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)
-
-First of all, you find the characters �"CM", which means CommonMacros. After that the type and the amount of inputs is placed: "_16IC_X4" (16 bits complex integers, four inputs). The syntax for type is the same as the one used with volk protokernels, refer to GNURadio documentation for more help. The it comes the name of the macro ("_SCALAR_PRODUCT"), and after that the type and the amount of outputs ("_16IC_X2"). Finally it is placed the SSE minimum version needed to run ("_U_SSE2"). In [...]
-The variables that the macro needs are specified when calling it in order to avoid after-compile problems: if you want to use a macro you will need to declare all the variables it needs before, or you will not be able to compile.
-
-2) Inside all the other headers, CommonMacros_XXXXXX.h you will find macros for a specific group of proto-kernels. The syntax is the same as the CommonMacros.h
-
-####################################################################
-Workflow
-####################################################################
-
-In order to use the macros easily, we usually test the code without macros inside a testing proto-kernel, where you are able to test it, debug it and use breakpoints.
-When it works we place code inside a macro an I test it again.
-
-####################################################################
-Why macros
-####################################################################
-1) They are the only way we could find for sharing code between proto-kernels without performance penalty.
-2) It is true that they are really difficult to debug, but if you work with them responsibly it is not so hard. Volk_gnsssdr checks all the SSE proto-kernels implementations results against the generic implementation results, so if your macro is not working you will appreciate it after profiling it.
\ No newline at end of file
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/README.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/README.txt
deleted file mode 100644
index 69ee93d..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/README.txt
+++ /dev/null
@@ -1,67 +0,0 @@
-########################################################################
-# How to create custom kernel dispatchers
-########################################################################
-A kernel dispatcher is kernel implementation that calls other kernel implementations.
-By default, a dispatcher is generated by the build system for every kernel such that:
- * the best aligned implemention is called when all pointer arguments are aligned,
- * and otherwise the best unaligned implementation is called.
-
-The author of a VOLK kernel may create a custom dispatcher,
-to be called in place of the automatically generated one.
-A custom dispatcher may be useful to handle head and tail cases,
-or to implement different alignment and bounds checking logic.
-
-########################################################################
-# Code for an example dispatcher w/ tail case
-########################################################################
-#include <volk_gnsssdr/volk_gnsssdr_common.h>
-
-#ifdef LV_HAVE_DISPATCHER
-
-static inline void volk_gnsssdr_32f_x2_add_32f_dispatcher(float* cVector, const float* aVector, const float* bVector, unsigned int num_points)
-{
- const unsigned int num_points_r = num_points%4;
- const unsigned int num_points_x = num_points - num_points_r;
-
- if (volk_gnsssdr_is_aligned(VOLK_OR_PTR(cVector, VOLK_OR_PTR(aVector, bVector))))
- {
- volk_gnsssdr_32f_x2_add_32f_a(cVector, aVector, bVector, num_points_x);
- }
- else
- {
- volk_gnsssdr_32f_x2_add_32f_u(cVector, aVector, bVector, num_points_x);
- }
-
- volk_gnsssdr_32f_x2_add_32f_g(cVector+num_points_x, aVector+num_points_x, bVector+num_points_x, num_points_r);
-}
-
-#endif //LV_HAVE_DISPATCHER
-
-########################################################################
-# Code for an example dispatcher w/ tail case and accumulator
-########################################################################
-#include <volk_gnsssdr/volk_gnsssdr_common.h>
-
-#ifdef LV_HAVE_DISPATCHER
-
-static inline void volk_gnsssdr_32f_x2_dot_prod_32f_dispatcher(float * result, const float * input, const float * taps, unsigned int num_points)
-{
- const unsigned int num_points_r = num_points%16;
- const unsigned int num_points_x = num_points - num_points_r;
-
- if (volk_gnsssdr_is_aligned(VOLK_OR_PTR(input, taps)))
- {
- volk_gnsssdr_32f_x2_dot_prod_32f_a(result, input, taps, num_points_x);
- }
- else
- {
- volk_gnsssdr_32f_x2_dot_prod_32f_u(result, input, taps, num_points_x);
- }
-
- float result_tail = 0;
- volk_gnsssdr_32f_x2_dot_prod_32f_g(&result_tail, input+num_points_x, taps+num_points_x, num_points_r);
-
- *result += result_tail;
-}
-
-#endif //LV_HAVE_DISPATCHER
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_16sc_magnitude_32f_aligned16_orc_impl.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_16sc_magnitude_32f_aligned16_orc_impl.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_16sc_magnitude_32f_aligned16_orc_impl.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_16sc_magnitude_32f_aligned16_orc_impl.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32f_x2_add_32f.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32f_x2_add_32f.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32f_x2_add_32f.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32f_x2_add_32f.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32fc_s32fc_multiply_32fc.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32fc_s32fc_multiply_32fc.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32fc_s32fc_multiply_32fc.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32fc_s32fc_multiply_32fc.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32fc_x2_multiply_32fc.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32fc_x2_multiply_32fc.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_32fc_x2_multiply_32fc.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_32fc_x2_multiply_32fc.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8i_accumulator_s8i.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8i_accumulator_s8i.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8i_accumulator_s8i.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8i_accumulator_s8i.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8i_x2_add_8i.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8i_x2_add_8i.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8i_x2_add_8i.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8i_x2_add_8i.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_conjugate_8ic.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_conjugate_8ic.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_conjugate_8ic.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_conjugate_8ic.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_magnitude_squared_8i.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_magnitude_squared_8i.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_magnitude_squared_8i.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_magnitude_squared_8i.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_s8ic_multiply_8ic.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_s8ic_multiply_8ic.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_s8ic_multiply_8ic.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_s8ic_multiply_8ic.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x2_dot_prod_8ic.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x2_dot_prod_8ic.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x2_dot_prod_8ic.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x2_dot_prod_8ic.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x2_multiply_8ic.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x2_multiply_8ic.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x2_multiply_8ic.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x2_multiply_8ic.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8u_x2_multiply_8u.orc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8u_x2_multiply_8u.orc
similarity index 100%
rename from src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/orc/volk_gnsssdr_8u_x2_multiply_8u.orc
rename to src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/asm/orc/volk_gnsssdr_8u_x2_multiply_8u.orc
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h
deleted file mode 100644
index 5b9811f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h
+++ /dev/null
@@ -1,461 +0,0 @@
-/*!
- * \file volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation with 32 bits vectors
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Early, Prompt, and Late correlation with 32 bits vectors (16 bits the
- * real part and 16 bits the imaginary part):
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 32 bits vectors) It returns the input
- * signal in base band (BB)
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 32 bits vectors), accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 32 bits vectors), accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 32 bits vectors), accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-
-/*! \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_u_sse4_1(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- //Adds the float 32 results
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- P_code_ptr += 4;
- L_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * E_code[i];
- tmp2 = bb_signal_sample * P_code[i];
- tmp3 = bb_signal_sample * L_code[i];
-
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t)tmp1;
- *P_out += (lv_32fc_t)tmp2;
- *L_out += (lv_32fc_t)tmp3;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_a_sse4_1(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_load_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_load_si128((__m128i*)input_ptr);
-
- y1 = _mm_load_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y1 = _mm_load_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- //Adds the float 32 results
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_load_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_load_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- P_code_ptr += 4;
- L_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_store_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_a_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * E_code[i];
- tmp2 = bb_signal_sample * P_code[i];
- tmp3 = bb_signal_sample * L_code[i];
-
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t)tmp1;
- *P_out += (lv_32fc_t)tmp2;
- *L_out += (lv_32fc_t)tmp3;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h
deleted file mode 100644
index 0710161..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h
+++ /dev/null
@@ -1,1573 +0,0 @@
-/*!
- * \file volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation with 32 bits vectors using different methods: inside u_sse4_1_first there is one method, inside u_sse4_1_second there is another... This protokernel has been created to test the performance of different methods.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Early, Prompt, and Late correlation with 32 bits vectors (16 bits the
- * real part and 16 bits the imaginary part):
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 32 bits vectors) It returns the input
- * signal in base band (BB)
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 32 bits vectors), accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 32 bits vectors), accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 32 bits vectors), accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
- /*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_first(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 4;
-
- __m128i x, y, yaux, yl, yh, tmp1, tmp2, z, bb_signal_sample, bb_signal_sample_suffled;
-
- __m128 z_ps_1, z_ps_2, z_E, z_P, z_L;
- __m128i z_i_1, z_i_2;
-
- lv_32fc_t dotProduct_E;
- lv_32fc_t dotProduct_P;
- lv_32fc_t dotProduct_L;
-
- z_E = _mm_setzero_ps();
- z_P = _mm_setzero_ps();
- z_L = _mm_setzero_ps();
-
- const lv_16sc_t* _input = input;
- const lv_16sc_t* _carrier = carrier;
- const lv_16sc_t* _E_code = E_code;
- const lv_16sc_t* _P_code = P_code;
- const lv_16sc_t* _L_code = L_code;
-
- dotProduct_E = 0;
- dotProduct_P = 0;
- dotProduct_L = 0;
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_lddqu_si128((__m128i*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- // Load yl with cr,cr,dr,dr
- // Load yh with ci,ci,di,di
- yaux = _mm_shuffle_epi8 (y, _mm_set_epi8 (15, 14, 11, 10, 7, 6, 3, 2, 13, 12, 9, 8, 5, 4, 1, 0));
- yl = _mm_unpacklo_epi16(yaux, yaux);
- yh = _mm_unpackhi_epi16(yaux, yaux);
-
- tmp1 = _mm_mullo_epi16(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_epi8 (x, _mm_set_epi8 (13, 12, 15, 14, 9, 8, 11, 10, 5, 4, 7, 6, 1, 0, 3, 2)); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mullo_epi16(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- tmp2 = _mm_mullo_epi16(tmp2,_mm_set_epi16 (1, -1, 1, -1, 1, -1, 1, -1));
- bb_signal_sample = _mm_add_epi16(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- bb_signal_sample_suffled = _mm_shuffle_epi8 (bb_signal_sample, _mm_set_epi8 (13, 12, 15, 14, 9, 8, 11, 10, 5, 4, 7, 6, 1, 0, 3, 2)); // Re-arrange bb_signal_sample to be ai,ar,bi,br
-
- // correlation E,P,L (3x vector scalar product)
- // Early
- y = _mm_lddqu_si128((__m128i*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yaux = _mm_shuffle_epi8 (y, _mm_set_epi8 (15, 14, 11, 10, 7, 6, 3, 2, 13, 12, 9, 8, 5, 4, 1, 0));
- yl = _mm_unpacklo_epi16(yaux, yaux);
- yh = _mm_unpackhi_epi16(yaux, yaux);
-
- tmp1 = _mm_mullo_epi16(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- tmp2 = _mm_mullo_epi16(bb_signal_sample_suffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- tmp2 = _mm_mullo_epi16(tmp2,_mm_set_epi16 (1, -1, 1, -1, 1, -1, 1, -1));
- z = _mm_add_epi16(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_i_1 = _mm_cvtepi16_epi32(z);
- z_ps_1 = _mm_cvtepi32_ps(z_i_1);
- z = _mm_srli_si128 (z, 8);
- z_i_2 = _mm_cvtepi16_epi32(z);
- z_ps_2 = _mm_cvtepi32_ps(z_i_2);
-
- z_E = _mm_add_ps(z_E, z_ps_1); // Add the complex multiplication results together
- z_E = _mm_add_ps(z_E, z_ps_2); // Add the complex multiplication results together
-
- // Prompt
- y = _mm_lddqu_si128((__m128i*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yaux = _mm_shuffle_epi8 (y, _mm_set_epi8 (15, 14, 11, 10, 7, 6, 3, 2, 13, 12, 9, 8, 5, 4, 1, 0));
- yl = _mm_unpacklo_epi16(yaux, yaux);
- yh = _mm_unpackhi_epi16(yaux, yaux);
-
- tmp1 = _mm_mullo_epi16(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- tmp2 = _mm_mullo_epi16(bb_signal_sample_suffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- tmp2 = _mm_mullo_epi16(tmp2,_mm_set_epi16 (1, -1, 1, -1, 1, -1, 1, -1));
- z = _mm_add_epi16(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_i_1 = _mm_cvtepi16_epi32(z);
- z_ps_1 = _mm_cvtepi32_ps(z_i_1);
- z = _mm_srli_si128 (z, 8);
- z_i_2 = _mm_cvtepi16_epi32(z);
- z_ps_2 = _mm_cvtepi32_ps(z_i_2);
-
- z_P = _mm_add_ps(z_P, z_ps_1); // Add the complex multiplication results together
- z_P = _mm_add_ps(z_P, z_ps_2); // Add the complex multiplication results together
-
- // Late
- y = _mm_lddqu_si128((__m128i*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yaux = _mm_shuffle_epi8 (y, _mm_set_epi8 (15, 14, 11, 10, 7, 6, 3, 2, 13, 12, 9, 8, 5, 4, 1, 0));
- yl = _mm_unpacklo_epi16(yaux, yaux);
- yh = _mm_unpackhi_epi16(yaux, yaux);
-
- tmp1 = _mm_mullo_epi16(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- tmp2 = _mm_mullo_epi16(bb_signal_sample_suffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- tmp2 = _mm_mullo_epi16(tmp2,_mm_set_epi16 (1, -1, 1, -1, 1, -1, 1, -1));
- z = _mm_add_epi16(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_i_1 = _mm_cvtepi16_epi32(z);
- z_ps_1 = _mm_cvtepi32_ps(z_i_1);
- z = _mm_srli_si128 (z, 8);
- z_i_2 = _mm_cvtepi16_epi32(z);
- z_ps_2 = _mm_cvtepi32_ps(z_i_2);
-
- z_L = _mm_add_ps(z_L, z_ps_1); // Add the complex multiplication results together
- z_L = _mm_add_ps(z_L, z_ps_2); // Add the complex multiplication results together
-
- _input += 4;
- _carrier += 4;
- _E_code += 4;
- _L_code += 4;
- _P_code += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_E[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_P[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_L[2];
-
- _mm_storeu_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
-
- dotProduct_E = ( dotProductVector_E[0] + dotProductVector_E[1] );
- dotProduct_P = ( dotProductVector_P[0] + dotProductVector_P[1] );
- dotProduct_L = ( dotProductVector_L[0] + dotProductVector_L[1] );
- }
-
- for(unsigned int i=0; i < num_points%4; ++i)
- {
- dotProduct_E += (lv_32fc_t)((*_input) * (*_E_code++)*(*_carrier));
- dotProduct_P += (lv_32fc_t)((*_input) * (*_P_code++)*(*_carrier));
- dotProduct_L += (lv_32fc_t)((*_input++) * (*_L_code++)*(*_carrier++));
- }
-
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
-
-
-
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_second(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2;
- __m128 real_output_ps_1, real_output_ps_2, imag_output_ps_1, imag_output_ps_2;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x1, 2);
- imagx = _mm_blend_epi16 (x2, imagx, 85);
- realx = _mm_slli_si128 (x2, 2);
- realx = _mm_blend_epi16 (realx, x1, 85);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps_1);
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps_2);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps_1);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps_2);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps_1);
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps_2);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps_1);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps_2);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps_1);
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps_2);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps_1);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps_2);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- L_code_ptr += 4;
- P_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_third(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
- unsigned int index = 0;
- unsigned int indexPlus4 = 0;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, real_output_i32, imag_output_i32;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(index = 0;index < 8*sse_iters; index+=8)
- {
- indexPlus4 = index + 4;
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)&input_ptr[index]);
- x2 = _mm_lddqu_si128((__m128i*)&input_ptr[indexPlus4]);
-
- y1 = _mm_lddqu_si128((__m128i*)&carrier_ptr[index]);
- y2 = _mm_lddqu_si128((__m128i*)&carrier_ptr[indexPlus4]);
-
- imagx = _mm_srli_si128 (x1, 2);
- imagx = _mm_blend_epi16 (x2, imagx, 85);
- realx = _mm_slli_si128 (x2, 2);
- realx = _mm_blend_epi16 (realx, x1, 85);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)&E_code_ptr[index]);
- y2 = _mm_lddqu_si128((__m128i*)&E_code_ptr[indexPlus4]);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)&P_code_ptr[index]);
- y2 = _mm_lddqu_si128((__m128i*)&P_code_ptr[indexPlus4]);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)&L_code_ptr[index]);
- y2 = _mm_lddqu_si128((__m128i*)&L_code_ptr[indexPlus4]);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(; index < num_points; index++)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input_ptr[index] * carrier_ptr[index];
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * E_code_ptr[index]);
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * P_code_ptr[index]);
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * L_code_ptr[index]);
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_fourth(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, real_output_i32, imag_output_i32;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x1, 2);
- imagx = _mm_blend_epi16 (x2, imagx, 85);
- realx = _mm_slli_si128 (x2, 2);
- realx = _mm_blend_epi16 (realx, x1, 85);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y1, 2);
- imagy = _mm_blend_epi16 (y2, imagy, 85);
- realy = _mm_slli_si128 (y2, 2);
- realy = _mm_blend_epi16 (realy, y1, 85);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- L_code_ptr += 4;
- P_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_fifth(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy;
- __m128i input_i_1, input_i_2, output_i32;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, real_output, imag_output;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)
-
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)
-
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(real_bb_signal_sample, imag_bb_signal_sample, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output)
-
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(real_output, input_i_1, input_i_2, output_i32, real_output_ps)
- CM_16IC_CONVERT_AND_ACC_32FC_U_SSE4_1(imag_output, input_i_1, input_i_2, output_i32, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- L_code_ptr += 4;
- P_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_sse4_1_sixth(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy;
- __m128i input_i_1, input_i_2, output_i32;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, real_output, imag_output;
-
- __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
- __m128 real_output_ps, imag_output_ps;
-
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- E_code_ptr += 4;
- L_code_ptr += 4;
- P_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- }
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * E_code[i];
- tmp2 = bb_signal_sample * P_code[i];
- tmp3 = bb_signal_sample * L_code[i];
-
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t)tmp1;
- *P_out += (lv_32fc_t)tmp2;
- *L_out += (lv_32fc_t)tmp3;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-//
-//#ifdef LV_HAVE_SSE4_1
-//#include <smmintrin.h>
-///*!
-// \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
-// \param input The input signal input
-// \param carrier The carrier signal input
-// \param E_code Early PRN code replica input
-// \param P_code Early PRN code replica input
-// \param L_code Early PRN code replica input
-// \param E_out Early correlation output
-// \param P_out Early correlation output
-// \param L_out Early correlation output
-// \param num_points The number of complex values in vectors
-// */
-//static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_a_sse4_1(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-//{
-// const unsigned int sse_iters = num_points / 8;
-//
-// __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
-// __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-//
-// __m128 real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc;
-// __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2;
-// __m128 real_output_ps_1, real_output_ps_2, imag_output_ps_1, imag_output_ps_2;
-//
-// float E_out_real = 0;
-// float E_out_imag = 0;
-// float P_out_real = 0;
-// float P_out_imag = 0;
-// float L_out_real = 0;
-// float L_out_imag = 0;
-//
-// const lv_16sc_t* input_ptr = input;
-// const lv_16sc_t* carrier_ptr = carrier;
-//
-// const lv_16sc_t* E_code_ptr = E_code;
-// lv_32fc_t* E_out_ptr = E_out;
-// const lv_16sc_t* L_code_ptr = L_code;
-// lv_32fc_t* L_out_ptr = L_out;
-// const lv_16sc_t* P_code_ptr = P_code;
-// lv_32fc_t* P_out_ptr = P_out;
-//
-// *E_out_ptr = 0;
-// *P_out_ptr = 0;
-// *L_out_ptr = 0;
-//
-// mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-//
-// real_E_code_acc = _mm_setzero_ps();
-// imag_E_code_acc = _mm_setzero_ps();
-// real_P_code_acc = _mm_setzero_ps();
-// imag_P_code_acc = _mm_setzero_ps();
-// real_L_code_acc = _mm_setzero_ps();
-// imag_L_code_acc = _mm_setzero_ps();
-//
-// if (sse_iters>0)
-// {
-// for(int number = 0;number < sse_iters; number++){
-//
-// //Perform the carrier wipe-off
-// x1 = _mm_lddqu_si128((__m128i*)input_ptr);
-// input_ptr += 4;
-// x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-//
-// y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-// carrier_ptr += 4;
-// y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-//
-// imagx = _mm_srli_si128 (x1, 2);
-// imagx = _mm_blend_epi16 (x2, imagx, 85);
-// realx = _mm_slli_si128 (x2, 2);
-// realx = _mm_blend_epi16 (realx, x1, 85);
-//
-// imagy = _mm_srli_si128 (y1, 2);
-// imagy = _mm_blend_epi16 (y2, imagy, 85);
-// realy = _mm_slli_si128 (y2, 2);
-// realy = _mm_blend_epi16 (realy, y1, 85);
-//
-// realx_mult_realy = _mm_mullo_epi16 (realx, realy);
-// imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
-// realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
-// imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-//
-// real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
-// imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-//
-// //Get early values
-// y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-// E_code_ptr += 4;
-// y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-//
-// imagy = _mm_srli_si128 (y1, 2);
-// imagy = _mm_blend_epi16 (y2, imagy, 85);
-// realy = _mm_slli_si128 (y2, 2);
-// realy = _mm_blend_epi16 (realy, y1, 85);
-//
-// realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
-// imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
-// realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
-// imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-//
-// real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
-// imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-//
-// real_output_i_1 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
-// real_output = _mm_srli_si128 (real_output, 8);
-// real_output_i_2 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-//
-// imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
-// imag_output = _mm_srli_si128 (imag_output, 8);
-// imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-//
-// real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps_1);
-// real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps_2);
-// imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps_1);
-// imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps_2);
-//
-// //Get prompt values
-// y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-// P_code_ptr += 4;
-// y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-//
-// imagy = _mm_srli_si128 (y1, 2);
-// imagy = _mm_blend_epi16 (y2, imagy, 85);
-// realy = _mm_slli_si128 (y2, 2);
-// realy = _mm_blend_epi16 (realy, y1, 85);
-//
-// realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
-// imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
-// realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
-// imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-//
-// real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
-// imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-//
-// real_output_i_1 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
-// real_output = _mm_srli_si128 (real_output, 8);
-// real_output_i_2 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-//
-// imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
-// imag_output = _mm_srli_si128 (imag_output, 8);
-// imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-//
-// real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps_1);
-// real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps_2);
-// imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps_1);
-// imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps_2);
-//
-// //Get late values
-// y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-// L_code_ptr += 4;
-// y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-//
-// imagy = _mm_srli_si128 (y1, 2);
-// imagy = _mm_blend_epi16 (y2, imagy, 85);
-// realy = _mm_slli_si128 (y2, 2);
-// realy = _mm_blend_epi16 (realy, y1, 85);
-//
-// realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
-// imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
-// realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
-// imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-//
-// real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
-// imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-//
-// real_output_i_1 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_1 = _mm_cvtepi32_ps(real_output_i_1);
-// real_output = _mm_srli_si128 (real_output, 8);
-// real_output_i_2 = _mm_cvtepi16_epi32(real_output);
-// real_output_ps_2 = _mm_cvtepi32_ps(real_output_i_2);
-//
-// imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_1 = _mm_cvtepi32_ps(imag_output_i_1);
-// imag_output = _mm_srli_si128 (imag_output, 8);
-// imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
-// imag_output_ps_2 = _mm_cvtepi32_ps(imag_output_i_2);
-//
-// real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps_1);
-// real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps_2);
-// imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps_1);
-// imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps_2);
-//
-// input_ptr += 4;
-// carrier_ptr += 4;
-// E_code_ptr += 4;
-// L_code_ptr += 4;
-// P_code_ptr += 4;
-// }
-//
-// __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
-// __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
-// __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
-// __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
-// __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
-// __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
-//
-// _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
-// _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
-// _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
-// _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
-// _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
-// _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
-//
-// for (int i = 0; i<4; ++i)
-// {
-// E_out_real += real_E_dotProductVector[i];
-// E_out_imag += imag_E_dotProductVector[i];
-// P_out_real += real_P_dotProductVector[i];
-// P_out_imag += imag_P_dotProductVector[i];
-// L_out_real += real_L_dotProductVector[i];
-// L_out_imag += imag_L_dotProductVector[i];
-// }
-// *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
-// *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
-// *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
-// }
-//
-// lv_16sc_t bb_signal_sample;
-// for(int i=0; i < num_points%8; ++i)
-// {
-// //Perform the carrier wipe-off
-// bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
-// // Now get early, late, and prompt values for each
-// *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
-// *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
-// *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
-// }
-//}
-//#endif /* LV_HAVE_SSE4_1 */
-//
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_a_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * E_code[i];
- tmp2 = bb_signal_sample * P_code[i];
- tmp3 = bb_signal_sample * L_code[i];
-
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t)tmp1;
- *P_out += (lv_32fc_t)tmp2;
- *L_out += (lv_32fc_t)tmp3;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h
deleted file mode 100644
index fdc7c59..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h
+++ /dev/null
@@ -1,595 +0,0 @@
-/*!
- * \file volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Very early, Early, Prompt, Late and very late correlation with 32 bits vectors and returns float32 values.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Very Early, Early, Prompt, Late and Very Late correlation with 32 bits vectors (16 bits the
- * real part and 16 bits the imaginary part) and accumulates into float32 values, returning them:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 32 bits vectors) It returns the input
- * signal in base band (BB)
- * - Very Early values are calculated by multiplying the input signal in BB by the
- * very early code (multiplication of 32 bits vectors), converting that to float32 and accumulating the results
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 32 bits vectors), converting that to float32 and accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 32 bits vectors), converting that to float32 and accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 32 bits vectors), converting that to float32 and accumulating the results
- * - Very Late values are calculated by multiplying the input signal in BB by the
- * very late code (multiplication of 32 bits vectors), converting that to float32 and accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
- /*!
- \brief Performs the carrier wipe-off mixing and the Very Early, Early, Prompt, Late and Very Vate correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_u_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* VE_code, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, const lv_16sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_16sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++){
-
- //Perform the carrier wipe-off
- x1 = _mm_lddqu_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_lddqu_si128((__m128i*)input_ptr);
-
- y1 = _mm_lddqu_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y1 = _mm_lddqu_si128((__m128i*)VE_code_ptr);
- VE_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y1 = _mm_lddqu_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_lddqu_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_lddqu_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y1 = _mm_lddqu_si128((__m128i*)VL_code_ptr);
- VL_code_ptr += 4;
- y2 = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- VE_code_ptr += 4;
- E_code_ptr += 4;
- P_code_ptr += 4;
- L_code_ptr += 4;
- VL_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Very Early, Early, Prompt, Late and Very Vate correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* VE_code, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, const lv_16sc_t* VL_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
- lv_16sc_t tmp4;
- lv_16sc_t tmp5;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * VE_code[i];
- tmp2 = bb_signal_sample * E_code[i];
- tmp3 = bb_signal_sample * P_code[i];
- tmp4 = bb_signal_sample * L_code[i];
- tmp5 = bb_signal_sample * VL_code[i];
-
- // Now get early, late, and prompt values for each
- *VE_out += (lv_32fc_t)tmp1;
- *E_out += (lv_32fc_t)tmp2;
- *P_out += (lv_32fc_t)tmp3;
- *L_out += (lv_32fc_t)tmp4;
- *VL_out += (lv_32fc_t)tmp5;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_16ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Very Early, Early, Prompt, Late and Very Vate correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_a_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* VE_code, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, const lv_16sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x1, x2, y1, y2, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output;
-
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- const lv_16sc_t* input_ptr = input;
- const lv_16sc_t* carrier_ptr = carrier;
-
- const lv_16sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_16sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_16sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_16sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_16sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++){
-
- //Perform the carrier wipe-off
- x1 = _mm_load_si128((__m128i*)input_ptr);
- input_ptr += 4;
- x2 = _mm_load_si128((__m128i*)input_ptr);
-
- y1 = _mm_load_si128((__m128i*)carrier_ptr);
- carrier_ptr += 4;
- y2 = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(x1, x2, realx, imagx)
- CM_16IC_X2_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE4_1(y1, y2, realy, imagy)
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y1 = _mm_load_si128((__m128i*)VE_code_ptr);
- VE_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)VE_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y1 = _mm_load_si128((__m128i*)E_code_ptr);
- E_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y1 = _mm_load_si128((__m128i*)P_code_ptr);
- P_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y1 = _mm_load_si128((__m128i*)L_code_ptr);
- L_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y1 = _mm_load_si128((__m128i*)VL_code_ptr);
- VL_code_ptr += 4;
- y2 = _mm_load_si128((__m128i*)VL_code_ptr);
-
- CM_16IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y1, y2, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 4;
- carrier_ptr += 4;
- VE_code_ptr += 4;
- E_code_ptr += 4;
- P_code_ptr += 4;
- L_code_ptr += 4;
- VL_code_ptr += 4;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_store_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Very Early, Early, Prompt, Late and Very Vate correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_a_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_16sc_t* input, const lv_16sc_t* carrier, const lv_16sc_t* VE_code, const lv_16sc_t* E_code, const lv_16sc_t* P_code, const lv_16sc_t* L_code, const lv_16sc_t* VL_code, unsigned int num_points)
-{
- lv_16sc_t bb_signal_sample;
- lv_16sc_t tmp1;
- lv_16sc_t tmp2;
- lv_16sc_t tmp3;
- lv_16sc_t tmp4;
- lv_16sc_t tmp5;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform Early, Prompt and Late correlation
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- tmp1 = bb_signal_sample * VE_code[i];
- tmp2 = bb_signal_sample * E_code[i];
- tmp3 = bb_signal_sample * P_code[i];
- tmp4 = bb_signal_sample * L_code[i];
- tmp5 = bb_signal_sample * VL_code[i];
-
- // Now get early, late, and prompt values for each
- *VE_out += (lv_32fc_t)tmp1;
- *E_out += (lv_32fc_t)tmp2;
- *P_out += (lv_32fc_t)tmp3;
- *L_out += (lv_32fc_t)tmp4;
- *VL_out += (lv_32fc_t)tmp5;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_convert_16ic.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_convert_16ic.h
deleted file mode 100644
index c7c9810..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_convert_16ic.h
+++ /dev/null
@@ -1,303 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_convert_16ic.h
- * \brief Volk protokernel: converts float32 complex values to 16 integer complex values taking care of overflow
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <math.h>
-#include "volk_gnsssdr/volk_gnsssdr_complex.h"
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_convert_16ic_u_H
-#define INCLUDED_volk_gnsssdr_32fc_convert_16ic_u_H
-
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_u_sse2(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points){
- const unsigned int sse_iters = num_points/4;
-
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
-
- float min_val = -32768;
- float max_val = 32767;
-
- __m128 inputVal1, inputVal2;
- __m128i intInputVal1, intInputVal2;
- __m128 ret1, ret2;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++){
- inputVal1 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
-
- _mm_storeu_si128((__m128i*)outputVectorPtr, intInputVal1);
- outputVectorPtr += 8;
- }
-
- for(unsigned int i = 0; i < (num_points%4)*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_SSE
-#include <xmmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_u_sse(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points){
- const unsigned int sse_iters = num_points/4;
-
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
-
- float min_val = -32768;
- float max_val = 32767;
-
- __m128 inputVal1, inputVal2;
- __m128i intInputVal1, intInputVal2;
- __m128 ret1, ret2;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++){
- inputVal1 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
-
- _mm_storeu_si128((__m128i*)outputVectorPtr, intInputVal1);
- outputVectorPtr += 8;
- }
-
- for(unsigned int i = 0; i < (num_points%4)*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_SSE */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_generic(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points){
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
- float min_val = -32768;
- float max_val = 32767;
-
- for(unsigned int i = 0; i < num_points*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_convert_16ic_u_H */
-
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_convert_16ic_a_H
-#define INCLUDED_volk_gnsssdr_32fc_convert_16ic_a_H
-
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_a_sse2(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points){
- const unsigned int sse_iters = num_points/4;
-
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
-
- float min_val = -32768;
- float max_val = 32767;
-
- __m128 inputVal1, inputVal2;
- __m128i intInputVal1, intInputVal2;
- __m128 ret1, ret2;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++)
- {
- inputVal1 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
-
- _mm_store_si128((__m128i*)outputVectorPtr, intInputVal1);
- outputVectorPtr += 8;
- }
-
- for(unsigned int i = 0; i < (num_points%4)*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_SSE
-#include <xmmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_a_sse(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points/4;
-
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
-
- float min_val = -32768;
- float max_val = 32767;
-
- __m128 inputVal1, inputVal2;
- __m128i intInputVal1, intInputVal2;
- __m128 ret1, ret2;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++)
- {
- inputVal1 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
-
- _mm_store_si128((__m128i*)outputVectorPtr, intInputVal1);
- outputVectorPtr += 8;
- }
-
- for(unsigned int i = 0; i < (num_points%4)*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_SSE */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 32 integer vector (16 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_convert_16ic_a_generic(lv_16sc_t* outputVector, const lv_32fc_t* inputVector, unsigned int num_points)
-{
- float* inputVectorPtr = (float*)inputVector;
- int16_t* outputVectorPtr = (int16_t*)outputVector;
- float min_val = -32768;
- float max_val = 32767;
-
- for(unsigned int i = 0; i < num_points*2; i++)
- {
- if(inputVectorPtr[i] > max_val)
- inputVectorPtr[i] = max_val;
- else if(inputVectorPtr[i] < min_val)
- inputVectorPtr[i] = min_val;
- outputVectorPtr[i] = (int16_t)rintf(inputVectorPtr[i]);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_convert_16ic_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_convert_8ic.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_convert_8ic.h
deleted file mode 100644
index c81a40f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_convert_8ic.h
+++ /dev/null
@@ -1,240 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_s32f_convert_8ic.h
- * \brief Volk protokernel: converts float32 complex values to 8 integer complex values taking care of overflow
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <math.h>
-#include "volk_gnsssdr/volk_gnsssdr_complex.h"
-
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_u_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_u_H
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 16 integer vector (8 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_s32f_convert_8ic_u_sse2(lv_8sc_t* outputVector, const lv_32fc_t* inputVector, const float scalar, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points/8;
-
- float* inputVectorPtr = (float*)inputVector;
- int8_t* outputVectorPtr = (int8_t*)outputVector;
- __m128 invScalar = _mm_set_ps1(1.0/scalar);
-
- float min_val = -128;
- float max_val = 127;
-
- __m128 inputVal1, inputVal2, inputVal3, inputVal4;
- __m128i intInputVal1, intInputVal2, intInputVal3, intInputVal4;
- __m128i int8InputVal;
- __m128 ret1, ret2, ret3, ret4;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++)
- {
- inputVal1 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal3 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal4 = _mm_loadu_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- inputVal1 = _mm_mul_ps(inputVal1, invScalar);
- inputVal2 = _mm_mul_ps(inputVal2, invScalar);
- inputVal3 = _mm_mul_ps(inputVal3, invScalar);
- inputVal4 = _mm_mul_ps(inputVal4, invScalar);
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
- ret3 = _mm_max_ps(_mm_min_ps(inputVal3, vmax_val), vmin_val);
- ret4 = _mm_max_ps(_mm_min_ps(inputVal4, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
- intInputVal3 = _mm_cvtps_epi32(ret3);
- intInputVal4 = _mm_cvtps_epi32(ret4);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
- intInputVal2 = _mm_packs_epi32(intInputVal3, intInputVal4);
- int8InputVal = _mm_packs_epi16(intInputVal1, intInputVal2);
-
- _mm_storeu_si128((__m128i*)outputVectorPtr, int8InputVal);
- outputVectorPtr += 16;
- }
-
- float scaled = 0;
- for(unsigned int i = 0; i < (num_points%4)*4; i++)
- {
- scaled = inputVectorPtr[i]/scalar;
- if(scaled > max_val)
- scaled = max_val;
- else if(scaled < min_val)
- scaled = min_val;
- outputVectorPtr[i] = (int8_t)rintf(scaled);
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 16 integer vector (8 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_s32f_convert_8ic_generic(lv_8sc_t* outputVector, const lv_32fc_t* inputVector, const float scalar, unsigned int num_points)
-{
- float* inputVectorPtr = (float*)inputVector;
- int8_t* outputVectorPtr = (int8_t*)outputVector;
- float scaled = 0;
- float min_val = -128;
- float max_val = 127;
-
- for(unsigned int i = 0; i < num_points*2; i++)
- {
- scaled = (inputVectorPtr[i])/scalar;
- if(scaled > max_val)
- scaled = max_val;
- else if(scaled < min_val)
- scaled = min_val;
- outputVectorPtr[i] = (int8_t)rintf(scaled);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_u_H */
-
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_a_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_a_H
-
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 16 integer vector (8 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_s32f_convert_8ic_a_sse2(lv_8sc_t* outputVector, const lv_32fc_t* inputVector, const float scalar, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points/8;
-
- float* inputVectorPtr = (float*)inputVector;
- int8_t* outputVectorPtr = (int8_t*)outputVector;
- __m128 invScalar = _mm_set_ps1(1.0/scalar);
-
- float min_val = -128;
- float max_val = 127;
-
- __m128 inputVal1, inputVal2, inputVal3, inputVal4;
- __m128i intInputVal1, intInputVal2, intInputVal3, intInputVal4;
- __m128i int8InputVal;
- __m128 ret1, ret2, ret3, ret4;
- __m128 vmin_val = _mm_set_ps1(min_val);
- __m128 vmax_val = _mm_set_ps1(max_val);
-
- for(unsigned int i = 0;i < sse_iters; i++)
- {
- inputVal1 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal2 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal3 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
- inputVal4 = _mm_load_ps((float*)inputVectorPtr); inputVectorPtr += 4;
-
- inputVal1 = _mm_mul_ps(inputVal1, invScalar);
- inputVal2 = _mm_mul_ps(inputVal2, invScalar);
- inputVal3 = _mm_mul_ps(inputVal3, invScalar);
- inputVal4 = _mm_mul_ps(inputVal4, invScalar);
- // Clip
- ret1 = _mm_max_ps(_mm_min_ps(inputVal1, vmax_val), vmin_val);
- ret2 = _mm_max_ps(_mm_min_ps(inputVal2, vmax_val), vmin_val);
- ret3 = _mm_max_ps(_mm_min_ps(inputVal3, vmax_val), vmin_val);
- ret4 = _mm_max_ps(_mm_min_ps(inputVal4, vmax_val), vmin_val);
-
- intInputVal1 = _mm_cvtps_epi32(ret1);
- intInputVal2 = _mm_cvtps_epi32(ret2);
- intInputVal3 = _mm_cvtps_epi32(ret3);
- intInputVal4 = _mm_cvtps_epi32(ret4);
-
- intInputVal1 = _mm_packs_epi32(intInputVal1, intInputVal2);
- intInputVal2 = _mm_packs_epi32(intInputVal3, intInputVal4);
- int8InputVal = _mm_packs_epi16(intInputVal1, intInputVal2);
-
- _mm_store_si128((__m128i*)outputVectorPtr, int8InputVal);
- outputVectorPtr += 16;
- }
-
- float scaled = 0;
- for(unsigned int i = 0; i < (num_points%4)*4; i++)
- {
- scaled = inputVectorPtr[i]/scalar;
- if(scaled > max_val)
- scaled = max_val;
- else if(scaled < min_val)
- scaled = min_val;
- outputVectorPtr[i] = (int8_t)rintf(scaled);
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Converts a float vector of 64 bits (32 bits each part) into a 16 integer vector (8 bits each part)
- \param inputVector The floating point input data buffer
- \param outputVector The 16 bit output data buffer
- \param num_points The number of data values to be converted
- */
-static inline void volk_gnsssdr_32fc_s32f_convert_8ic_a_generic(lv_8sc_t* outputVector, const lv_32fc_t* inputVector, const float scalar, unsigned int num_points)
-{
- float* inputVectorPtr = (float*)inputVector;
- int8_t* outputVectorPtr = (int8_t*)outputVector;
- float scaled = 0;
- float min_val = -128;
- float max_val = 127;
-
- for(unsigned int i = 0; i < num_points*2; i++)
- {
- scaled = inputVectorPtr[i]/scalar;
- if(scaled > max_val)
- scaled = max_val;
- else if(scaled < min_val)
- scaled = min_val;
- outputVectorPtr[i] = (int8_t)rintf(scaled);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_convert_8ic_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc.h
deleted file mode 100644
index c574132..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc.h
+++ /dev/null
@@ -1,231 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc
- * \brief Volk protokernel: replaces the tracking function for update_local_code
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that replaces the tracking function for update_local_code
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_u_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_u_H
-
-#include <float.h>
-#include <inttypes.h>
-#include <math.h>
-#include <stdio.h>
-#include "volk_gnsssdr/volk_gnsssdr_complex.h"
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Takes the conjugate of a complex vector.
- \param cVector The vector where the results will be stored
- \param aVector Vector to be conjugated
- \param num_points The number of complex values in aVector to be conjugated and stored into cVector
- */
-static inline void volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_u_sse4_1(lv_32fc_t* d_very_early_code, const float d_very_early_late_spc_chips, const float code_length_half_chips, const float code_phase_step_half_chips, const float tcode_half_chips_input, const lv_32fc_t* d_ca_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 4;
-
- __m128 tquot, fmod_num, fmod_result, associated_chip_index_array;
-
- __m128 tcode_half_chips_array = _mm_set_ps (tcode_half_chips_input+3*code_phase_step_half_chips, tcode_half_chips_input+2*code_phase_step_half_chips, tcode_half_chips_input+code_phase_step_half_chips, tcode_half_chips_input);
- __m128 code_phase_step_half_chips_array = _mm_set1_ps (code_phase_step_half_chips*4);
- __m128 d_very_early_late_spc_chips_Multiplied_by_2 = _mm_set1_ps (2*d_very_early_late_spc_chips);
- __m128 code_length_half_chips_array = _mm_set1_ps (code_length_half_chips);
- __m128 twos = _mm_set1_ps (2);
- __m128i associated_chip_index_array_int;
-
- __VOLK_ATTR_ALIGNED(16) int32_t output[4];
-
- for (unsigned int i = 0; i < sse_iters; i++)
- {
- //fmod = numer - tquot * denom; tquot = numer/denom truncated
- //associated_chip_index = 2 + round(fmod(tcode_half_chips - 2*d_very_early_late_spc_chips, code_length_half_chips));
- fmod_num = _mm_sub_ps (tcode_half_chips_array, d_very_early_late_spc_chips_Multiplied_by_2);
- tquot = _mm_div_ps (fmod_num, code_length_half_chips_array);
- tquot = _mm_round_ps (tquot, (_MM_FROUND_TO_ZERO |_MM_FROUND_NO_EXC) );
- fmod_result = _mm_sub_ps (fmod_num, _mm_mul_ps (tquot, code_length_half_chips_array));
-
- associated_chip_index_array = _mm_round_ps (fmod_result, (_MM_FROUND_TO_NEAREST_INT |_MM_FROUND_NO_EXC));
- associated_chip_index_array = _mm_add_ps(twos, associated_chip_index_array);
- associated_chip_index_array_int = _mm_cvtps_epi32 (associated_chip_index_array);
- _mm_storeu_si128 ((__m128i*)output, associated_chip_index_array_int);
-
- //d_very_early_code[i] = d_ca_code[associated_chip_index];
- *d_very_early_code++ = d_ca_code[output[0]];
- *d_very_early_code++ = d_ca_code[output[1]];
- *d_very_early_code++ = d_ca_code[output[2]];
- *d_very_early_code++ = d_ca_code[output[3]];
-
- //tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- tcode_half_chips_array = _mm_add_ps (tcode_half_chips_array, code_phase_step_half_chips_array);
- }
-
- if (num_points % 4 != 0)
- {
- __VOLK_ATTR_ALIGNED(16) float tcode_half_chips_stored[4];
- _mm_storeu_ps ((float*)tcode_half_chips_stored, tcode_half_chips_array);
-
- int associated_chip_index;
- float tcode_half_chips = tcode_half_chips_stored[0];
- float d_very_early_late_spc_chips_multiplied_by_2 = 2*d_very_early_late_spc_chips;
-
- for (unsigned int i = 0; i < num_points%4; i++)
- {
- associated_chip_index = 2 + round(fmod(tcode_half_chips - d_very_early_late_spc_chips_multiplied_by_2, code_length_half_chips));
- d_very_early_code[i] = d_ca_code[associated_chip_index];
- tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- }
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Takes the conjugate of a complex vector.
- \param cVector The vector where the results will be stored
- \param aVector Vector to be conjugated
- \param num_points The number of complex values in aVector to be conjugated and stored into cVector
- */
-static inline void volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_generic(lv_32fc_t* d_very_early_code, const float d_very_early_late_spc_chips, const float code_length_half_chips, const float code_phase_step_half_chips, const float tcode_half_chips_input, const lv_32fc_t* d_ca_code, unsigned int num_points)
-{
- int associated_chip_index;
- float tcode_half_chips = tcode_half_chips_input;
- float d_very_early_late_spc_chips_multiplied_by_2 = 2*d_very_early_late_spc_chips;
-
- for (unsigned int i = 0; i < num_points; i++)
- {
- associated_chip_index = 2 + round(fmod(tcode_half_chips - d_very_early_late_spc_chips_multiplied_by_2, code_length_half_chips));
- d_very_early_code[i] = d_ca_code[associated_chip_index];
- tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-
-
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_u_H */
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_a_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Takes the conjugate of a complex vector.
- \param cVector The vector where the results will be stored
- \param aVector Vector to be conjugated
- \param num_points The number of complex values in aVector to be conjugated and stored into cVector
- */
-static inline void volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_a_sse4_1(lv_32fc_t* d_very_early_code, const float d_very_early_late_spc_chips, const float code_length_half_chips, const float code_phase_step_half_chips, const float tcode_half_chips_input, const lv_32fc_t* d_ca_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 4;
-
- __m128 tquot, fmod_num, fmod_result, associated_chip_index_array;
-
- __m128 tcode_half_chips_array = _mm_set_ps (tcode_half_chips_input+3*code_phase_step_half_chips, tcode_half_chips_input+2*code_phase_step_half_chips, tcode_half_chips_input+code_phase_step_half_chips, tcode_half_chips_input);
- __m128 code_phase_step_half_chips_array = _mm_set1_ps (code_phase_step_half_chips*4);
- __m128 d_very_early_late_spc_chips_Multiplied_by_2 = _mm_set1_ps (2*d_very_early_late_spc_chips);
- __m128 code_length_half_chips_array = _mm_set1_ps (code_length_half_chips);
- __m128 twos = _mm_set1_ps (2);
- __m128i associated_chip_index_array_int;
-
- __VOLK_ATTR_ALIGNED(16) int32_t output[4];
-
- for (unsigned int i = 0; i < sse_iters; i++)
- {
- //fmod = numer - tquot * denom; tquot = numer/denom truncated
- //associated_chip_index = 2 + round(fmod(tcode_half_chips - 2*d_very_early_late_spc_chips, code_length_half_chips));
- fmod_num = _mm_sub_ps (tcode_half_chips_array, d_very_early_late_spc_chips_Multiplied_by_2);
- tquot = _mm_div_ps (fmod_num, code_length_half_chips_array);
- tquot = _mm_round_ps (tquot, (_MM_FROUND_TO_ZERO |_MM_FROUND_NO_EXC) );
- fmod_result = _mm_sub_ps (fmod_num, _mm_mul_ps (tquot, code_length_half_chips_array));
-
- associated_chip_index_array = _mm_round_ps (fmod_result, (_MM_FROUND_TO_NEAREST_INT |_MM_FROUND_NO_EXC));
- associated_chip_index_array = _mm_add_ps(twos, associated_chip_index_array);
- associated_chip_index_array_int = _mm_cvtps_epi32 (associated_chip_index_array);
- _mm_store_si128 ((__m128i*)output, associated_chip_index_array_int);
-
- //d_very_early_code[i] = d_ca_code[associated_chip_index];
- *d_very_early_code++ = d_ca_code[output[0]];
- *d_very_early_code++ = d_ca_code[output[1]];
- *d_very_early_code++ = d_ca_code[output[2]];
- *d_very_early_code++ = d_ca_code[output[3]];
-
- //tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- tcode_half_chips_array = _mm_add_ps (tcode_half_chips_array, code_phase_step_half_chips_array);
- }
-
- if (num_points % 4 != 0)
- {
- __VOLK_ATTR_ALIGNED(16) float tcode_half_chips_stored[4];
- _mm_storeu_ps ((float*)tcode_half_chips_stored, tcode_half_chips_array);
-
- int associated_chip_index;
- float tcode_half_chips = tcode_half_chips_stored[0];
- float d_very_early_late_spc_chips_multiplied_by_2 = 2*d_very_early_late_spc_chips;
-
- for (unsigned int i = 0; i < num_points%4; i++)
- {
- associated_chip_index = 2 + round(fmod(tcode_half_chips - d_very_early_late_spc_chips_multiplied_by_2, code_length_half_chips));
- d_very_early_code[i] = d_ca_code[associated_chip_index];
- tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- }
- }
-
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Takes the conjugate of a complex vector.
- \param cVector The vector where the results will be stored
- \param aVector Vector to be conjugated
- \param num_points The number of complex values in aVector to be conjugated and stored into cVector
- */
-static inline void volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_a_generic(lv_32fc_t* d_very_early_code, const float d_very_early_late_spc_chips, const float code_length_half_chips, const float code_phase_step_half_chips, const float tcode_half_chips_input, const lv_32fc_t* d_ca_code, unsigned int num_points)
-{
- int associated_chip_index;
- float tcode_half_chips = tcode_half_chips_input;
- float d_very_early_late_spc_chips_multiplied_by_2 = 2*d_very_early_late_spc_chips;
-
- for (unsigned int i = 0; i < num_points; i++)
- {
- associated_chip_index = 2 + round(fmod(tcode_half_chips - d_very_early_late_spc_chips_multiplied_by_2, code_length_half_chips));
- d_very_early_code[i] = d_ca_code[associated_chip_index];
- tcode_half_chips = tcode_half_chips + code_phase_step_half_chips;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3.h
deleted file mode 100644
index 2f13102..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3.h
+++ /dev/null
@@ -1,455 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_x5_cw_vepl_corr_32fc_x5
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Early, Prompt and Late correlation with 64 bits vectors
- * \authors <ul>
- * <li> Javier Arribas, 2011. jarribas(at)cttc.es
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Early, Prompt and Late correlation with 64 bits vectors (32 bits the
- * real part and 32 bits the imaginary part):
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 64 bits vectors) It returns the input
- * signal in base band (BB)
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 64 bits vectors), accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 64 bits vectors), accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 64 bits vectors), accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-/*!
- * TODO: Code the SSE4 version and benchmark it
- */
-#ifdef LV_HAVE_SSE3
-#include <pmmintrin.h>
-
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_u_sse3(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 2;
-
- lv_32fc_t dotProduct_E;
- memset(&dotProduct_E, 0x0, 2*sizeof(float));
- lv_32fc_t dotProduct_P;
- memset(&dotProduct_P, 0x0, 2*sizeof(float));
- lv_32fc_t dotProduct_L;
- memset(&dotProduct_L, 0x0, 2*sizeof(float));
-
- // Aux vars
- __m128 x, y, yl, yh, z, tmp1, tmp2, z_E, z_P, z_L;
-
- z_E = _mm_setzero_ps();
- z_P = _mm_setzero_ps();
- z_L = _mm_setzero_ps();
-
- //input and output vectors
- //lv_32fc_t* _input_BB = input_BB;
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm_loadu_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_loadu_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- //_mm_storeu_ps((float*)_input_BB,z); // Store the results back into the _input_BB container
-
- // correlation E,P,L (3x vector scalar product)
- // Early
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- x = z;
-
- y = _mm_load_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_E = _mm_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_P = _mm_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_L = _mm_add_ps(z_L, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 2;
- _input += 2;
- //_input_BB += 2;
- _E_code += 2;
- _P_code += 2;
- _L_code +=2;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_E[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_P[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_L[2];
- //__VOLK_ATTR_ALIGNED(16) lv_32fc_t _input_BB;
-
- _mm_store_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
-
- dotProduct_E += ( dotProductVector_E[0] + dotProductVector_E[1] );
- dotProduct_P += ( dotProductVector_P[0] + dotProductVector_P[1] );
- dotProduct_L += ( dotProductVector_L[0] + dotProductVector_L[1] );
-
- if((num_points % 2) != 0)
- {
- //_input_BB = (*_input) * (*_carrier);
- dotProduct_E += (*_input) * (*_E_code)*(*_carrier);
- dotProduct_P += (*_input) * (*_P_code)*(*_carrier);
- dotProduct_L += (*_input) * (*_L_code)*(*_carrier);
- }
-
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
-}
-
-#endif /* LV_HAVE_SSE3 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, unsigned int num_points)
-{
- lv_32fc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE3
-#include <pmmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_a_sse3(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 2;
-
- lv_32fc_t dotProduct_E;
- memset(&dotProduct_E, 0x0, 2*sizeof(float));
- lv_32fc_t dotProduct_P;
- memset(&dotProduct_P, 0x0, 2*sizeof(float));
- lv_32fc_t dotProduct_L;
- memset(&dotProduct_L, 0x0, 2*sizeof(float));
-
- // Aux vars
- __m128 x, y, yl, yh, z, tmp1, tmp2, z_E, z_P, z_L;
-
- z_E = _mm_setzero_ps();
- z_P = _mm_setzero_ps();
- z_L = _mm_setzero_ps();
-
- //input and output vectors
- //lv_32fc_t* _input_BB = input_BB;
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm_load_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- //_mm_storeu_ps((float*)_input_BB,z); // Store the results back into the _input_BB container
-
- // correlation E,P,L (3x vector scalar product)
- // Early
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- x = z;
-
- y = _mm_load_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_E = _mm_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_P = _mm_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
-
- z_L = _mm_add_ps(z_L, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 2;
- _input += 2;
- //_input_BB += 2;
- _E_code += 2;
- _P_code += 2;
- _L_code +=2;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_E[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_P[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_L[2];
- //__VOLK_ATTR_ALIGNED(16) lv_32fc_t _input_BB;
-
- _mm_store_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
-
- dotProduct_E += ( dotProductVector_E[0] + dotProductVector_E[1] );
- dotProduct_P += ( dotProductVector_P[0] + dotProductVector_P[1] );
- dotProduct_L += ( dotProductVector_L[0] + dotProductVector_L[1] );
-
- if((num_points % 2) != 0)
- {
- //_input_BB = (*_input) * (*_carrier);
- dotProduct_E += (*_input) * (*_E_code)*(*_carrier);
- dotProduct_P += (*_input) * (*_P_code)*(*_carrier);
- dotProduct_L += (*_input) * (*_L_code)*(*_carrier);
- }
-
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
-}
-
-#endif /* LV_HAVE_SSE3 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_a_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, unsigned int num_points)
-{
- lv_32fc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5.h
deleted file mode 100644
index 14c9c4f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5.h
+++ /dev/null
@@ -1,848 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation with 64 bits vectors
- * \authors <ul>
- * <li> Javier Arribas, 2011. jarribas(at)cttc.es
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * VE, Early, Prompt, Late and VL correlation with 64 bits vectors (32 bits the
- * real part and 32 bits the imaginary part):
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 64 bits vectors) It returns the input
- * signal in base band (BB)
- * - VE values are calculated by multiplying the input signal in BB by the
- * VE code (multiplication of 64 bits vectors), accumulating the results
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 64 bits vectors), accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 64 bits vectors), accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 64 bits vectors), accumulating the results
- * - VL values are calculated by multiplying the input signal in BB by the
- * VL code (multiplication of 64 bits vectors), accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_AVX
-#include <immintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_u_avx(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 4;
-
- lv_32fc_t dotProduct_VE;
- lv_32fc_t dotProduct_E;
- lv_32fc_t dotProduct_P;
- lv_32fc_t dotProduct_L;
- lv_32fc_t dotProduct_VL;
-
- // Aux vars
- __m256 x, y, yl, yh, z, tmp1, tmp2, z_VE, z_E, z_P, z_L, z_VL;
- __m256 bb_signal_sample, bb_signal_sample_shuffled;
-
- z_VE = _mm256_setzero_ps();
- z_E = _mm256_setzero_ps();
- z_P = _mm256_setzero_ps();
- z_L = _mm256_setzero_ps();
- z_VL = _mm256_setzero_ps();
-
- //input and output vectors
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _VE_code = VE_code;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
- const lv_32fc_t* _VL_code = VL_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm256_loadu_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm256_loadu_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm256_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm256_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- bb_signal_sample = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- bb_signal_sample_shuffled = _mm256_shuffle_ps(bb_signal_sample,bb_signal_sample,0xB1); // Re-arrange bb_signal_sample to be ai,ar,bi,br
-
- // correlation VE,E,P,L,VL (5x vector scalar product)
- // VE
- y = _mm256_loadu_ps((float*)_VE_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VE = _mm256_add_ps(z_VE, z); // Add the complex multiplication results together
-
- // Early
- y = _mm256_loadu_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_E = _mm256_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- y = _mm256_loadu_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_P = _mm256_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- y = _mm256_loadu_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_L = _mm256_add_ps(z_L, z); // Add the complex multiplication results together
-
- // VL
- y = _mm256_loadu_ps((float*)_VL_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VL = _mm256_add_ps(z_VL, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 4;
- _input += 4;
- _VE_code += 4;
- _E_code += 4;
- _P_code += 4;
- _L_code += 4;
- _VL_code += 4;
- }
-
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_VE[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_E[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_P[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_L[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_VL[4];
-
- _mm256_storeu_ps((float*)dotProductVector_VE,z_VE); // Store the results back into the dot product vector
- _mm256_storeu_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm256_storeu_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm256_storeu_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
- _mm256_storeu_ps((float*)dotProductVector_VL,z_VL); // Store the results back into the dot product vector
-
- dotProduct_VE = ( dotProductVector_VE[0] + dotProductVector_VE[1] + dotProductVector_VE[2] + dotProductVector_VE[3] );
- dotProduct_E = ( dotProductVector_E[0] + dotProductVector_E[1] + dotProductVector_E[2] + dotProductVector_E[3] );
- dotProduct_P = ( dotProductVector_P[0] + dotProductVector_P[1] + dotProductVector_P[2] + dotProductVector_P[3] );
- dotProduct_L = ( dotProductVector_L[0] + dotProductVector_L[1] + dotProductVector_L[2] + dotProductVector_L[3] );
- dotProduct_VL = ( dotProductVector_VL[0] + dotProductVector_VL[1] + dotProductVector_VL[2] + dotProductVector_VL[3] );
-
- for (unsigned int i = 0; i<(num_points % 4); ++i)
- {
- dotProduct_VE += (*_input) * (*_VE_code++) * (*_carrier);
- dotProduct_E += (*_input) * (*_E_code++) * (*_carrier);
- dotProduct_P += (*_input) * (*_P_code++) * (*_carrier);
- dotProduct_L += (*_input) * (*_L_code++) * (*_carrier);
- dotProduct_VL += (*_input++) * (*_VL_code++) * (*_carrier++);
- }
-
- *VE_out = dotProduct_VE;
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
- *VL_out = dotProduct_VL;
-}
-#endif /* LV_HAVE_AVX */
-
-#ifdef LV_HAVE_SSE3
-#include <pmmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_u_sse3(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 2;
-
- lv_32fc_t dotProduct_VE;
- lv_32fc_t dotProduct_E;
- lv_32fc_t dotProduct_P;
- lv_32fc_t dotProduct_L;
- lv_32fc_t dotProduct_VL;
-
- // Aux vars
- __m128 x, y, yl, yh, z, tmp1, tmp2, z_VE, z_E, z_P, z_L, z_VL;
- __m128 bb_signal_sample, bb_signal_sample_shuffled;
-
- z_VE = _mm_setzero_ps();
- z_E = _mm_setzero_ps();
- z_P = _mm_setzero_ps();
- z_L = _mm_setzero_ps();
- z_VL = _mm_setzero_ps();
-
- //input and output vectors
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _VE_code = VE_code;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
- const lv_32fc_t* _VL_code = VL_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm_loadu_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_loadu_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- bb_signal_sample = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- bb_signal_sample_shuffled = _mm_shuffle_ps(bb_signal_sample,bb_signal_sample,0xB1); // Re-arrange bb_signal_sample to be ai,ar,bi,br
-
- // correlation VE,E,P,L,VL (5x vector scalar product)
- // VE
- y = _mm_loadu_ps((float*)_VE_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VE = _mm_add_ps(z_VE, z); // Add the complex multiplication results together
-
- // Early
- y = _mm_loadu_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_E = _mm_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- y = _mm_loadu_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_P = _mm_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- y = _mm_loadu_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_L = _mm_add_ps(z_L, z); // Add the complex multiplication results together
-
- // VL
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_loadu_ps((float*)_VL_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VL = _mm_add_ps(z_VL, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 2;
- _input += 2;
- _VE_code += 2;
- _E_code += 2;
- _P_code += 2;
- _L_code +=2;
- _VL_code +=2;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_VE[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_E[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_P[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_L[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_VL[2];
-
- _mm_storeu_ps((float*)dotProductVector_VE,z_VE); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)dotProductVector_VL,z_VL); // Store the results back into the dot product vector
-
- dotProduct_VE = ( dotProductVector_VE[0] + dotProductVector_VE[1] );
- dotProduct_E = ( dotProductVector_E[0] + dotProductVector_E[1] );
- dotProduct_P = ( dotProductVector_P[0] + dotProductVector_P[1] );
- dotProduct_L = ( dotProductVector_L[0] + dotProductVector_L[1] );
- dotProduct_VL = ( dotProductVector_VL[0] + dotProductVector_VL[1] );
-
- if((num_points % 2) != 0)
- {
- dotProduct_VE += (*_input) * (*_VE_code)*(*_carrier);
- dotProduct_E += (*_input) * (*_E_code)*(*_carrier);
- dotProduct_P += (*_input) * (*_P_code)*(*_carrier);
- dotProduct_L += (*_input) * (*_L_code)*(*_carrier);
- dotProduct_VL += (*_input) * (*_VL_code)*(*_carrier);
- }
-
- *VE_out = dotProduct_VE;
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
- *VL_out = dotProduct_VL;
-}
-#endif /* LV_HAVE_SSE3 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- lv_32fc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *VE_out += bb_signal_sample * VE_code[i];
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- *VL_out += bb_signal_sample * VL_code[i];
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_AVX
-#include <immintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_avx(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 4;
-
- lv_32fc_t dotProduct_VE;
- lv_32fc_t dotProduct_E;
- lv_32fc_t dotProduct_P;
- lv_32fc_t dotProduct_L;
- lv_32fc_t dotProduct_VL;
-
- // Aux vars
- __m256 x, y, yl, yh, z, tmp1, tmp2, z_VE, z_E, z_P, z_L, z_VL;
- __m256 bb_signal_sample, bb_signal_sample_shuffled;
-
- z_VE = _mm256_setzero_ps();
- z_E = _mm256_setzero_ps();
- z_P = _mm256_setzero_ps();
- z_L = _mm256_setzero_ps();
- z_VL = _mm256_setzero_ps();
-
- //input and output vectors
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _VE_code = VE_code;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
- const lv_32fc_t* _VL_code = VL_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm256_load_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm256_load_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm256_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm256_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- bb_signal_sample = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- bb_signal_sample_shuffled = _mm256_shuffle_ps(bb_signal_sample,bb_signal_sample,0xB1); // Re-arrange bb_signal_sample to be ai,ar,bi,br
-
- // correlation VE,E,P,L,VL (5x vector scalar product)
- // VE
- y = _mm256_load_ps((float*)_VE_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VE = _mm256_add_ps(z_VE, z); // Add the complex multiplication results together
-
- // Early
- y = _mm256_load_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_E = _mm256_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- y = _mm256_load_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_P = _mm256_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- y = _mm256_load_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_L = _mm256_add_ps(z_L, z); // Add the complex multiplication results together
-
- // VL
- y = _mm256_load_ps((float*)_VL_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm256_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm256_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm256_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm256_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm256_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VL = _mm256_add_ps(z_VL, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 4;
- _input += 4;
- _VE_code += 4;
- _E_code += 4;
- _P_code += 4;
- _L_code += 4;
- _VL_code += 4;
- }
-
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_VE[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_E[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_P[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_L[4];
- __VOLK_ATTR_ALIGNED(32) lv_32fc_t dotProductVector_VL[4];
-
- _mm256_store_ps((float*)dotProductVector_VE,z_VE); // Store the results back into the dot product vector
- _mm256_store_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm256_store_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm256_store_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
- _mm256_store_ps((float*)dotProductVector_VL,z_VL); // Store the results back into the dot product vector
-
- dotProduct_VE = ( dotProductVector_VE[0] + dotProductVector_VE[1] + dotProductVector_VE[2] + dotProductVector_VE[3] );
- dotProduct_E = ( dotProductVector_E[0] + dotProductVector_E[1] + dotProductVector_E[2] + dotProductVector_E[3] );
- dotProduct_P = ( dotProductVector_P[0] + dotProductVector_P[1] + dotProductVector_P[2] + dotProductVector_P[3] );
- dotProduct_L = ( dotProductVector_L[0] + dotProductVector_L[1] + dotProductVector_L[2] + dotProductVector_L[3] );
- dotProduct_VL = ( dotProductVector_VL[0] + dotProductVector_VL[1] + dotProductVector_VL[2] + dotProductVector_VL[3] );
-
- for (unsigned int i = 0; i<(num_points % 4); ++i)
- {
- dotProduct_VE += (*_input) * (*_VE_code++) * (*_carrier);
- dotProduct_E += (*_input) * (*_E_code++) * (*_carrier);
- dotProduct_P += (*_input) * (*_P_code++) * (*_carrier);
- dotProduct_L += (*_input) * (*_L_code++) * (*_carrier);
- dotProduct_VL += (*_input++) * (*_VL_code++) * (*_carrier++);
- }
-
- *VE_out = dotProduct_VE;
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
- *VL_out = dotProduct_VL;
-}
-#endif /* LV_HAVE_AVX */
-
-#ifdef LV_HAVE_SSE3
-#include <pmmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_sse3(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- unsigned int number = 0;
- const unsigned int halfPoints = num_points / 2;
-
- lv_32fc_t dotProduct_VE;
- lv_32fc_t dotProduct_E;
- lv_32fc_t dotProduct_P;
- lv_32fc_t dotProduct_L;
- lv_32fc_t dotProduct_VL;
-
- // Aux vars
- __m128 x, y, yl, yh, z, tmp1, tmp2, z_VE, z_E, z_P, z_L, z_VL;
- __m128 bb_signal_sample, bb_signal_sample_shuffled;
-
- z_VE = _mm_setzero_ps();
- z_E = _mm_setzero_ps();
- z_P = _mm_setzero_ps();
- z_L = _mm_setzero_ps();
- z_VL = _mm_setzero_ps();
-
- //input and output vectors
- const lv_32fc_t* _input = input;
- const lv_32fc_t* _carrier = carrier;
- const lv_32fc_t* _VE_code = VE_code;
- const lv_32fc_t* _E_code = E_code;
- const lv_32fc_t* _P_code = P_code;
- const lv_32fc_t* _L_code = L_code;
- const lv_32fc_t* _VL_code = VL_code;
-
- for(;number < halfPoints; number++)
- {
- // carrier wipe-off (vector point-to-point product)
- x = _mm_load_ps((float*)_input); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_carrier); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(x,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
-
- x = _mm_shuffle_ps(x,x,0xB1); // Re-arrange x to be ai,ar,bi,br
-
- tmp2 = _mm_mul_ps(x,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- bb_signal_sample = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- bb_signal_sample_shuffled = _mm_shuffle_ps(bb_signal_sample,bb_signal_sample,0xB1); // Re-arrange bb_signal_sample to be ai,ar,bi,br
-
- // correlation VE,E,P,L,VL (5x vector scalar product)
- // VE
- y = _mm_load_ps((float*)_VE_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VE = _mm_add_ps(z_VE, z); // Add the complex multiplication results together
-
- // Early
- y = _mm_load_ps((float*)_E_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_E = _mm_add_ps(z_E, z); // Add the complex multiplication results together
-
- // Prompt
- y = _mm_load_ps((float*)_P_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_P = _mm_add_ps(z_P, z); // Add the complex multiplication results together
-
- // Late
- y = _mm_load_ps((float*)_L_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_L = _mm_add_ps(z_L, z); // Add the complex multiplication results together
-
- // VL
- //x = _mm_load_ps((float*)_input_BB); // Load the ar + ai, br + bi as ar,ai,br,bi
- y = _mm_load_ps((float*)_VL_code); // Load the cr + ci, dr + di as cr,ci,dr,di
-
- yl = _mm_moveldup_ps(y); // Load yl with cr,cr,dr,dr
- yh = _mm_movehdup_ps(y); // Load yh with ci,ci,di,di
-
- tmp1 = _mm_mul_ps(bb_signal_sample,yl); // tmp1 = ar*cr,ai*cr,br*dr,bi*dr
- tmp2 = _mm_mul_ps(bb_signal_sample_shuffled,yh); // tmp2 = ai*ci,ar*ci,bi*di,br*di
-
- z = _mm_addsub_ps(tmp1,tmp2); // ar*cr-ai*ci, ai*cr+ar*ci, br*dr-bi*di, bi*dr+br*di
- z_VL = _mm_add_ps(z_VL, z); // Add the complex multiplication results together
-
- /*pointer increment*/
- _carrier += 2;
- _input += 2;
- _VE_code += 2;
- _E_code += 2;
- _P_code += 2;
- _L_code +=2;
- _VL_code +=2;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_VE[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_E[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_P[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_L[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t dotProductVector_VL[2];
-
- _mm_store_ps((float*)dotProductVector_VE,z_VE); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_E,z_E); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_P,z_P); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_L,z_L); // Store the results back into the dot product vector
- _mm_store_ps((float*)dotProductVector_VL,z_VL); // Store the results back into the dot product vector
-
- dotProduct_VE = ( dotProductVector_VE[0] + dotProductVector_VE[1] );
- dotProduct_E = ( dotProductVector_E[0] + dotProductVector_E[1] );
- dotProduct_P = ( dotProductVector_P[0] + dotProductVector_P[1] );
- dotProduct_L = ( dotProductVector_L[0] + dotProductVector_L[1] );
- dotProduct_VL = ( dotProductVector_VL[0] + dotProductVector_VL[1] );
-
- if((num_points % 2) != 0)
- {
- dotProduct_VE += (*_input) * (*_VE_code)*(*_carrier);
- dotProduct_E += (*_input) * (*_E_code)*(*_carrier);
- dotProduct_P += (*_input) * (*_P_code)*(*_carrier);
- dotProduct_L += (*_input) * (*_L_code)*(*_carrier);
- dotProduct_VL += (*_input) * (*_VL_code)*(*_carrier);
- }
-
- *VE_out = dotProduct_VE;
- *E_out = dotProduct_E;
- *P_out = dotProduct_P;
- *L_out = dotProduct_L;
- *VL_out = dotProduct_VL;
-}
-#endif /* LV_HAVE_SSE3 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the VE, Early, Prompt, Late and VL correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code VE PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param VL_code VL PRN code replica input
- \param VE_out VE correlation output
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param VL_out VL correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_32fc_t* input, const lv_32fc_t* carrier, const lv_32fc_t* VE_code, const lv_32fc_t* E_code, const lv_32fc_t* P_code, const lv_32fc_t* L_code, const lv_32fc_t* VL_code, unsigned int num_points)
-{
- lv_32fc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *VE_out += bb_signal_sample * VE_code[i];
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- *VL_out += bb_signal_sample * VL_code[i];
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h
deleted file mode 100644
index 5b39eee..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h
+++ /dev/null
@@ -1,614 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation with 16 bits vectors, and accumulates the results into float32.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Early, Prompt, and Late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part), and accumulates the result
- * in 32 bits single point values, returning float32 values:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse4_1(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 E_code_acc, P_code_acc, L_code_acc;
- __m128i input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2;
- __m128 output_ps;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- E_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
-
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_sse2(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 E_code_acc, P_code_acc, L_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- E_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_loadu_si128((__m128i*)input_ptr);
- y = _mm_loadu_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y = _mm_loadu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_loadu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_loadu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
-
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
-
- for (unsigned int i = 0; i<2; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_sse4_1(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 E_code_acc, P_code_acc, L_code_acc;
- __m128i input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2;
- __m128 output_ps;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- E_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
-
- _mm_store_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_sse2(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 E_code_acc, P_code_acc, L_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- E_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
-
- _mm_store_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
-
- for (unsigned int i = 0; i<2; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_generic(lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h
deleted file mode 100644
index 03b7f4f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h
+++ /dev/null
@@ -1,874 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation with 16 bits vectors
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Early, Prompt, and Late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part):
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-
-/*! \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse4_1(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample, real_E_code_acc, imag_E_code_acc, real_L_code_acc, imag_L_code_acc, real_P_code_acc, imag_P_code_acc;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_8sc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_8sc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_8sc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_si128();
- imag_E_code_acc = _mm_setzero_si128();
- real_L_code_acc = _mm_setzero_si128();
- imag_L_code_acc = _mm_setzero_si128();
- real_P_code_acc = _mm_setzero_si128();
- imag_P_code_acc = _mm_setzero_si128();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x, 1);
- imagx = _mm_and_si128 (imagx, mult1);
- realx = _mm_and_si128 (x, mult1);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_E_code_acc = _mm_add_epi16 (real_E_code_acc, real_output);
- imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_L_code_acc = _mm_add_epi16 (real_L_code_acc, real_output);
- imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_P_code_acc = _mm_add_epi16 (real_P_code_acc, real_output);
- imag_P_code_acc = _mm_add_epi16 (imag_P_code_acc, imag_output);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- L_code_ptr += 8;
- P_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t E_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t L_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t P_dotProductVector[8];
-
- imag_E_code_acc = _mm_slli_si128 (imag_E_code_acc, 1);
- output = _mm_blendv_epi8 (imag_E_code_acc, real_E_code_acc, mult1);
- _mm_storeu_si128((__m128i*)E_dotProductVector, output);
-
- imag_L_code_acc = _mm_slli_si128 (imag_L_code_acc, 1);
- output = _mm_blendv_epi8 (imag_L_code_acc, real_L_code_acc, mult1);
- _mm_storeu_si128((__m128i*)L_dotProductVector, output);
-
- imag_P_code_acc = _mm_slli_si128 (imag_P_code_acc, 1);
- output = _mm_blendv_epi8 (imag_P_code_acc, real_P_code_acc, mult1);
- _mm_storeu_si128((__m128i*)P_dotProductVector, output);
-
- for (int i = 0; i<8; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += bb_signal_sample * (*E_code_ptr++);
- *P_out_ptr += bb_signal_sample * (*P_code_ptr++);
- *L_out_ptr += bb_signal_sample * (*L_code_ptr++);
- }
-}
-
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_sse2(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample, real_E_code_acc, imag_E_code_acc, real_L_code_acc, imag_L_code_acc, real_P_code_acc, imag_P_code_acc;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_8sc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_8sc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_8sc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_si128();
- imag_E_code_acc = _mm_setzero_si128();
- real_L_code_acc = _mm_setzero_si128();
- imag_L_code_acc = _mm_setzero_si128();
- real_P_code_acc = _mm_setzero_si128();
- imag_P_code_acc = _mm_setzero_si128();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_loadu_si128((__m128i*)input_ptr);
- y = _mm_loadu_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x, 1);
- imagx = _mm_and_si128 (imagx, mult1);
- realx = _mm_and_si128 (x, mult1);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y = _mm_loadu_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_E_code_acc = _mm_add_epi16 (real_E_code_acc, real_output);
- imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output);
-
- //Get late values
- y = _mm_loadu_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_L_code_acc = _mm_add_epi16 (real_L_code_acc, real_output);
- imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output);
-
- //Get prompt values
- y = _mm_loadu_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_P_code_acc = _mm_add_epi16 (real_P_code_acc, real_output);
- imag_P_code_acc = _mm_add_epi16 (imag_P_code_acc, imag_output);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- L_code_ptr += 8;
- P_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t E_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t L_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t P_dotProductVector[8];
-
- real_E_code_acc = _mm_and_si128 (real_E_code_acc, mult1);
- imag_E_code_acc = _mm_and_si128 (imag_E_code_acc, mult1);
- imag_E_code_acc = _mm_slli_si128 (imag_E_code_acc, 1);
- output = _mm_or_si128 (real_E_code_acc, imag_E_code_acc);
- _mm_storeu_si128((__m128i*)E_dotProductVector, output);
-
- real_L_code_acc = _mm_and_si128 (real_L_code_acc, mult1);
- imag_L_code_acc = _mm_and_si128 (imag_L_code_acc, mult1);
- imag_L_code_acc = _mm_slli_si128 (imag_L_code_acc, 1);
- output = _mm_or_si128 (real_L_code_acc, imag_L_code_acc);
- _mm_storeu_si128((__m128i*)L_dotProductVector, output);
-
- real_P_code_acc = _mm_and_si128 (real_P_code_acc, mult1);
- imag_P_code_acc = _mm_and_si128 (imag_P_code_acc, mult1);
- imag_P_code_acc = _mm_slli_si128 (imag_P_code_acc, 1);
- output = _mm_or_si128 (real_P_code_acc, imag_P_code_acc);
- _mm_storeu_si128((__m128i*)P_dotProductVector, output);
-
- for (int i = 0; i<8; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += bb_signal_sample * (*E_code_ptr++);
- *P_out_ptr += bb_signal_sample * (*P_code_ptr++);
- *L_out_ptr += bb_signal_sample * (*L_code_ptr++);
- }
-}
-
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_generic(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_sse4_1(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample, real_E_code_acc, imag_E_code_acc, real_L_code_acc, imag_L_code_acc, real_P_code_acc, imag_P_code_acc;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_8sc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_8sc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_8sc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_si128();
- imag_E_code_acc = _mm_setzero_si128();
- real_L_code_acc = _mm_setzero_si128();
- imag_L_code_acc = _mm_setzero_si128();
- real_P_code_acc = _mm_setzero_si128();
- imag_P_code_acc = _mm_setzero_si128();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x, 1);
- imagx = _mm_and_si128 (imagx, mult1);
- realx = _mm_and_si128 (x, mult1);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_E_code_acc = _mm_add_epi16 (real_E_code_acc, real_output);
- imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_L_code_acc = _mm_add_epi16 (real_L_code_acc, real_output);
- imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_P_code_acc = _mm_add_epi16 (real_P_code_acc, real_output);
- imag_P_code_acc = _mm_add_epi16 (imag_P_code_acc, imag_output);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- L_code_ptr += 8;
- P_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t E_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t L_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t P_dotProductVector[8];
-
- imag_E_code_acc = _mm_slli_si128 (imag_E_code_acc, 1);
- output = _mm_blendv_epi8 (imag_E_code_acc, real_E_code_acc, mult1);
- _mm_store_si128((__m128i*)E_dotProductVector, output);
-
- imag_L_code_acc = _mm_slli_si128 (imag_L_code_acc, 1);
- output = _mm_blendv_epi8 (imag_L_code_acc, real_L_code_acc, mult1);
- _mm_store_si128((__m128i*)L_dotProductVector, output);
-
- imag_P_code_acc = _mm_slli_si128 (imag_P_code_acc, 1);
- output = _mm_blendv_epi8 (imag_P_code_acc, real_P_code_acc, mult1);
- _mm_store_si128((__m128i*)P_dotProductVector, output);
-
- for (int i = 0; i<8; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += bb_signal_sample * (*E_code_ptr++);
- *P_out_ptr += bb_signal_sample * (*P_code_ptr++);
- *L_out_ptr += bb_signal_sample * (*L_code_ptr++);
- }
-}
-
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_sse2(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample, real_E_code_acc, imag_E_code_acc, real_L_code_acc, imag_L_code_acc, real_P_code_acc, imag_P_code_acc;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* E_code_ptr = E_code;
- lv_8sc_t* E_out_ptr = E_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_8sc_t* L_out_ptr = L_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_8sc_t* P_out_ptr = P_out;
-
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_E_code_acc = _mm_setzero_si128();
- imag_E_code_acc = _mm_setzero_si128();
- real_L_code_acc = _mm_setzero_si128();
- imag_L_code_acc = _mm_setzero_si128();
- real_P_code_acc = _mm_setzero_si128();
- imag_P_code_acc = _mm_setzero_si128();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x, 1);
- imagx = _mm_and_si128 (imagx, mult1);
- realx = _mm_and_si128 (x, mult1);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_E_code_acc = _mm_add_epi16 (real_E_code_acc, real_output);
- imag_E_code_acc = _mm_add_epi16 (imag_E_code_acc, imag_output);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_L_code_acc = _mm_add_epi16 (real_L_code_acc, real_output);
- imag_L_code_acc = _mm_add_epi16 (imag_L_code_acc, imag_output);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- real_P_code_acc = _mm_add_epi16 (real_P_code_acc, real_output);
- imag_P_code_acc = _mm_add_epi16 (imag_P_code_acc, imag_output);
-
- input_ptr += 8;
- carrier_ptr += 8;
- E_code_ptr += 8;
- L_code_ptr += 8;
- P_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t E_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t L_dotProductVector[8];
- __VOLK_ATTR_ALIGNED(16) lv_8sc_t P_dotProductVector[8];
-
- real_E_code_acc = _mm_and_si128 (real_E_code_acc, mult1);
- imag_E_code_acc = _mm_and_si128 (imag_E_code_acc, mult1);
- imag_E_code_acc = _mm_slli_si128 (imag_E_code_acc, 1);
- output = _mm_or_si128 (real_E_code_acc, imag_E_code_acc);
- _mm_store_si128((__m128i*)E_dotProductVector, output);
-
- real_L_code_acc = _mm_and_si128 (real_L_code_acc, mult1);
- imag_L_code_acc = _mm_and_si128 (imag_L_code_acc, mult1);
- imag_L_code_acc = _mm_slli_si128 (imag_L_code_acc, 1);
- output = _mm_or_si128 (real_L_code_acc, imag_L_code_acc);
- _mm_store_si128((__m128i*)L_dotProductVector, output);
-
- real_P_code_acc = _mm_and_si128 (real_P_code_acc, mult1);
- imag_P_code_acc = _mm_and_si128 (imag_P_code_acc, mult1);
- imag_P_code_acc = _mm_slli_si128 (imag_P_code_acc, 1);
- output = _mm_or_si128 (real_P_code_acc, imag_P_code_acc);
- _mm_store_si128((__m128i*)P_dotProductVector, output);
-
- for (unsigned int i = 0; i<8; ++i)
- {
- *E_out_ptr += E_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get early, late, and prompt values for each
- *E_out_ptr += bb_signal_sample * (*E_code_ptr++);
- *P_out_ptr += bb_signal_sample * (*P_code_ptr++);
- *L_out_ptr += bb_signal_sample * (*L_code_ptr++);
- }
-}
-
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_generic(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- // perform Early, Prompt and Late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get early, late, and prompt values for each
- *E_out += bb_signal_sample * E_code[i];
- *P_out += bb_signal_sample * P_code[i];
- *L_out += bb_signal_sample * L_code[i];
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#ifdef LV_HAVE_ORC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param E_code Early PRN code replica input
- \param P_code Early PRN code replica input
- \param L_code Early PRN code replica input
- \param E_out Early correlation output
- \param P_out Early correlation output
- \param L_out Early correlation output
- \param num_points The number of complex values in vectors
- */
-
-extern void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_first_a_orc_impl(short* E_out_real, short* E_out_imag, short* P_out_real, short* P_out_imag, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, unsigned int num_points);
-extern void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_second_a_orc_impl(short* L_out_real, short* L_out_imag, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* L_code, unsigned int num_points);
-static inline void volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_u_orc(lv_8sc_t* E_out, lv_8sc_t* P_out, lv_8sc_t* L_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, unsigned int num_points){
-
- short E_out_real = 0;
- short E_out_imag = 0;
- char* E_out_real_c = (char*)&E_out_real;
- E_out_real_c++;
- char* E_out_imag_c = (char*)&E_out_imag;
- E_out_imag_c++;
-
- short P_out_real = 0;
- short P_out_imag = 0;
- char* P_out_real_c = (char*)&P_out_real;
- P_out_real_c++;
- char* P_out_imag_c = (char*)&P_out_imag;
- P_out_imag_c++;
-
- short L_out_real = 0;
- short L_out_imag = 0;
- char* L_out_real_c = (char*)&L_out_real;
- L_out_real_c++;
- char* L_out_imag_c = (char*)&L_out_imag;
- L_out_imag_c++;
-
- volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_first_a_orc_impl( &E_out_real, &E_out_imag, &P_out_real, &P_out_imag, input, carrier, E_code, P_code, num_points);
- volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_second_a_orc_impl( &L_out_real, &L_out_imag, input, carrier, L_code, num_points);
-
- //ORC implementation of 8ic_x5_cw_epl_corr_8ic_x3 is done in two different functions because it seems that
- //in one function the length of the code gives memory problems (bad access, segmentation fault).
- //Also, the maximum number of accumulators that can be used is 4 (and we need 6).
- //The "carrier wipe-off" step is done two times: one in the first function and another one in the second.
- //Joining all the ORC code in one function would be quicker because the "carrier wipe-off" step would be done just
- //one time.
-
- *E_out = lv_cmake(*E_out_real_c, *E_out_imag_c);
- *P_out = lv_cmake(*P_out_real_c, *P_out_imag_c);
- *L_out = lv_cmake(*L_out_real_c, *L_out_imag_c);
-}
-#endif /* LV_HAVE_ORC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h
deleted file mode 100644
index e3c0666..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h
+++ /dev/null
@@ -1,797 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Very early, Early, Prompt, Late and very late correlation with 16 bits vectors, and accumulates the results into float32. In order to avoid overflow, If input, carrier and XX_code have the same number of bits, they must be values between —3 and 3 (2 bits).
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Very early, Early, Prompt, Late and very late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part), and accumulates the result
- * in 32 bits single point values, returning float32 values:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Very Early values are calculated by multiplying the input signal in BB by the
- * very early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Very Late values are calculated by multiplying the input signal in BB by the
- * very late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- *
- * -------------------------------------------------------------------------
- * Bits analysis
- *
- * input = 8 bits
- * carrier = 8 bits
- * XX_code = 8 bits
- * XX_out = 8 bits
- * bb_signal_sample = 8 bits
- *
- * bb_signal_sample = input*carrier -> 17 bits limited to 8 bits = input and carrier must be values between —7 and 7 to avoid overflow (3 bits)
- *
- * XX_out16 = XX_code*bb_signal_sample -> 17 bits limited to 8 bits = XX_code and bb_signal_sample must be values between —7 and 7 to avoid overflow (3 bits)
- *
- * conclusion = input and carrier must be values between —1 and 1 (1 bit) and XX_code must be values between —7 and 7 to avoid overflow (3 bits)
- * If input, carrier and XX_code have the same number of bits, they must be values between —3 and 3 to avoid overflow (2 bits).
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2;
- __m128 output_ps;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_storeu_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_sse2(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_loadu_si128((__m128i*)input_ptr);
- y = _mm_loadu_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y = _mm_loadu_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_1);
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2);
-
- //Get early values
- y = _mm_loadu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_loadu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_loadu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- //Get very late values
- y = _mm_loadu_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_1);
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_storeu_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (unsigned int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform very early, Early, Prompt, Late and very late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code[i]);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code[i]);
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2;
- __m128 output_ps;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y = _mm_load_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps);
-
- //Get very late values
- y = _mm_load_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE4_1(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_i32_1, output_i32_2, output_ps)
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_store_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_sse2(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(unsigned int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(x, mult1, realx, imagx)
- CM_8IC_REARRANGE_VECTOR_INTO_REAL_IMAG_16IC_X2_U_SSE2(y, mult1, realy, imagy)
-
- CM_16IC_X4_SCALAR_PRODUCT_16IC_X2_U_SSE2(realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_bb_signal_sample, imag_bb_signal_sample)
-
- //Get very early values
- y = _mm_load_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_1);
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- //Get very late values
- y = _mm_load_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_32FC_X2_U_SSE2(y, mult1, realy, imagy, real_bb_signal_sample, imag_bb_signal_sample,realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, real_output, imag_output, input_i_1, input_i_2, output_i32, output_ps_1, output_ps_2)
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_1);
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_store_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (unsigned int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(unsigned int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- lv_8sc_t bb_signal_sample;
-
- bb_signal_sample = lv_cmake(0, 0);
-
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
- // perform very early, Early, Prompt, Late and very late correlation
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
-
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code[i]);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code[i]);
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h
deleted file mode 100644
index 9a28147..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h
+++ /dev/null
@@ -1,1518 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Very early, Early, Prompt, Late and very late correlation with 16 bits vectors using different methods: inside u_sse4_1_first there is one method, inside u_sse4_1_second there is another... This protokernel has been created to test the performance of different methods.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Very early, Early, Prompt, Late and very late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part), and accumulates the result
- * in 32 bits single point values, returning float32 values:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Very Early values are calculated by multiplying the input signal in BB by the
- * very early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Very Late values are calculated by multiplying the input signal in BB by the
- * very late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_first(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, y, real_bb_signal_sample, imag_bb_signal_sample;
- __m128i mult1, realx, imagx, realy, imagy, realx_mult_realy, imagx_mult_imagy, realx_mult_imagy, imagx_mult_realy, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- imagx = _mm_srli_si128 (x, 1);
- imagx = _mm_and_si128 (imagx, mult1);
- realx = _mm_and_si128 (x, mult1);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (realx, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imagx, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (realx, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imagx, realy);
-
- real_bb_signal_sample = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_bb_signal_sample = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_1);
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- imagy = _mm_srli_si128 (y, 1);
- imagy = _mm_and_si128 (imagy, mult1);
- realy = _mm_and_si128 (y, mult1);
-
- realx_mult_realy = _mm_mullo_epi16 (real_bb_signal_sample, realy);
- imagx_mult_imagy = _mm_mullo_epi16 (imag_bb_signal_sample, imagy);
- realx_mult_imagy = _mm_mullo_epi16 (real_bb_signal_sample, imagy);
- imagx_mult_realy = _mm_mullo_epi16 (imag_bb_signal_sample, realy);
-
- real_output = _mm_sub_epi16 (realx_mult_realy, imagx_mult_imagy);
- imag_output = _mm_add_epi16 (realx_mult_imagy, imagx_mult_realy);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_1);
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_storeu_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_second(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i mult1, output, real_output, imag_output;
-
- __m128 VE_code_acc, E_code_acc, P_code_acc, L_code_acc, VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 output_ps_1, output_ps_2;
-
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- *VE_out_ptr = 0;
- *E_out_ptr = 0;
- *P_out_ptr = 0;
- *L_out_ptr = 0;
- *VL_out_ptr = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- VE_code_acc = _mm_setzero_ps();
- E_code_acc = _mm_setzero_ps();
- P_code_acc = _mm_setzero_ps();
- L_code_acc = _mm_setzero_ps();
- VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- y_aux = _mm_sign_epi8 (y, x);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, x);
- imag_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_1);
- VE_code_acc = _mm_add_ps (VE_code_acc, output_ps_2);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_1);
- E_code_acc = _mm_add_ps (E_code_acc, output_ps_2);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_1);
- P_code_acc = _mm_add_ps (P_code_acc, output_ps_2);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_1);
- L_code_acc = _mm_add_ps (L_code_acc, output_ps_2);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- output = _mm_blendv_epi8 (imag_output, real_output, mult1);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_1 = _mm_cvtepi32_ps(output_i32);
-
- input_i_1 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- input_i_2 = _mm_cvtepi8_epi32(output);
- output = _mm_srli_si128 (output, 4);
- output_i32 = _mm_add_epi32 (input_i_1, input_i_2);
- output_ps_2 = _mm_cvtepi32_ps(output_i32);
-
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_1);
- VL_code_acc = _mm_add_ps (VL_code_acc, output_ps_2);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VE_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t E_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t P_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t L_dotProductVector[2];
- __VOLK_ATTR_ALIGNED(16) lv_32fc_t VL_dotProductVector[2];
-
- _mm_storeu_ps((float*)VE_dotProductVector,VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)E_dotProductVector,E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)P_dotProductVector,P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)L_dotProductVector,L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)VL_dotProductVector,VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<2; ++i)
- {
- *VE_out_ptr += VE_dotProductVector[i];
- *E_out_ptr += E_dotProductVector[i];
- *P_out_ptr += P_dotProductVector[i];
- *L_out_ptr += L_dotProductVector[i];
- *VL_out_ptr += VL_dotProductVector[i];
- }
- }
-
- lv_8sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * (*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * (*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * (*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * (*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_third(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i mult1, real_output, imag_output;
-
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2, real_output_i32, imag_output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- y_aux = _mm_sign_epi8 (y, x);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, x);
- imag_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_sse4_1_fourth(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i real_output, imag_output;
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i real_output_i_1, real_output_i_2, imag_output_i_1, imag_output_i_2, real_output_i32, imag_output_i32;
- __m128 real_output_ps, imag_output_ps;
- __m128i minus128control;
-
- __m128i minus128 = _mm_set1_epi8 (-128);
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
- __m128i mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- y_aux = _mm_sign_epi8 (y, x);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, x);
- imag_output = _mm_maddubs_epi16 (x_abs, y_aux);
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
- minus128control = _mm_cmpeq_epi8 (y, minus128);
- y = _mm_sub_epi8 (y, minus128control);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
- minus128control = _mm_cmpeq_epi8 (y, minus128);
- y = _mm_sub_epi8 (y, minus128control);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
- minus128control = _mm_cmpeq_epi8 (y, minus128);
- y = _mm_sub_epi8 (y, minus128control);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
- minus128control = _mm_cmpeq_epi8 (y, minus128);
- y = _mm_sub_epi8 (y, minus128control);
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, rearrange_sequence);
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
- minus128control = _mm_cmpeq_epi8 (y, minus128);
- y = _mm_sub_epi8 (y, minus128control);
-
-
- y_aux = _mm_sign_epi8 (y, bb_signal_sample_aux);
- y_aux = _mm_sign_epi8 (y_aux, check_sign_sequence);
- real_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- y_aux = _mm_shuffle_epi8 (y, _mm_set_epi8 (14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1));
- y_aux = _mm_sign_epi8 (y_aux, bb_signal_sample_aux);
- imag_output = _mm_maddubs_epi16 (bb_signal_sample_aux_abs, y_aux);
-
- real_output_i_1 = _mm_cvtepi16_epi32(real_output);
- real_output = _mm_srli_si128 (real_output, 8);
- real_output_i_2 = _mm_cvtepi16_epi32(real_output);
- real_output_i32 = _mm_add_epi32 (real_output_i_1, real_output_i_2);
- real_output_ps = _mm_cvtepi32_ps(real_output_i32);
-
- imag_output_i_1 = _mm_cvtepi16_epi32(imag_output);
- imag_output = _mm_srli_si128 (imag_output, 8);
- imag_output_i_2 = _mm_cvtepi16_epi32(imag_output);
- imag_output_i32 = _mm_add_epi32 (imag_output_i_1, imag_output_i_2);
- imag_output_ps = _mm_cvtepi32_ps(imag_output_i32);
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-
-#ifdef LV_HAVE_GENERIC
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
-
-
- lv_16sc_t VE_code_value;
- lv_16sc_t E_code_value;
- lv_16sc_t P_code_value;
- lv_16sc_t L_code_value;
- lv_16sc_t VL_code_value;
- lv_16sc_t bb_signal_sample;
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- VE_code_value = VE_code[i];
- E_code_value = E_code[i];
- P_code_value = P_code[i];
- L_code_value = L_code[i];
- VL_code_value = VL_code[i];
-
- if(lv_creal(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(-127, lv_cimag(VE_code_value));
- }
- if(lv_cimag(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(lv_creal(VE_code_value), -127);
- }
-
- if(lv_creal(E_code_value) == -128)
- {
- E_code_value = lv_cmake(-127, lv_cimag(E_code_value));
- }
- if(lv_cimag(E_code_value) == -128)
- {
- E_code_value = lv_cmake(lv_creal(E_code_value), -127);
- }
-
- if(lv_creal(P_code_value) == -128)
- {
- P_code_value = lv_cmake(-127, lv_cimag(P_code_value));
- }
- if(lv_cimag(P_code_value) == -128)
- {
- P_code_value = lv_cmake(lv_creal(P_code_value), -127);
- }
-
- if(lv_creal(L_code_value) == -128)
- {
- L_code_value = lv_cmake(-127, lv_cimag(L_code_value));
- }
- if(lv_cimag(L_code_value) == -128)
- {
- L_code_value = lv_cmake(lv_creal(L_code_value), -127);
- }
-
- if(lv_creal(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(-127, lv_cimag(VL_code_value));
- }
- if(lv_cimag(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(lv_creal(VL_code_value), -127);
- }
-
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get very early, early, prompt, late and very late values for each
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code_value);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code_value);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code_value);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code_value);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code_value);
- }
-}
-
-#endif /* LV_HAVE_GENERIC */
-
-//#ifdef LV_HAVE_GENERIC
-//#include <stdio.h>
-//#include <stdlib.h>
-//#include <tmmintrin.h>
-//
-//#ifndef MAX
-//#define MAX(a,b) ((a) > (b) ? a : b)
-//#endif
-//
-//#ifndef MIN
-//#define MIN(a,b) ((a) < (b) ? a : b)
-//#endif
-//
-///*!
-// \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
-// \param input The input signal input
-// \param carrier The carrier signal input
-// \param VE_code Very Early PRN code replica input
-// \param E_code Early PRN code replica input
-// \param P_code Prompt PRN code replica input
-// \param L_code Late PRN code replica input
-// \param VL_code Very Late PRN code replica input
-// \param VE_out Very Early correlation output
-// \param E_out Early correlation output
-// \param P_out Prompt correlation output
-// \param L_out Late correlation output
-// \param VL_out Very Late correlation output
-// \param num_points The number of complex values in vectors
-// */
-//static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-//{
-// *VE_out = 0;
-// *E_out = 0;
-// *P_out = 0;
-// *L_out = 0;
-// *VL_out = 0;
-//
-// lv_16sc_t VE_out16;
-// lv_16sc_t E_out16;
-// lv_16sc_t P_out16;
-// lv_16sc_t L_out16;
-// lv_16sc_t VL_out16;
-//
-// int32_t max = 32767;
-// int32_t min = -32768;
-//
-// int16_t real_real;
-// int16_t imag_imag;
-// int16_t real_imag;
-// int16_t imag_real;
-// int32_t out_real_32;
-// int32_t out_imag_32;
-// int16_t out_real_16;
-// int16_t out_imag_16;
-// int16_t aux1;
-// int16_t aux2;
-//
-//
-// lv_8sc_t bb_signal_sample = lv_cmake(0, 0);
-//
-// // perform very early, Early, Prompt, Late and very late correlation
-// for(int i=0; i < num_points; ++i)
-// {
-// //Perform the carrier wipe-off
-// bb_signal_sample = input[i] * carrier[i];
-//
-// aux1 = (int16_t)lv_creal(bb_signal_sample);
-// aux2 = (int16_t)lv_creal(VE_code[i]);
-// real_real = aux1*aux2;
-// aux1 = (int16_t)lv_cimag(bb_signal_sample);
-// aux2 = (int16_t)lv_cimag(VE_code[i]);
-// imag_imag = aux1*aux2;
-// aux1 = (int16_t)lv_creal(bb_signal_sample);
-// aux2 = (int16_t)lv_cimag(VE_code[i]);
-// real_imag = aux1*aux2;
-// aux1 = (int16_t)lv_cimag(bb_signal_sample);
-// aux2 = (int16_t)lv_creal(VE_code[i]);
-// imag_real = aux1*aux2;
-// out_real_32 = (int32_t)real_real - (int32_t)imag_imag;
-// out_imag_32 = (int32_t)real_imag + (int32_t)imag_real;
-// out_real_16 = MIN(MAX(out_real_32, min), max);
-// out_imag_16 = MIN(MAX(out_imag_32, min), max);
-// VE_out16 = lv_cmake(out_real_16, out_imag_16);
-//
-//
-//
-// if(lv_creal(L_code[i]) == -128)
-// {
-// int8_t* L_pointer = (int8_t*)&L_code[i];
-// *L_pointer = -127;
-// }
-// if(lv_cimag(L_code[i]) == -128)
-// {
-// int8_t* L_pointer = (int8_t*)&L_code[i];
-// L_pointer++;
-// *L_pointer = -127;
-// }
-// aux1 = (int16_t)lv_creal(bb_signal_sample);
-// aux2 = (int16_t)lv_creal(L_code[i]);
-// real_real = aux1*aux2;
-// aux1 = (int16_t)lv_cimag(bb_signal_sample);
-// aux2 = (int16_t)lv_cimag(L_code[i]);
-// imag_imag = aux1*aux2;
-// aux1 = (int16_t)lv_creal(bb_signal_sample);
-// aux2 = (int16_t)lv_cimag(L_code[i]);
-// real_imag = aux1*aux2;
-// aux1 = (int16_t)lv_cimag(bb_signal_sample);
-// aux2 = (int16_t)lv_creal(L_code[i]);
-// imag_real = aux1*aux2;
-// out_real_32 = (int32_t)real_real - (int32_t)imag_imag;
-// out_imag_32 = (int32_t)real_imag + (int32_t)imag_real;
-// out_real_16 = MIN(MAX(out_real_32, min), max);
-// out_imag_16 = MIN(MAX(out_imag_32, min), max);
-// L_out16 = lv_cmake(out_real_16, out_imag_16);
-//
-// E_out16 = (lv_16sc_t)bb_signal_sample * (lv_16sc_t)E_code[i];
-// P_out16 = (lv_16sc_t)bb_signal_sample * (lv_16sc_t)P_code[i];
-// VL_out16 = (lv_16sc_t)bb_signal_sample * (lv_16sc_t)VL_code[i];
-//
-//
-// *VE_out += (lv_32fc_t) VE_out16;
-// *E_out += (lv_32fc_t) E_out16;
-// *P_out += (lv_32fc_t) P_out16;
-// *L_out += (lv_32fc_t) L_out16;
-// *VL_out += (lv_32fc_t) VL_out16;
-//
-// //error en la parte real de L con 32 muestras
-// //*L_out = lv_cmake(12, 12);
-// }
-//}
-//
-//#endif /* LV_HAVE_GENERIC */
-
-//#ifdef LV_HAVE_GENERIC
-///*!
-// \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
-// \param input The input signal input
-// \param carrier The carrier signal input
-// \param VE_code Very Early PRN code replica input
-// \param E_code Early PRN code replica input
-// \param P_code Prompt PRN code replica input
-// \param L_code Late PRN code replica input
-// \param VL_code Very Late PRN code replica input
-// \param VE_out Very Early correlation output
-// \param E_out Early correlation output
-// \param P_out Prompt correlation output
-// \param L_out Late correlation output
-// \param VL_out Very Late correlation output
-// \param num_points The number of complex values in vectors
-// */
-//static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-//{
-// lv_8sc_t bb_signal_sample;
-//
-// bb_signal_sample = lv_cmake(0, 0);
-//
-// *VE_out = 0;
-// *E_out = 0;
-// *P_out = 0;
-// *L_out = 0;
-// *VL_out = 0;
-// // perform very early, Early, Prompt, Late and very late correlation
-// for(int i=0; i < num_points; ++i)
-// {
-// //Perform the carrier wipe-off
-// bb_signal_sample = input[i] * carrier[i];
-//
-// *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code[i]);
-// *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
-// *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
-// *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
-// *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code[i]);
-// }
-//}
-//
-//#endif /* LV_HAVE_GENERIC */
-
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5_u_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h
deleted file mode 100644
index 83d861f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h
+++ /dev/null
@@ -1,768 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Very early, Early, Prompt, Late and very late correlation with 16 bits vectors, and accumulates the results into float32. This protokernel is called "safe" because it checks when the inputs have a -128 value, and replaces it with a -127 value. By doing this it avoids malfunctioning, but it lasts more time that the "unsafe" implementation. In order to avoid overflow, "input" and "carrier" must be values between —7 an [...]
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Very early, Early, Prompt, Late and very late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part), and accumulates the result
- * in 32 bits single point values, returning float32 values:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Very Early values are calculated by multiplying the input signal in BB by the
- * very early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Very Late values are calculated by multiplying the input signal in BB by the
- * very late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- *
- * -------------------------------------------------------------------------
- * Bits analysis
- *
- * input = 8 bits
- * carrier = 8 bits
- * XX_code = 8 bits
- * XX_out16 = 16 bits
- * bb_signal_sample = 8 bits
- *
- * bb_signal_sample = input*carrier -> 17 bits limited to 8 bits = input and carrier must be values between —7 and 7 to avoid overflow (3 bits)
- *
- * XX_out16 = XX_code*bb_signal_sample -> 17 bits limited to 16 bits = XX_code must be values between —127 and 127 to avoid overflow (7 bits)
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_u_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i real_output, imag_output;
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
- __m128i minus128control;
-
- __m128i minus128 = _mm_set1_epi8 (-128);
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
- __m128i mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, x, check_sign_sequence, rearrange_sequence, y_aux, x_abs, real_output, imag_output)
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- if(num_points%8!=0)
- {
- lv_16sc_t bb_signal_sample;
- lv_16sc_t VE_code_value;
- lv_16sc_t E_code_value;
- lv_16sc_t P_code_value;
- lv_16sc_t L_code_value;
- lv_16sc_t VL_code_value;
-
- for(int i=0; i < num_points%8; ++i)
- {
- VE_code_value = *VE_code_ptr++;
- E_code_value = *E_code_ptr++;
- P_code_value = *P_code_ptr++;
- L_code_value = *L_code_ptr++;
- VL_code_value = *VL_code_ptr++;
-
- if(lv_creal(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(-127, lv_cimag(VE_code_value));
- }
- if(lv_cimag(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(lv_creal(VE_code_value), -127);
- }
-
- if(lv_creal(E_code_value) == -128)
- {
- E_code_value = lv_cmake(-127, lv_cimag(E_code_value));
- }
- if(lv_cimag(E_code_value) == -128)
- {
- E_code_value = lv_cmake(lv_creal(E_code_value), -127);
- }
-
- if(lv_creal(P_code_value) == -128)
- {
- P_code_value = lv_cmake(-127, lv_cimag(P_code_value));
- }
- if(lv_cimag(P_code_value) == -128)
- {
- P_code_value = lv_cmake(lv_creal(P_code_value), -127);
- }
-
- if(lv_creal(L_code_value) == -128)
- {
- L_code_value = lv_cmake(-127, lv_cimag(L_code_value));
- }
- if(lv_cimag(L_code_value) == -128)
- {
- L_code_value = lv_cmake(lv_creal(L_code_value), -127);
- }
-
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * VE_code_value);
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * E_code_value);
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * P_code_value);
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * L_code_value);
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * VL_code_value);
- }
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
-
- lv_16sc_t VE_code_value;
- lv_16sc_t E_code_value;
- lv_16sc_t P_code_value;
- lv_16sc_t L_code_value;
- lv_16sc_t VL_code_value;
- lv_16sc_t bb_signal_sample;
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- VE_code_value = VE_code[i];
- E_code_value = E_code[i];
- P_code_value = P_code[i];
- L_code_value = L_code[i];
- VL_code_value = VL_code[i];
-
- if(lv_creal(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(-127, lv_cimag(VE_code_value));
- }
- if(lv_cimag(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(lv_creal(VE_code_value), -127);
- }
-
- if(lv_creal(E_code_value) == -128)
- {
- E_code_value = lv_cmake(-127, lv_cimag(E_code_value));
- }
- if(lv_cimag(E_code_value) == -128)
- {
- E_code_value = lv_cmake(lv_creal(E_code_value), -127);
- }
-
- if(lv_creal(P_code_value) == -128)
- {
- P_code_value = lv_cmake(-127, lv_cimag(P_code_value));
- }
- if(lv_cimag(P_code_value) == -128)
- {
- P_code_value = lv_cmake(lv_creal(P_code_value), -127);
- }
-
- if(lv_creal(L_code_value) == -128)
- {
- L_code_value = lv_cmake(-127, lv_cimag(L_code_value));
- }
- if(lv_cimag(L_code_value) == -128)
- {
- L_code_value = lv_cmake(lv_creal(L_code_value), -127);
- }
-
- if(lv_creal(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(-127, lv_cimag(VL_code_value));
- }
- if(lv_cimag(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(lv_creal(VL_code_value), -127);
- }
-
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get very early, early, prompt, late and very late values for each
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code_value);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code_value);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code_value);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code_value);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code_value);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i real_output, imag_output;
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
- __m128i minus128control;
-
- __m128i minus128 = _mm_set1_epi8 (-128);
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
- __m128i mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, x, check_sign_sequence, rearrange_sequence, y_aux, x_abs, real_output, imag_output)
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_load_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_load_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_SAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, minus128, minus128control, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_store_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- if(num_points%8!=0)
- {
- lv_16sc_t bb_signal_sample;
- lv_16sc_t VE_code_value;
- lv_16sc_t E_code_value;
- lv_16sc_t P_code_value;
- lv_16sc_t L_code_value;
- lv_16sc_t VL_code_value;
-
- for(int i=0; i < num_points%8; ++i)
- {
- VE_code_value = *VE_code_ptr++;
- E_code_value = *E_code_ptr++;
- P_code_value = *P_code_ptr++;
- L_code_value = *L_code_ptr++;
- VL_code_value = *VL_code_ptr++;
-
- if(lv_creal(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(-127, lv_cimag(VE_code_value));
- }
- if(lv_cimag(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(lv_creal(VE_code_value), -127);
- }
-
- if(lv_creal(E_code_value) == -128)
- {
- E_code_value = lv_cmake(-127, lv_cimag(E_code_value));
- }
- if(lv_cimag(E_code_value) == -128)
- {
- E_code_value = lv_cmake(lv_creal(E_code_value), -127);
- }
-
- if(lv_creal(P_code_value) == -128)
- {
- P_code_value = lv_cmake(-127, lv_cimag(P_code_value));
- }
- if(lv_cimag(P_code_value) == -128)
- {
- P_code_value = lv_cmake(lv_creal(P_code_value), -127);
- }
-
- if(lv_creal(L_code_value) == -128)
- {
- L_code_value = lv_cmake(-127, lv_cimag(L_code_value));
- }
- if(lv_cimag(L_code_value) == -128)
- {
- L_code_value = lv_cmake(lv_creal(L_code_value), -127);
- }
-
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * VE_code_value);
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * E_code_value);
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * P_code_value);
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * L_code_value);
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * VL_code_value);
- }
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
-
- lv_16sc_t VE_code_value;
- lv_16sc_t E_code_value;
- lv_16sc_t P_code_value;
- lv_16sc_t L_code_value;
- lv_16sc_t VL_code_value;
- lv_16sc_t bb_signal_sample;
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- VE_code_value = VE_code[i];
- E_code_value = E_code[i];
- P_code_value = P_code[i];
- L_code_value = L_code[i];
- VL_code_value = VL_code[i];
-
- if(lv_creal(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(-127, lv_cimag(VE_code_value));
- }
- if(lv_cimag(VE_code_value) == -128)
- {
- VE_code_value = lv_cmake(lv_creal(VE_code_value), -127);
- }
-
- if(lv_creal(E_code_value) == -128)
- {
- E_code_value = lv_cmake(-127, lv_cimag(E_code_value));
- }
- if(lv_cimag(E_code_value) == -128)
- {
- E_code_value = lv_cmake(lv_creal(E_code_value), -127);
- }
-
- if(lv_creal(P_code_value) == -128)
- {
- P_code_value = lv_cmake(-127, lv_cimag(P_code_value));
- }
- if(lv_cimag(P_code_value) == -128)
- {
- P_code_value = lv_cmake(lv_creal(P_code_value), -127);
- }
-
- if(lv_creal(L_code_value) == -128)
- {
- L_code_value = lv_cmake(-127, lv_cimag(L_code_value));
- }
- if(lv_cimag(L_code_value) == -128)
- {
- L_code_value = lv_cmake(lv_creal(L_code_value), -127);
- }
-
- if(lv_creal(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(-127, lv_cimag(VL_code_value));
- }
- if(lv_cimag(VL_code_value) == -128)
- {
- VL_code_value = lv_cmake(lv_creal(VL_code_value), -127);
- }
-
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get very early, early, prompt, late and very late values for each
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code_value);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code_value);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code_value);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code_value);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code_value);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h
deleted file mode 100644
index d370d7a..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h
+++ /dev/null
@@ -1,550 +0,0 @@
-/*!
- * \file volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5.h
- * \brief Volk protokernel: performs the carrier wipe-off mixing and the Very early, Early, Prompt, Late and very late correlation with 16 bits vectors, and accumulates the results into float32. This protokernel is called "unsafe" because it does NOT check when the inputs have a -128 value. If you introduce a -128 value the protokernel will NOT operate properly (generic implementation will have different results than volk implementation). In order to avoid overflow, "input" and "carrier" [...]
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that performs the carrier wipe-off mixing and the
- * Very early, Early, Prompt, Late and very late correlation with 16 bits vectors (8 bits the
- * real part and 8 bits the imaginary part), and accumulates the result
- * in 32 bits single point values, returning float32 values:
- * - The carrier wipe-off is done by multiplying the input signal by the
- * carrier (multiplication of 16 bits vectors) It returns the input
- * signal in base band (BB)
- * - Very Early values are calculated by multiplying the input signal in BB by the
- * very early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Early values are calculated by multiplying the input signal in BB by the
- * early code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Prompt values are calculated by multiplying the input signal in BB by the
- * prompt code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Late values are calculated by multiplying the input signal in BB by the
- * late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- * - Very Late values are calculated by multiplying the input signal in BB by the
- * very late code (multiplication of 16 bits vectors), accumulating the results into float32 values
- *
- * -------------------------------------------------------------------------
- * Bits analysis
- *
- * input = 8 bits
- * carrier = 8 bits
- * XX_code = 8 bits
- * XX_out16 = 16 bits
- * bb_signal_sample = 8 bits
- *
- * bb_signal_sample = input*carrier -> 17 bits limited to 8 bits = input and carrier must be values between —7 and 7 to avoid overflow (3 bits)
- *
- * XX_out16 = XX_code*bb_signal_sample -> 17 bits limited to 16 bits = XX_code must be values between —127 and 127 to avoid overflow (7 bits)
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_u_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_u_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_u_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i real_output, imag_output;
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
- __m128i mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_lddqu_si128((__m128i*)input_ptr);
- y = _mm_lddqu_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, x, check_sign_sequence, rearrange_sequence, y_aux, x_abs, real_output, imag_output)
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_lddqu_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_lddqu_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_lddqu_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_lddqu_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_lddqu_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_storeu_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_storeu_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
-
- lv_16sc_t bb_signal_sample;
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get very early, early, prompt, late and very late values for each
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code[i]);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code[i]);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_u_H */
-
-
-#ifndef INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_H
-#define INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_H
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <volk_gnsssdr/volk_gnsssdr_complex.h>
-#include <float.h>
-#include <string.h>
-
-#ifdef LV_HAVE_SSE4_1
-#include <smmintrin.h>
-#include "CommonMacros/CommonMacros_8ic_cw_epl_corr_32fc.h"
-#include "CommonMacros/CommonMacros.h"
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_sse4_1(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- const unsigned int sse_iters = num_points / 8;
-
- __m128i x, x_abs, y, y_aux, bb_signal_sample_aux, bb_signal_sample_aux_abs;;
- __m128i real_output, imag_output;
- __m128 real_VE_code_acc, imag_VE_code_acc, real_E_code_acc, imag_E_code_acc, real_P_code_acc, imag_P_code_acc, real_L_code_acc, imag_L_code_acc, real_VL_code_acc, imag_VL_code_acc;
- __m128i input_i_1, input_i_2, output_i32;
- __m128 real_output_ps, imag_output_ps;
-
- __m128i check_sign_sequence = _mm_set_epi8 (255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1, 255, 1);
- __m128i rearrange_sequence = _mm_set_epi8(14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1);
- __m128i mult1 = _mm_set_epi8(0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255, 0, 255);
-
- const lv_8sc_t* input_ptr = input;
- const lv_8sc_t* carrier_ptr = carrier;
-
- const lv_8sc_t* VE_code_ptr = VE_code;
- lv_32fc_t* VE_out_ptr = VE_out;
- const lv_8sc_t* E_code_ptr = E_code;
- lv_32fc_t* E_out_ptr = E_out;
- const lv_8sc_t* P_code_ptr = P_code;
- lv_32fc_t* P_out_ptr = P_out;
- const lv_8sc_t* L_code_ptr = L_code;
- lv_32fc_t* L_out_ptr = L_out;
- const lv_8sc_t* VL_code_ptr = VL_code;
- lv_32fc_t* VL_out_ptr = VL_out;
-
- float VE_out_real = 0;
- float VE_out_imag = 0;
- float E_out_real = 0;
- float E_out_imag = 0;
- float P_out_real = 0;
- float P_out_imag = 0;
- float L_out_real = 0;
- float L_out_imag = 0;
- float VL_out_real = 0;
- float VL_out_imag = 0;
-
- real_VE_code_acc = _mm_setzero_ps();
- imag_VE_code_acc = _mm_setzero_ps();
- real_E_code_acc = _mm_setzero_ps();
- imag_E_code_acc = _mm_setzero_ps();
- real_P_code_acc = _mm_setzero_ps();
- imag_P_code_acc = _mm_setzero_ps();
- real_L_code_acc = _mm_setzero_ps();
- imag_L_code_acc = _mm_setzero_ps();
- real_VL_code_acc = _mm_setzero_ps();
- imag_VL_code_acc = _mm_setzero_ps();
-
- if (sse_iters>0)
- {
- for(int number = 0;number < sse_iters; number++)
- {
- //Perform the carrier wipe-off
- x = _mm_load_si128((__m128i*)input_ptr);
- y = _mm_load_si128((__m128i*)carrier_ptr);
-
- x_abs = _mm_abs_epi8 (x);
-
- CM_8IC_X2_SCALAR_PRODUCT_16IC_X2_U_SSSE3(y, x, check_sign_sequence, rearrange_sequence, y_aux, x_abs, real_output, imag_output)
-
- imag_output = _mm_slli_si128 (imag_output, 1);
- bb_signal_sample_aux = _mm_blendv_epi8 (imag_output, real_output, mult1);
- bb_signal_sample_aux_abs = _mm_abs_epi8 (bb_signal_sample_aux);
-
- //Get very early values
- y = _mm_load_si128((__m128i*)VE_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VE_code_acc = _mm_add_ps (real_VE_code_acc, real_output_ps);
- imag_VE_code_acc = _mm_add_ps (imag_VE_code_acc, imag_output_ps);
-
- //Get early values
- y = _mm_load_si128((__m128i*)E_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_E_code_acc = _mm_add_ps (real_E_code_acc, real_output_ps);
- imag_E_code_acc = _mm_add_ps (imag_E_code_acc, imag_output_ps);
-
- //Get prompt values
- y = _mm_load_si128((__m128i*)P_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_P_code_acc = _mm_add_ps (real_P_code_acc, real_output_ps);
- imag_P_code_acc = _mm_add_ps (imag_P_code_acc, imag_output_ps);
-
- //Get late values
- y = _mm_load_si128((__m128i*)L_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_L_code_acc = _mm_add_ps (real_L_code_acc, real_output_ps);
- imag_L_code_acc = _mm_add_ps (imag_L_code_acc, imag_output_ps);
-
- //Get very late values
- y = _mm_load_si128((__m128i*)VL_code_ptr);
-
- CM_8IC_X2_CW_CORR_UNSAFE_32FC_X2_U_SSE4_1(y, bb_signal_sample_aux, check_sign_sequence, rearrange_sequence, y_aux, bb_signal_sample_aux_abs, real_output, imag_output, input_i_1, input_i_2, output_i32, real_output_ps, imag_output_ps)
-
- real_VL_code_acc = _mm_add_ps (real_VL_code_acc, real_output_ps);
- imag_VL_code_acc = _mm_add_ps (imag_VL_code_acc, imag_output_ps);
-
- input_ptr += 8;
- carrier_ptr += 8;
- VE_code_ptr += 8;
- E_code_ptr += 8;
- P_code_ptr += 8;
- L_code_ptr += 8;
- VL_code_ptr += 8;
- }
-
- __VOLK_ATTR_ALIGNED(16) float real_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VE_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_E_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_P_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_L_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float real_VL_dotProductVector[4];
- __VOLK_ATTR_ALIGNED(16) float imag_VL_dotProductVector[4];
-
- _mm_store_ps((float*)real_VE_dotProductVector,real_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VE_dotProductVector,imag_VE_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_E_dotProductVector,real_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_E_dotProductVector,imag_E_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_P_dotProductVector,real_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_P_dotProductVector,imag_P_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_L_dotProductVector,real_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_L_dotProductVector,imag_L_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)real_VL_dotProductVector,real_VL_code_acc); // Store the results back into the dot product vector
- _mm_store_ps((float*)imag_VL_dotProductVector,imag_VL_code_acc); // Store the results back into the dot product vector
-
- for (int i = 0; i<4; ++i)
- {
- VE_out_real += real_VE_dotProductVector[i];
- VE_out_imag += imag_VE_dotProductVector[i];
- E_out_real += real_E_dotProductVector[i];
- E_out_imag += imag_E_dotProductVector[i];
- P_out_real += real_P_dotProductVector[i];
- P_out_imag += imag_P_dotProductVector[i];
- L_out_real += real_L_dotProductVector[i];
- L_out_imag += imag_L_dotProductVector[i];
- VL_out_real += real_VL_dotProductVector[i];
- VL_out_imag += imag_VL_dotProductVector[i];
- }
- *VE_out_ptr = lv_cmake(VE_out_real, VE_out_imag);
- *E_out_ptr = lv_cmake(E_out_real, E_out_imag);
- *P_out_ptr = lv_cmake(P_out_real, P_out_imag);
- *L_out_ptr = lv_cmake(L_out_real, L_out_imag);
- *VL_out_ptr = lv_cmake(VL_out_real, VL_out_imag);
- }
-
- lv_16sc_t bb_signal_sample;
- for(int i=0; i < num_points%8; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = (*input_ptr++) * (*carrier_ptr++);
- // Now get very early, early, prompt, late and very late values for each
- *VE_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VE_code_ptr++));
- *E_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*E_code_ptr++));
- *P_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*P_code_ptr++));
- *L_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*L_code_ptr++));
- *VL_out_ptr += (lv_32fc_t) (bb_signal_sample * ((lv_16sc_t)*VL_code_ptr++));
- }
-}
-#endif /* LV_HAVE_SSE4_1 */
-
-#ifdef LV_HAVE_GENERIC
-
-/*!
- \brief Performs the carrier wipe-off mixing and the Early, Prompt, and Late correlation
- \param input The input signal input
- \param carrier The carrier signal input
- \param VE_code Very Early PRN code replica input
- \param E_code Early PRN code replica input
- \param P_code Prompt PRN code replica input
- \param L_code Late PRN code replica input
- \param VL_code Very Late PRN code replica input
- \param VE_out Very Early correlation output
- \param E_out Early correlation output
- \param P_out Prompt correlation output
- \param L_out Late correlation output
- \param VL_out Very Late correlation output
- \param num_points The number of complex values in vectors
- */
-static inline void volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_generic(lv_32fc_t* VE_out, lv_32fc_t* E_out, lv_32fc_t* P_out, lv_32fc_t* L_out, lv_32fc_t* VL_out, const lv_8sc_t* input, const lv_8sc_t* carrier, const lv_8sc_t* VE_code, const lv_8sc_t* E_code, const lv_8sc_t* P_code, const lv_8sc_t* L_code, const lv_8sc_t* VL_code, unsigned int num_points)
-{
- *VE_out = 0;
- *E_out = 0;
- *P_out = 0;
- *L_out = 0;
- *VL_out = 0;
-
- lv_16sc_t bb_signal_sample;
-
- for(unsigned int i=0; i < num_points; ++i)
- {
- //Perform the carrier wipe-off
- bb_signal_sample = input[i] * carrier[i];
- // Now get very early, early, prompt, late and very late values for each
- *VE_out += (lv_32fc_t) (bb_signal_sample * VE_code[i]);
- *E_out += (lv_32fc_t) (bb_signal_sample * E_code[i]);
- *P_out += (lv_32fc_t) (bb_signal_sample * P_code[i]);
- *L_out += (lv_32fc_t) (bb_signal_sample * L_code[i]);
- *VL_out += (lv_32fc_t) (bb_signal_sample * VL_code[i]);
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_gnsssdr_volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5_a_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_s32f_x2_update_local_carrier_32fc.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_s32f_x2_update_local_carrier_32fc.h
deleted file mode 100644
index 66e741f..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/kernels/volk_gnsssdr/volk_gnsssdr_s32f_x2_update_local_carrier_32fc.h
+++ /dev/null
@@ -1,865 +0,0 @@
-/*!
- * \file volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc
- * \brief Volk protokernel: replaces the tracking function for update_local_carrier. Algorithm by Julien Pommier and Giovanni Garberoglio, modified by Andres Cecilia.
- * \authors <ul>
- * <li> Andres Cecilia, 2014. a.cecilia.luque(at)gmail.com
- * </ul>
- *
- * Volk protokernel that replaces the tracking function for update_local_carrier. Algorithm by Julien Pommier and Giovanni Garberoglio, modified by Andres Cecilia.
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2007 Julien Pommier
- *
- * This software is provided 'as-is', without any express or implied
- * warranty. In no event will the authors be held liable for any damages
- * arising from the use of this software.
- *
- * Permission is granted to anyone to use this software for any purpose,
- * including commercial applications, and to alter it and redistribute it
- * freely, subject to the following restrictions:
- *
- * 1. The origin of this software must not be misrepresented; you must not
- * claim that you wrote the original software. If you use this software
- * in a product, an acknowledgment in the product documentation would be
- * appreciated but is not required.
- * 2. Altered source versions must be plainly marked as such, and must not be
- * misrepresented as being the original software.
- * 3. This notice may not be removed or altered from any source distribution.
- *
- * (this is the zlib license)
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2012 Giovanni Garberoglio
- * Interdisciplinary Laboratory for Computational Science (LISC)
- * Fondazione Bruno Kessler and University of Trento
- * via Sommarive, 18
- * I-38123 Trento (Italy)
- *
- * -------------------------------------------------------------------------
- *
- * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * GNSS-SDR is a software defined Global Navigation
- * Satellite Systems receiver
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- *
- * -------------------------------------------------------------------------
- */
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_u_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_u_H
-
-#include <volk_gnsssdr/volk_gnsssdr_common.h>
-#include <inttypes.h>
-#include <stdio.h>
-
-#ifdef LV_HAVE_AVX
-#include <immintrin.h>
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_u_avx(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- const unsigned int sse_iters = num_points / 8;
-
- __m256 _ps256_minus_cephes_DP1 = _mm256_set1_ps(-0.78515625f);
- __m256 _ps256_minus_cephes_DP2 = _mm256_set1_ps(-2.4187564849853515625e-4f);
- __m256 _ps256_minus_cephes_DP3 = _mm256_set1_ps(-3.77489497744594108e-8f);
- __m256 _ps256_sign_mask = _mm256_set1_ps(-0.f);
- __m128i _pi32avx_1 = _mm_set1_epi32(1);
- __m128i _pi32avx_inv1 = _mm_set1_epi32(~1);
- __m128i _pi32avx_2 = _mm_set1_epi32(2);
- __m128i _pi32avx_4 = _mm_set1_epi32(4);
- __m256 _ps256_cephes_FOPI = _mm256_set1_ps(1.27323954473516f); // 4 / PI
- __m256 _ps256_sincof_p0 = _mm256_set1_ps(-1.9515295891E-4f);
- __m256 _ps256_sincof_p1 = _mm256_set1_ps( 8.3321608736E-3f);
- __m256 _ps256_sincof_p2 = _mm256_set1_ps(-1.6666654611E-1f);
- __m256 _ps256_coscof_p0 = _mm256_set1_ps( 2.443315711809948E-005f);
- __m256 _ps256_coscof_p1 = _mm256_set1_ps(-1.388731625493765E-003f);
- __m256 _ps256_coscof_p2 = _mm256_set1_ps( 4.166664568298827E-002f);
- __m256 _ps256_1 = _mm256_set1_ps(1.f);
- __m256 _ps256_0p5 = _mm256_set1_ps(0.5f);
-
- __m256 phase_step_rad_array = _mm256_set1_ps(8*phase_step_rad);
-
- __m256 phase_rad_array, x, s, c, swap_sign_bit_sin, sign_bit_cos, poly_mask, z, tmp, y, y2, ysin1, ysin2;
- __m256 xmm1, xmm2, xmm3, sign_bit_sin;
- __m256i imm0, imm2, imm4, tmp256i;
- __m128i imm0_1, imm0_2, imm2_1, imm2_2, imm4_1, imm4_2;
- __VOLK_ATTR_ALIGNED(32) float sin_value[8];
- __VOLK_ATTR_ALIGNED(32) float cos_value[8];
-
- phase_rad_array = _mm256_set_ps (phase_rad_init+7*phase_step_rad, phase_rad_init+6*phase_step_rad, phase_rad_init+5*phase_step_rad, phase_rad_init+4*phase_step_rad, phase_rad_init+3*phase_step_rad, phase_rad_init+2*phase_step_rad, phase_rad_init+phase_step_rad, phase_rad_init);
-
- for(int i = 0; i < sse_iters; i++)
- {
- x = phase_rad_array;
-
- /* extract the sign bit (upper one) */
- sign_bit_sin = _mm256_and_ps(x, _ps256_sign_mask);
-
- /* take the absolute value */
- x = _mm256_xor_ps(x, sign_bit_sin);
-
- /* scale by 4/Pi */
- y = _mm256_mul_ps(x, _ps256_cephes_FOPI);
-
- /* we use SSE2 routines to perform the integer ops */
-
- //COPY_IMM_TO_XMM(_mm256_cvttps_epi32(y),imm2_1,imm2_2);
- tmp256i = _mm256_cvttps_epi32(y);
- imm2_1 = _mm256_extractf128_si256 (tmp256i, 0);
- imm2_2 = _mm256_extractf128_si256 (tmp256i, 1);
-
- imm2_1 = _mm_add_epi32(imm2_1, _pi32avx_1);
- imm2_2 = _mm_add_epi32(imm2_2, _pi32avx_1);
-
- imm2_1 = _mm_and_si128(imm2_1, _pi32avx_inv1);
- imm2_2 = _mm_and_si128(imm2_2, _pi32avx_inv1);
-
- //COPY_XMM_TO_IMM(imm2_1,imm2_2,imm2);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm2 = _mm256_set_m128i (imm2_2, imm2_1);
- imm2 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm2_1),(imm2_2),1);
-
- y = _mm256_cvtepi32_ps(imm2);
-
- imm4_1 = imm2_1;
- imm4_2 = imm2_2;
-
- imm0_1 = _mm_and_si128(imm2_1, _pi32avx_4);
- imm0_2 = _mm_and_si128(imm2_2, _pi32avx_4);
-
- imm0_1 = _mm_slli_epi32(imm0_1, 29);
- imm0_2 = _mm_slli_epi32(imm0_2, 29);
-
- //COPY_XMM_TO_IMM(imm0_1, imm0_2, imm0);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm0 = _mm256_set_m128i (imm0_2, imm0_1);
- imm0 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm0_1),(imm0_2),1);
-
- imm2_1 = _mm_and_si128(imm2_1, _pi32avx_2);
- imm2_2 = _mm_and_si128(imm2_2, _pi32avx_2);
-
- imm2_1 = _mm_cmpeq_epi32(imm2_1, _mm_setzero_si128());
- imm2_2 = _mm_cmpeq_epi32(imm2_2, _mm_setzero_si128());
-
- //COPY_XMM_TO_IMM(imm2_1, imm2_2, imm2);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm2 = _mm256_set_m128i (imm2_2, imm2_1);
- imm2 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm2_1),(imm2_2),1);
-
- swap_sign_bit_sin = _mm256_castsi256_ps(imm0);
- poly_mask = _mm256_castsi256_ps(imm2);
-
- /* The magic pass: "Extended precision modular arithmetic"
- x = ((x - y * DP1) - y * DP2) - y * DP3; */
- xmm1 = _ps256_minus_cephes_DP1;
- xmm2 = _ps256_minus_cephes_DP2;
- xmm3 = _ps256_minus_cephes_DP3;
- xmm1 = _mm256_mul_ps(y, xmm1);
- xmm2 = _mm256_mul_ps(y, xmm2);
- xmm3 = _mm256_mul_ps(y, xmm3);
- x = _mm256_add_ps(x, xmm1);
- x = _mm256_add_ps(x, xmm2);
- x = _mm256_add_ps(x, xmm3);
-
- imm4_1 = _mm_sub_epi32(imm4_1, _pi32avx_2);
- imm4_2 = _mm_sub_epi32(imm4_2, _pi32avx_2);
-
- imm4_1 = _mm_andnot_si128(imm4_1, _pi32avx_4);
- imm4_2 = _mm_andnot_si128(imm4_2, _pi32avx_4);
-
- imm4_1 = _mm_slli_epi32(imm4_1, 29);
- imm4_2 = _mm_slli_epi32(imm4_2, 29);
-
- //COPY_XMM_TO_IMM(imm4_1, imm4_2, imm4);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm4 = _mm256_set_m128i (imm4_2, imm4_1);
- imm4 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm4_1),(imm4_2),1);
-
- sign_bit_cos = _mm256_castsi256_ps(imm4);
-
- sign_bit_sin = _mm256_xor_ps(sign_bit_sin, swap_sign_bit_sin);
-
- /* Evaluate the first polynom (0 <= x <= Pi/4) */
- z = _mm256_mul_ps(x,x);
- y = _ps256_coscof_p0;
-
- y = _mm256_mul_ps(y, z);
- y = _mm256_add_ps(y, _ps256_coscof_p1);
- y = _mm256_mul_ps(y, z);
- y = _mm256_add_ps(y, _ps256_coscof_p2);
- y = _mm256_mul_ps(y, z);
- y = _mm256_mul_ps(y, z);
- tmp = _mm256_mul_ps(z, _ps256_0p5);
- y = _mm256_sub_ps(y, tmp);
- y = _mm256_add_ps(y, _ps256_1);
-
- /* Evaluate the second polynom (Pi/4 <= x <= 0) */
-
- y2 = _ps256_sincof_p0;
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_add_ps(y2, _ps256_sincof_p1);
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_add_ps(y2, _ps256_sincof_p2);
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_mul_ps(y2, x);
- y2 = _mm256_add_ps(y2, x);
-
- /* select the correct result from the two polynoms */
- xmm3 = poly_mask;
- ysin2 = _mm256_and_ps(xmm3, y2);
- ysin1 = _mm256_andnot_ps(xmm3, y);
- y2 = _mm256_sub_ps(y2,ysin2);
- y = _mm256_sub_ps(y, ysin1);
-
- xmm1 = _mm256_add_ps(ysin1,ysin2);
- xmm2 = _mm256_add_ps(y,y2);
-
- /* update the sign */
- s = _mm256_xor_ps(xmm1, sign_bit_sin);
- c = _mm256_xor_ps(xmm2, sign_bit_cos);
-
- //GNSS-SDR needs to return -sin
- s = _mm256_xor_ps(s, _ps256_sign_mask);
-
- _mm256_storeu_ps ((float*)sin_value, s);
- _mm256_storeu_ps ((float*)cos_value, c);
-
- for(int i = 0; i < 8; i++)
- {
- d_carr_sign[i] = lv_cmake(cos_value[i], sin_value[i]);
- }
- d_carr_sign += 8;
-
- phase_rad_array = _mm256_add_ps (phase_rad_array, phase_step_rad_array);
- }
-
- if (num_points%8!=0)
- {
- __VOLK_ATTR_ALIGNED(32) float phase_rad_store[8];
- _mm256_storeu_ps ((float*)phase_rad_store, phase_rad_array);
-
- float phase_rad = phase_rad_store[0];
-
- for(int i = 0; i < num_points%8; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
- }
-}
-#endif /* LV_HAVE_AVX */
-
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_u_sse2(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- const unsigned int sse_iters = num_points / 4;
-
- __m128 _ps_minus_cephes_DP1 = _mm_set1_ps(-0.78515625f);
- __m128 _ps_minus_cephes_DP2 = _mm_set1_ps(-2.4187564849853515625e-4f);
- __m128 _ps_minus_cephes_DP3 = _mm_set1_ps(-3.77489497744594108e-8f);
- __m128 _ps_sign_mask = _mm_set1_ps(-0.f);
- __m128i _pi32_1 = _mm_set1_epi32(1);
- __m128i _pi32_inv1 = _mm_set1_epi32(~1);
- __m128i _pi32_2 = _mm_set1_epi32(2);
- __m128i _pi32_4 = _mm_set1_epi32(4);
- __m128 _ps_cephes_FOPI = _mm_set1_ps(1.27323954473516f); // 4 / PI
- __m128 _ps_sincof_p0 = _mm_set1_ps(-1.9515295891E-4f);
- __m128 _ps_sincof_p1 = _mm_set1_ps( 8.3321608736E-3f);
- __m128 _ps_sincof_p2 = _mm_set1_ps(-1.6666654611E-1f);
- __m128 _ps_coscof_p0 = _mm_set1_ps( 2.443315711809948E-005f);
- __m128 _ps_coscof_p1 = _mm_set1_ps(-1.388731625493765E-003f);
- __m128 _ps_coscof_p2 = _mm_set1_ps( 4.166664568298827E-002f);
- __m128 _ps_1 = _mm_set1_ps(1.f);
- __m128 _ps_0p5 = _mm_set1_ps(0.5f);
-
- __m128 phase_step_rad_array = _mm_set1_ps(4*phase_step_rad);
-
- __m128 phase_rad_array, x, s, c, swap_sign_bit_sin, sign_bit_cos, poly_mask, z, tmp, y, y2, ysin1, ysin2;
- __m128 xmm1, xmm2, xmm3, sign_bit_sin;
- __m128i emm0, emm2, emm4;
- __VOLK_ATTR_ALIGNED(16) float sin_value[4];
- __VOLK_ATTR_ALIGNED(16) float cos_value[4];
-
- phase_rad_array = _mm_set_ps (phase_rad_init+3*phase_step_rad, phase_rad_init+2*phase_step_rad, phase_rad_init+phase_step_rad, phase_rad_init);
-
- for(unsigned int i = 0; i < sse_iters; i++)
- {
- x = phase_rad_array;
-
- /* extract the sign bit (upper one) */
- sign_bit_sin = _mm_and_ps(x, _ps_sign_mask);
-
- /* take the absolute value */
- x = _mm_xor_ps(x, sign_bit_sin);
-
- /* scale by 4/Pi */
- y = _mm_mul_ps(x, _ps_cephes_FOPI);
-
- /* store the integer part of y in emm2 */
- emm2 = _mm_cvttps_epi32(y);
-
- /* j=(j+1) & (~1) (see the cephes sources) */
- emm2 = _mm_add_epi32(emm2, _pi32_1);
- emm2 = _mm_and_si128(emm2, _pi32_inv1);
- y = _mm_cvtepi32_ps(emm2);
-
- emm4 = emm2;
-
- /* get the swap sign flag for the sine */
- emm0 = _mm_and_si128(emm2, _pi32_4);
- emm0 = _mm_slli_epi32(emm0, 29);
- swap_sign_bit_sin = _mm_castsi128_ps(emm0);
-
- /* get the polynom selection mask for the sine*/
- emm2 = _mm_and_si128(emm2, _pi32_2);
- emm2 = _mm_cmpeq_epi32(emm2, _mm_setzero_si128());
- poly_mask = _mm_castsi128_ps(emm2);
-
- /* The magic pass: "Extended precision modular arithmetic"
- x = ((x - y * DP1) - y * DP2) - y * DP3; */
- xmm1 = _mm_mul_ps(y, _ps_minus_cephes_DP1);
- xmm2 = _mm_mul_ps(y, _ps_minus_cephes_DP2);
- xmm3 = _mm_mul_ps(y, _ps_minus_cephes_DP3);
- x = _mm_add_ps(_mm_add_ps(x, xmm1), _mm_add_ps(xmm2, xmm3));
-
- emm4 = _mm_sub_epi32(emm4, _pi32_2);
- emm4 = _mm_andnot_si128(emm4, _pi32_4);
- emm4 = _mm_slli_epi32(emm4, 29);
- sign_bit_cos = _mm_castsi128_ps(emm4);
-
- sign_bit_sin = _mm_xor_ps(sign_bit_sin, swap_sign_bit_sin);
-
- /* Evaluate the first polynom (0 <= x <= Pi/4) */
- z = _mm_mul_ps(x,x);
- y = _ps_coscof_p0;
- y = _mm_mul_ps(y, z);
- y = _mm_add_ps(y, _ps_coscof_p1);
- y = _mm_mul_ps(y, z);
- y = _mm_add_ps(y, _ps_coscof_p2);
- y = _mm_mul_ps(y, _mm_mul_ps(z, z));
- tmp = _mm_mul_ps(z, _ps_0p5);
- y = _mm_sub_ps(y, tmp);
- y = _mm_add_ps(y, _ps_1);
-
- /* Evaluate the second polynom (Pi/4 <= x <= 0) */
- y2 = _ps_sincof_p0;
- y2 = _mm_mul_ps(y2, z);
- y2 = _mm_add_ps(y2, _ps_sincof_p1);
- y2 = _mm_mul_ps(y2, z);
- y2 = _mm_add_ps(y2, _ps_sincof_p2);
- y2 = _mm_mul_ps(y2, _mm_mul_ps(z, x));
- y2 = _mm_add_ps(y2, x);
-
- /* select the correct result from the two polynoms */
- xmm3 = poly_mask;
- ysin2 = _mm_and_ps(xmm3, y2);
- ysin1 = _mm_andnot_ps(xmm3, y);
- y2 = _mm_sub_ps(y2,ysin2);
- y = _mm_sub_ps(y, ysin1);
-
- xmm1 = _mm_add_ps(ysin1,ysin2);
- xmm2 = _mm_add_ps(y,y2);
-
- /* update the sign */
- s = _mm_xor_ps(xmm1, sign_bit_sin);
- c = _mm_xor_ps(xmm2, sign_bit_cos);
-
- //GNSS-SDR needs to return -sin
- s = _mm_xor_ps(s, _ps_sign_mask);
-
- _mm_storeu_ps ((float*)sin_value, s);
- _mm_storeu_ps ((float*)cos_value, c);
-
- for(unsigned int e = 0; e < 4; e++)
- {
- d_carr_sign[e] = lv_cmake(cos_value[e], sin_value[e]);
- }
- d_carr_sign += 4;
-
- phase_rad_array = _mm_add_ps (phase_rad_array, phase_step_rad_array);
- }
-
- if (num_points%4!=0)
- {
- __VOLK_ATTR_ALIGNED(16) float phase_rad_store[4];
- _mm_storeu_ps ((float*)phase_rad_store, phase_rad_array);
-
- float phase_rad = phase_rad_store[0];
-
- for(unsigned int i = 0; i < num_points%4; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_generic(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- float phase_rad = phase_rad_init;
- for(unsigned int i = 0; i < num_points; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_u_H */
-
-
-#ifndef INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_a_H
-#define INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_a_H
-
-#include <volk_gnsssdr/volk_gnsssdr_common.h>
-#include <inttypes.h>
-#include <stdio.h>
-
-#ifdef LV_HAVE_AVX
-#include <immintrin.h>
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_a_avx(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- const unsigned int sse_iters = num_points / 8;
-
- __m256 _ps256_minus_cephes_DP1 = _mm256_set1_ps(-0.78515625f);
- __m256 _ps256_minus_cephes_DP2 = _mm256_set1_ps(-2.4187564849853515625e-4f);
- __m256 _ps256_minus_cephes_DP3 = _mm256_set1_ps(-3.77489497744594108e-8f);
- __m256 _ps256_sign_mask = _mm256_set1_ps(-0.f);
- __m128i _pi32avx_1 = _mm_set1_epi32(1);
- __m128i _pi32avx_inv1 = _mm_set1_epi32(~1);
- __m128i _pi32avx_2 = _mm_set1_epi32(2);
- __m128i _pi32avx_4 = _mm_set1_epi32(4);
- __m256 _ps256_cephes_FOPI = _mm256_set1_ps(1.27323954473516f); // 4 / PI
- __m256 _ps256_sincof_p0 = _mm256_set1_ps(-1.9515295891E-4f);
- __m256 _ps256_sincof_p1 = _mm256_set1_ps( 8.3321608736E-3f);
- __m256 _ps256_sincof_p2 = _mm256_set1_ps(-1.6666654611E-1f);
- __m256 _ps256_coscof_p0 = _mm256_set1_ps( 2.443315711809948E-005f);
- __m256 _ps256_coscof_p1 = _mm256_set1_ps(-1.388731625493765E-003f);
- __m256 _ps256_coscof_p2 = _mm256_set1_ps( 4.166664568298827E-002f);
- __m256 _ps256_1 = _mm256_set1_ps(1.f);
- __m256 _ps256_0p5 = _mm256_set1_ps(0.5f);
-
- __m256 phase_step_rad_array = _mm256_set1_ps(8*phase_step_rad);
-
- __m256 phase_rad_array, x, s, c, swap_sign_bit_sin, sign_bit_cos, poly_mask, z, tmp, y, y2, ysin1, ysin2;
- __m256 xmm1, xmm2, xmm3, sign_bit_sin;
- __m256i imm0, imm2, imm4, tmp256i;
- __m128i imm0_1, imm0_2, imm2_1, imm2_2, imm4_1, imm4_2;
- __VOLK_ATTR_ALIGNED(32) float sin_value[8];
- __VOLK_ATTR_ALIGNED(32) float cos_value[8];
-
- phase_rad_array = _mm256_set_ps (phase_rad_init + 7*phase_step_rad, phase_rad_init + 6*phase_step_rad, phase_rad_init + 5*phase_step_rad, phase_rad_init + 4*phase_step_rad, phase_rad_init + 3*phase_step_rad, phase_rad_init + 2*phase_step_rad, phase_rad_init + phase_step_rad, phase_rad_init);
-
- for(int i = 0; i < sse_iters; i++)
- {
-
- x = phase_rad_array;
-
- /* extract the sign bit (upper one) */
- sign_bit_sin = _mm256_and_ps(x, _ps256_sign_mask);
-
- /* take the absolute value */
- x = _mm256_xor_ps(x, sign_bit_sin);
-
- /* scale by 4/Pi */
- y = _mm256_mul_ps(x, _ps256_cephes_FOPI);
-
- /* we use SSE2 routines to perform the integer ops */
-
- //COPY_IMM_TO_XMM(_mm256_cvttps_epi32(y),imm2_1,imm2_2);
- tmp256i = _mm256_cvttps_epi32(y);
- imm2_1 = _mm256_extractf128_si256 (tmp256i, 0);
- imm2_2 = _mm256_extractf128_si256 (tmp256i, 1);
-
- imm2_1 = _mm_add_epi32(imm2_1, _pi32avx_1);
- imm2_2 = _mm_add_epi32(imm2_2, _pi32avx_1);
-
- imm2_1 = _mm_and_si128(imm2_1, _pi32avx_inv1);
- imm2_2 = _mm_and_si128(imm2_2, _pi32avx_inv1);
-
- //COPY_XMM_TO_IMM(imm2_1,imm2_2,imm2);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm2 = _mm256_set_m128i (imm2_2, imm2_1);
- imm2 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm2_1),(imm2_2),1);
-
- y = _mm256_cvtepi32_ps(imm2);
-
- imm4_1 = imm2_1;
- imm4_2 = imm2_2;
-
- imm0_1 = _mm_and_si128(imm2_1, _pi32avx_4);
- imm0_2 = _mm_and_si128(imm2_2, _pi32avx_4);
-
- imm0_1 = _mm_slli_epi32(imm0_1, 29);
- imm0_2 = _mm_slli_epi32(imm0_2, 29);
-
- //COPY_XMM_TO_IMM(imm0_1, imm0_2, imm0);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm0 = _mm256_set_m128i (imm0_2, imm0_1);
- imm0 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm0_1),(imm0_2),1);
-
- imm2_1 = _mm_and_si128(imm2_1, _pi32avx_2);
- imm2_2 = _mm_and_si128(imm2_2, _pi32avx_2);
-
- imm2_1 = _mm_cmpeq_epi32(imm2_1, _mm_setzero_si128());
- imm2_2 = _mm_cmpeq_epi32(imm2_2, _mm_setzero_si128());
-
- //COPY_XMM_TO_IMM(imm2_1, imm2_2, imm2);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm2 = _mm256_set_m128i (imm2_2, imm2_1);
- imm2 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm2_1),(imm2_2),1);
-
- swap_sign_bit_sin = _mm256_castsi256_ps(imm0);
- poly_mask = _mm256_castsi256_ps(imm2);
-
- /* The magic pass: "Extended precision modular arithmetic"
- x = ((x - y * DP1) - y * DP2) - y * DP3; */
- xmm1 = _ps256_minus_cephes_DP1;
- xmm2 = _ps256_minus_cephes_DP2;
- xmm3 = _ps256_minus_cephes_DP3;
- xmm1 = _mm256_mul_ps(y, xmm1);
- xmm2 = _mm256_mul_ps(y, xmm2);
- xmm3 = _mm256_mul_ps(y, xmm3);
- x = _mm256_add_ps(x, xmm1);
- x = _mm256_add_ps(x, xmm2);
- x = _mm256_add_ps(x, xmm3);
-
- imm4_1 = _mm_sub_epi32(imm4_1, _pi32avx_2);
- imm4_2 = _mm_sub_epi32(imm4_2, _pi32avx_2);
-
- imm4_1 = _mm_andnot_si128(imm4_1, _pi32avx_4);
- imm4_2 = _mm_andnot_si128(imm4_2, _pi32avx_4);
-
- imm4_1 = _mm_slli_epi32(imm4_1, 29);
- imm4_2 = _mm_slli_epi32(imm4_2, 29);
-
- //COPY_XMM_TO_IMM(imm4_1, imm4_2, imm4);
- //_mm256_set_m128i not defined in some versions of immintrin.h
- //imm4 = _mm256_set_m128i (imm4_2, imm4_1);
- imm4 = _mm256_insertf128_si256(_mm256_castsi128_si256(imm4_1),(imm4_2),1);
-
- sign_bit_cos = _mm256_castsi256_ps(imm4);
-
- sign_bit_sin = _mm256_xor_ps(sign_bit_sin, swap_sign_bit_sin);
-
- /* Evaluate the first polynom (0 <= x <= Pi/4) */
- z = _mm256_mul_ps(x,x);
- y = _ps256_coscof_p0;
-
- y = _mm256_mul_ps(y, z);
- y = _mm256_add_ps(y, _ps256_coscof_p1);
- y = _mm256_mul_ps(y, z);
- y = _mm256_add_ps(y, _ps256_coscof_p2);
- y = _mm256_mul_ps(y, z);
- y = _mm256_mul_ps(y, z);
- tmp = _mm256_mul_ps(z, _ps256_0p5);
- y = _mm256_sub_ps(y, tmp);
- y = _mm256_add_ps(y, _ps256_1);
-
- /* Evaluate the second polynom (Pi/4 <= x <= 0) */
-
- y2 = _ps256_sincof_p0;
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_add_ps(y2, _ps256_sincof_p1);
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_add_ps(y2, _ps256_sincof_p2);
- y2 = _mm256_mul_ps(y2, z);
- y2 = _mm256_mul_ps(y2, x);
- y2 = _mm256_add_ps(y2, x);
-
- /* select the correct result from the two polynoms */
- xmm3 = poly_mask;
- ysin2 = _mm256_and_ps(xmm3, y2);
- ysin1 = _mm256_andnot_ps(xmm3, y);
- y2 = _mm256_sub_ps(y2,ysin2);
- y = _mm256_sub_ps(y, ysin1);
-
- xmm1 = _mm256_add_ps(ysin1,ysin2);
- xmm2 = _mm256_add_ps(y,y2);
-
- /* update the sign */
- s = _mm256_xor_ps(xmm1, sign_bit_sin);
- c = _mm256_xor_ps(xmm2, sign_bit_cos);
-
- //GNSS-SDR needs to return -sin
- s = _mm256_xor_ps(s, _ps256_sign_mask);
-
- _mm256_store_ps ((float*)sin_value, s);
- _mm256_store_ps ((float*)cos_value, c);
-
- for(int i = 0; i < 8; i++)
- {
- d_carr_sign[i] = lv_cmake(cos_value[i], sin_value[i]);
- }
- d_carr_sign += 8;
-
- phase_rad_array = _mm256_add_ps (phase_rad_array, phase_step_rad_array);
- }
-
- if (num_points%8!=0)
- {
- __VOLK_ATTR_ALIGNED(32) float phase_rad_store[8];
- _mm256_store_ps ((float*)phase_rad_store, phase_rad_array);
-
- float phase_rad = phase_rad_store[0];
-
- for(int i = 0; i < num_points%8; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
- }
-}
-#endif /* LV_HAVE_AVX */
-
-#ifdef LV_HAVE_SSE2
-#include <emmintrin.h>
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_a_sse2(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- const unsigned int sse_iters = num_points / 4;
-
- __m128 _ps_minus_cephes_DP1 = _mm_set1_ps(-0.78515625f);
- __m128 _ps_minus_cephes_DP2 = _mm_set1_ps(-2.4187564849853515625e-4f);
- __m128 _ps_minus_cephes_DP3 = _mm_set1_ps(-3.77489497744594108e-8f);
- __m128 _ps_sign_mask = _mm_set1_ps(-0.f);
- __m128i _pi32_1 = _mm_set1_epi32(1);
- __m128i _pi32_inv1 = _mm_set1_epi32(~1);
- __m128i _pi32_2 = _mm_set1_epi32(2);
- __m128i _pi32_4 = _mm_set1_epi32(4);
- __m128 _ps_cephes_FOPI = _mm_set1_ps(1.27323954473516f); // 4 / PI
- __m128 _ps_sincof_p0 = _mm_set1_ps(-1.9515295891E-4f);
- __m128 _ps_sincof_p1 = _mm_set1_ps( 8.3321608736E-3f);
- __m128 _ps_sincof_p2 = _mm_set1_ps(-1.6666654611E-1f);
- __m128 _ps_coscof_p0 = _mm_set1_ps( 2.443315711809948E-005f);
- __m128 _ps_coscof_p1 = _mm_set1_ps(-1.388731625493765E-003f);
- __m128 _ps_coscof_p2 = _mm_set1_ps( 4.166664568298827E-002f);
- __m128 _ps_1 = _mm_set1_ps(1.f);
- __m128 _ps_0p5 = _mm_set1_ps(0.5f);
-
- __m128 phase_step_rad_array = _mm_set1_ps(4*phase_step_rad);
-
- __m128 phase_rad_array, x, s, c, swap_sign_bit_sin, sign_bit_cos, poly_mask, z, tmp, y, y2, ysin1, ysin2;
- __m128 xmm1, xmm2, xmm3, sign_bit_sin;
- __m128i emm0, emm2, emm4;
- __VOLK_ATTR_ALIGNED(16) float sin_value[4];
- __VOLK_ATTR_ALIGNED(16) float cos_value[4];
-
- phase_rad_array = _mm_set_ps (phase_rad_init+3*phase_step_rad, phase_rad_init+2*phase_step_rad, phase_rad_init+phase_step_rad, phase_rad_init);
-
- for(unsigned int i = 0; i < sse_iters; i++)
- {
- x = phase_rad_array;
-
- /* extract the sign bit (upper one) */
- sign_bit_sin = _mm_and_ps(x, _ps_sign_mask);
-
- /* take the absolute value */
- x = _mm_xor_ps(x, sign_bit_sin);
-
- /* scale by 4/Pi */
- y = _mm_mul_ps(x, _ps_cephes_FOPI);
-
- /* store the integer part of y in emm2 */
- emm2 = _mm_cvttps_epi32(y);
-
- /* j=(j+1) & (~1) (see the cephes sources) */
- emm2 = _mm_add_epi32(emm2, _pi32_1);
- emm2 = _mm_and_si128(emm2, _pi32_inv1);
- y = _mm_cvtepi32_ps(emm2);
-
- emm4 = emm2;
-
- /* get the swap sign flag for the sine */
- emm0 = _mm_and_si128(emm2, _pi32_4);
- emm0 = _mm_slli_epi32(emm0, 29);
- swap_sign_bit_sin = _mm_castsi128_ps(emm0);
-
- /* get the polynom selection mask for the sine*/
- emm2 = _mm_and_si128(emm2, _pi32_2);
- emm2 = _mm_cmpeq_epi32(emm2, _mm_setzero_si128());
- poly_mask = _mm_castsi128_ps(emm2);
-
- /* The magic pass: "Extended precision modular arithmetic"
- x = ((x - y * DP1) - y * DP2) - y * DP3; */
- xmm1 = _mm_mul_ps(y, _ps_minus_cephes_DP1);
- xmm2 = _mm_mul_ps(y, _ps_minus_cephes_DP2);
- xmm3 = _mm_mul_ps(y, _ps_minus_cephes_DP3);
- x = _mm_add_ps(_mm_add_ps(x, xmm1), _mm_add_ps(xmm2, xmm3));
-
- emm4 = _mm_sub_epi32(emm4, _pi32_2);
- emm4 = _mm_andnot_si128(emm4, _pi32_4);
- emm4 = _mm_slli_epi32(emm4, 29);
- sign_bit_cos = _mm_castsi128_ps(emm4);
-
- sign_bit_sin = _mm_xor_ps(sign_bit_sin, swap_sign_bit_sin);
-
- /* Evaluate the first polynom (0 <= x <= Pi/4) */
- z = _mm_mul_ps(x,x);
- y = _ps_coscof_p0;
- y = _mm_mul_ps(y, z);
- y = _mm_add_ps(y, _ps_coscof_p1);
- y = _mm_mul_ps(y, z);
- y = _mm_add_ps(y, _ps_coscof_p2);
- y = _mm_mul_ps(y, _mm_mul_ps(z, z));
- tmp = _mm_mul_ps(z, _ps_0p5);
- y = _mm_sub_ps(y, tmp);
- y = _mm_add_ps(y, _ps_1);
-
- /* Evaluate the second polynom (Pi/4 <= x <= 0) */
- y2 = _ps_sincof_p0;
- y2 = _mm_mul_ps(y2, z);
- y2 = _mm_add_ps(y2, _ps_sincof_p1);
- y2 = _mm_mul_ps(y2, z);
- y2 = _mm_add_ps(y2, _ps_sincof_p2);
- y2 = _mm_mul_ps(y2, _mm_mul_ps(z, x));
- y2 = _mm_add_ps(y2, x);
-
- /* select the correct result from the two polynoms */
- xmm3 = poly_mask;
- ysin2 = _mm_and_ps(xmm3, y2);
- ysin1 = _mm_andnot_ps(xmm3, y);
- y2 = _mm_sub_ps(y2,ysin2);
- y = _mm_sub_ps(y, ysin1);
-
- xmm1 = _mm_add_ps(ysin1,ysin2);
- xmm2 = _mm_add_ps(y,y2);
-
- /* update the sign */
- s = _mm_xor_ps(xmm1, sign_bit_sin);
- c = _mm_xor_ps(xmm2, sign_bit_cos);
-
- //GNSS-SDR needs to return -sin
- s = _mm_xor_ps(s, _ps_sign_mask);
-
- _mm_store_ps ((float*)sin_value, s);
- _mm_store_ps ((float*)cos_value, c);
-
- for(unsigned int e = 0; e < 4; e++)
- {
- d_carr_sign[e] = lv_cmake(cos_value[e], sin_value[e]);
- }
- d_carr_sign += 4;
-
- phase_rad_array = _mm_add_ps (phase_rad_array, phase_step_rad_array);
- }
-
- if (num_points % 4 != 0)
- {
- __VOLK_ATTR_ALIGNED(16) float phase_rad_store[4];
- _mm_store_ps ((float*)phase_rad_store, phase_rad_array);
-
- float phase_rad = phase_rad_store[0];
-
- for(unsigned int i = 0; i < num_points%4; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
- }
-}
-#endif /* LV_HAVE_SSE2 */
-
-#ifdef LV_HAVE_GENERIC
-/*!
- \brief Accumulates the values in the input buffer
- \param result The accumulated result
- \param inputBuffer The buffer of data to be accumulated
- \param num_points The number of values in inputBuffer to be accumulated
- */
-static inline void volk_gnsssdr_s32f_x2_update_local_carrier_32fc_a_generic(lv_32fc_t* d_carr_sign, const float phase_rad_init, const float phase_step_rad, unsigned int num_points)
-{
- // float* pointer1 = (float*)&phase_rad_init;
- // *pointer1 = 0;
- // float* pointer2 = (float*)&phase_step_rad;
- // *pointer2 = 0.5;
-
- float phase_rad = phase_rad_init;
- for(unsigned int i = 0; i < num_points; i++)
- {
- *d_carr_sign = lv_cmake(cos(phase_rad), -sin(phase_rad));
- d_carr_sign++;
- phase_rad += phase_step_rad;
- }
-}
-#endif /* LV_HAVE_GENERIC */
-#endif /* INCLUDED_volk_gnsssdr_32fc_s32f_x2_update_local_carrier_32fc_a_H */
-
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/CMakeLists.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/CMakeLists.txt
index 62cdb5d..314fbf9 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/CMakeLists.txt
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/CMakeLists.txt
@@ -17,6 +17,23 @@
# along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
#
+#
+# Copyright 2011-2012,2014 Free Software Foundation, Inc.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
########################################################################
# header file detection
########################################################################
@@ -79,10 +96,6 @@ if(HAVE_POSIX_MEMALIGN)
add_definitions(-DHAVE_POSIX_MEMALIGN)
endif(HAVE_POSIX_MEMALIGN)
-if(NOT DEFINED _XOPEN_SOURCE)
- add_definitions(-D_XOPEN_SOURCE=700)
-endif(NOT DEFINED _XOPEN_SOURCE)
-
########################################################################
# detect x86 flavor of CPU
########################################################################
@@ -244,7 +257,6 @@ endif(NOT CPU_IS_x86)
# implement overruling in the ORC case,
# since ORC always passes flag detection
########################################################################
-find_package(ORC)
if(NOT ORC_FOUND)
OVERRULE_ARCH(orc "ORC support not found")
endif()
@@ -254,17 +266,20 @@ endif()
# this makes things work when both -m32 and -m64 pass
########################################################################
if(NOT CROSSCOMPILE_MULTILIB AND CPU_IS_x86)
- if( CMAKE_SIZEOF_VOID_P EQUAL 8 )
+ include(CheckTypeSize)
+ check_type_size("void*[8]" SIZEOF_CPU BUILTIN_TYPES_ONLY)
+ if (${SIZEOF_CPU} EQUAL 64)
OVERRULE_ARCH(32 "CPU width is 64 bits")
endif()
- if( CMAKE_SIZEOF_VOID_P EQUAL 4 )
+ if (${SIZEOF_CPU} EQUAL 32)
OVERRULE_ARCH(64 "CPU width is 32 bits")
endif()
#MSVC 64 bit does not have MMX, overrule it
- if (CMAKE_SIZEOF_VOID_P EQUAL 8 AND MSVC)
+ if (${SIZEOF_CPU} EQUAL 64 AND MSVC)
OVERRULE_ARCH(mmx "No MMX for Win64")
endif()
+
endif()
########################################################################
@@ -336,24 +351,24 @@ gen_template(${CMAKE_SOURCE_DIR}/tmpl/volk_gnsssdr_machines.tmpl.h ${CMAKE_B
gen_template(${CMAKE_SOURCE_DIR}/tmpl/volk_gnsssdr_machines.tmpl.c ${CMAKE_BINARY_DIR}/lib/volk_gnsssdr_machines.c)
set(BASE_CFLAGS NONE)
-STRING(TOUPPER ${CMAKE_BUILD_TYPE} CBTU)
-MESSAGE(STATUS BUILT TYPE ${CBTU})
-MESSAGE(STATUS "Base cflags = ${CMAKE_C_FLAGS_${CBTU}} ${CMAKE_C_FLAGS}")
+string(TOUPPER ${CMAKE_BUILD_TYPE} CBTU)
+message(STATUS "BUILD TYPE = ${CBTU}")
+message(STATUS "Base cflags = ${CMAKE_C_FLAGS_${CBTU}} ${CMAKE_C_FLAGS}")
set(COMPILER_INFO "")
-IF(MSVC)
- IF(MSVC90) #Visual Studio 9
- SET(cmake_c_compiler_version "Microsoft Visual Studio 9.0")
- ELSE(MSVC10) #Visual Studio 10
- SET(cmake_c_compiler_version "Microsoft Visual Studio 10.0")
- ELSE(MSVC11) #Visual Studio 11
- SET(cmake_c_compiler_version "Microsoft Visual Studio 11.0")
- ELSE(MSVC12) #Visual Studio 12
+if(MSVC)
+ if(MSVC90) #Visual Studio 9
+ set(cmake_c_compiler_version "Microsoft Visual Studio 9.0")
+ elseif(MSVC10) #Visual Studio 10
+ set(cmake_c_compiler_version "Microsoft Visual Studio 10.0")
+ elseif(MSVC11) #Visual Studio 11
+ set(cmake_c_compiler_version "Microsoft Visual Studio 11.0")
+ elseif(MSVC12) #Visual Studio 12
SET(cmake_c_compiler_version "Microsoft Visual Studio 12.0")
- ENDIF()
-ELSE()
+ endif()
+else()
execute_process(COMMAND ${CMAKE_C_COMPILER} --version
OUTPUT_VARIABLE cmake_c_compiler_version)
-ENDIF(MSVC)
+endif(MSVC)
set(COMPILER_INFO "${CMAKE_C_COMPILER}:::${CMAKE_C_FLAGS_${GRCBTU}} ${CMAKE_C_FLAGS}\n${CMAKE_CXX_COMPILER}:::${CMAKE_CXX_FLAGS_${GRCBTU}} ${CMAKE_CXX_FLAGS}\n" )
foreach(machine_name ${available_machines})
@@ -402,7 +417,7 @@ include_directories(
# on by default, but let users turn it off
########################################################################
if(${CMAKE_VERSION} VERSION_GREATER "2.8.9")
- set(ASM_ARCHS_AVAILABLE "armv7")
+ set(ASM_ARCHS_AVAILABLE "neon")
set(FULL_C_FLAGS "${CMAKE_C_FLAGS}" "${CMAKE_CXX_COMPILER_ARG1}")
@@ -410,10 +425,10 @@ if(${CMAKE_VERSION} VERSION_GREATER "2.8.9")
# if we find one that matches our current system architecture
# set up the assembler flags and include the source files
foreach(ARCH ${ASM_ARCHS_AVAILABLE})
- string(REGEX MATCH "${ARCH}" ASM_ARCH "${FULL_C_FLAGS}")
- if( ASM_ARCH STREQUAL "armv7" )
+ string(REGEX MATCH "${ARCH}" ASM_ARCH "${available_archs}")
+ if( ASM_ARCH STREQUAL "neon" )
message(STATUS "---- Adding ASM files") # we always use ATT syntax
- message(STATUS "-- Detected armv7 architecture; enabling ASM")
+ message(STATUS "-- Detected neon architecture; enabling ASM")
# setup architecture specific assembler flags
set(ARCH_ASM_FLAGS "-mfpu=neon -g")
# then add the files
@@ -450,7 +465,7 @@ if(ORC_FOUND)
list(APPEND volk_gnsssdr_libraries ${ORC_LIBRARIES})
#setup orc functions
- file(GLOB orc_files ${CMAKE_SOURCE_DIR}/orc/*.orc)
+ file(GLOB orc_files ${CMAKE_SOURCE_DIR}/kernels/volk_gnsssdr/asm/orc/*.orc)
foreach(orc_file ${orc_files})
#extract the name for the generated c source from the orc file
@@ -469,16 +484,10 @@ else()
message(STATUS "Did not find liborc and orcc, disabling orc support...")
endif()
-
########################################################################
# Handle the generated constants
########################################################################
-execute_process(COMMAND ${PYTHON_EXECUTABLE} -c
- "import time;print time.strftime('%a, %d %b %Y %H:%M:%S', time.gmtime())"
- OUTPUT_VARIABLE BUILD_DATE OUTPUT_STRIP_TRAILING_WHITESPACE
-)
-message(STATUS "Loading build date ${BUILD_DATE} into constants...")
message(STATUS "Loading version ${VERSION} into constants...")
#double escape for windows backslash path separators
@@ -520,71 +529,84 @@ if(MSVC)
set_source_files_properties(${volk_gnsssdr_sources} PROPERTIES LANGUAGE CXX)
endif()
-#create the volk_gnsssdr runtime library
-
-#MODIFICATIONS BY GNSS-SDR
-file(GLOB orc ${CMAKE_SOURCE_DIR}/orc/*.orc)
-file(GLOB CommonMacros ${CMAKE_SOURCE_DIR}/kernels/CommonMacros/*.h ${CMAKE_SOURCE_DIR}/kernels/CommonMacros/README.txt)
+#Use object library for faster overall build in newer versions of cmake
+if(CMAKE_VERSION VERSION_GREATER "2.8.7")
+ #Create a volk_gnsssdr object library (requires cmake >= 2.8.8)
+ add_library(volk_gnsssdr_obj OBJECT ${volk_gnsssdr_sources})
+
+ #Add dynamic library
+ add_library(volk_gnsssdr SHARED $<TARGET_OBJECTS:volk_gnsssdr_obj>)
+ target_link_libraries(volk_gnsssdr ${volk_gnsssdr_libraries})
+
+ #Configure target properties
+ set_target_properties(volk_gnsssdr_obj PROPERTIES COMPILE_FLAGS "-fPIC")
+ set_target_properties(volk_gnsssdr PROPERTIES SOVERSION ${LIBVER})
+ set_target_properties(volk_gnsssdr PROPERTIES DEFINE_SYMBOL "volk_gnsssdr_EXPORTS")
+
+ #Install locations
+ install(TARGETS volk_gnsssdr
+ LIBRARY DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_runtime" # .so file
+ ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel" # .lib file
+ RUNTIME DESTINATION bin COMPONENT "volk_gnsssdr_runtime" # .dll file
+ )
-#add_library(volk_gnsssdr SHARED ${volk_gnsssdr_sources})
-if(ENABLE_STATIC_LIBS)
- add_library(volk_gnsssdr STATIC ${volk_gnsssdr_sources} ${h_files} ${CommonMacros} ${orc})
-else(ENABLE_STATIC_LIBS)
- add_library(volk_gnsssdr SHARED ${volk_gnsssdr_sources} ${h_files} ${CommonMacros} ${orc})
-endif(ENABLE_STATIC_LIBS)
+ #Configure static library
+ if(ENABLE_STATIC_LIBS)
+ add_library(volk_gnsssdr_static STATIC $<TARGET_OBJECTS:volk_gnsssdr_obj>)
-source_group("Kernels" FILES ${h_files})
-source_group("Common Macros" FILES ${CommonMacros})
-source_group("ORC Files" FILES ${orc})
-#END OF MODIFICATIONS
+ set_target_properties(volk_gnsssdr_static PROPERTIES OUTPUT_NAME volk_gnsssdr)
-target_link_libraries(volk_gnsssdr ${volk_gnsssdr_libraries})
-set_target_properties(volk_gnsssdr PROPERTIES SOVERSION ${LIBVER})
-set_target_properties(volk_gnsssdr PROPERTIES DEFINE_SYMBOL "volk_gnsssdr_EXPORTS")
+ install(TARGETS volk_gnsssdr_static
+ ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel"
+ )
+ endif(ENABLE_STATIC_LIBS)
-install(TARGETS volk_gnsssdr
- LIBRARY DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_runtime" # .so file
- ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel" # .lib file
- RUNTIME DESTINATION bin COMPONENT "volk_gnsssdr_runtime" # .dll file
-)
+#Older cmake versions (slower to build when building dynamic/static libs)
+else()
+ #create the volk_gnsssdr runtime library
+ add_library(volk_gnsssdr SHARED ${volk_gnsssdr_sources})
+ target_link_libraries(volk_gnsssdr ${volk_gnsssdr_libraries})
+ set_target_properties(volk_gnsssdr PROPERTIES SOVERSION ${LIBVER})
+ set_target_properties(volk_gnsssdr PROPERTIES DEFINE_SYMBOL "volk_gnsssdr_EXPORTS")
+
+ install(TARGETS volk_gnsssdr
+ LIBRARY DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_runtime" # .so file
+ ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel" # .lib file
+ RUNTIME DESTINATION bin COMPONENT "volk_gnsssdr_runtime" # .dll file
+ )
-if(ENABLE_STATIC_LIBS)
- add_library(volk_gnsssdr_static STATIC ${volk_gnsssdr_sources})
+ if(ENABLE_STATIC_LIBS)
+ add_library(volk_gnsssdr_static STATIC ${volk_gnsssdr_sources})
- if(NOT WIN32)
- set_target_properties(volk_gnsssdr_static
- PROPERTIES OUTPUT_NAME volk_gnsssdr)
- endif(NOT WIN32)
+ if(NOT WIN32)
+ set_target_properties(volk_gnsssdr_static
+ PROPERTIES OUTPUT_NAME volk_gnsssdr)
+ endif(NOT WIN32)
- install(TARGETS volk_gnsssdr_static
- ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel" # .lib file
- )
-endif(ENABLE_STATIC_LIBS)
+ install(TARGETS volk_gnsssdr_static
+ ARCHIVE DESTINATION lib${LIB_SUFFIX} COMPONENT "volk_gnsssdr_devel" # .lib file
+ )
+ endif(ENABLE_STATIC_LIBS)
+endif(CMAKE_VERSION VERSION_GREATER "2.8.7")
########################################################################
# Build the QA test application
########################################################################
+if(ENABLE_TESTING)
-
-if(Boost_FOUND)
+ #include Boost headers
+ include_directories(${Boost_INCLUDE_DIRS})
+ make_directory(${CMAKE_CURRENT_BINARY_DIR}/.unittest)
set_source_files_properties(
${CMAKE_CURRENT_SOURCE_DIR}/testqa.cc PROPERTIES
COMPILE_DEFINITIONS "BOOST_TEST_DYN_LINK;BOOST_TEST_MAIN"
)
- include_directories(${Boost_INCLUDE_DIRS})
- link_directories(${Boost_LIBRARY_DIRS})
-
- add_executable(test_all
- ${CMAKE_CURRENT_SOURCE_DIR}/testqa.cc
- ${CMAKE_CURRENT_SOURCE_DIR}/qa_utils.cc
+ include(VolkAddTest)
+ VOLK_ADD_TEST(test_all
+ SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/testqa.cc
+ ${CMAKE_CURRENT_SOURCE_DIR}/qa_utils.cc
+ TARGET_DEPS volk_gnsssdr
)
- if("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
- set(Clang_required_link "c++")
- elseif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
- set(Clang_required_link "")
- endif("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
- target_link_libraries(test_all volk_gnsssdr ${Boost_LIBRARIES} ${Clang_required_link})
- add_test(qa_volk_gnsssdr_test_all test_all)
-
-endif(Boost_FOUND)
+
+endif(ENABLE_TESTING)
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/kernel_tests.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/kernel_tests.h
new file mode 100644
index 0000000..27e5072
--- /dev/null
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/kernel_tests.h
@@ -0,0 +1,84 @@
+/*!
+ * \file kernel_tests.h
+ * \author Carles Fernandez-Prades, 2015. cfernandez(at)cttc.es
+ *
+ * -------------------------------------------------------------------------
+ *
+ * Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
+ *
+ * GNSS-SDR is a software defined Global Navigation
+ * Satellite Systems receiver
+ *
+ * This file is part of GNSS-SDR.
+ *
+ * GNSS-SDR is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * GNSS-SDR is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * -------------------------------------------------------------------------
+ */
+
+
+#include "qa_utils.h"
+#include <vector>
+#include <boost/assign/list_of.hpp>
+#include <volk_gnsssdr/volk_gnsssdr.h>
+
+
+// macros for initializing volk_gnsssdr_test_case_t. Macros are needed to generate
+// function names of the pattern kernel_name_*
+
+// for puppets we need to get all the func_variants for the puppet and just
+// keep track of the actual function name to write to results
+#define VOLK_INIT_PUPP(func, puppet_master_func, test_params)\
+ volk_gnsssdr_test_case_t(func##_get_func_desc(), (void(*)())func##_manual, std::string(#func),\
+ std::string(#puppet_master_func), test_params)
+
+#define VOLK_INIT_TEST(func, test_params)\
+ volk_gnsssdr_test_case_t(func##_get_func_desc(), (void(*)())func##_manual, std::string(#func),\
+ test_params)
+
+std::vector<volk_gnsssdr_test_case_t> init_test_list(volk_gnsssdr_test_params_t test_params)
+{
+
+ // Some kernels need a lower tolerance
+ volk_gnsssdr_test_params_t test_params_inacc = volk_gnsssdr_test_params_t(1e-3, test_params.scalar(),
+ test_params.vlen(), test_params.iter(), test_params.benchmark_mode(), test_params.kernel_regex());
+ volk_gnsssdr_test_params_t test_params_int1 = volk_gnsssdr_test_params_t(1, test_params.scalar(),
+ test_params.vlen(), test_params.iter(), test_params.benchmark_mode(), test_params.kernel_regex());
+
+ std::vector<volk_gnsssdr_test_case_t> test_cases = boost::assign::list_of
+ // no one uses these, so don't test them
+ //VOLK_PROFILE(volk_gnsssdr_16i_x5_add_quad_16i_x4, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
+ //VOLK_PROFILE(volk_gnsssdr_16i_branch_4_state_8, 1e-4, 2046, 10000, &results, benchmark_mode, kernel_regex);
+ //VOLK_PROFILE(volk_gnsssdr_16i_max_star_16i, 0, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
+ //VOLK_PROFILE(volk_gnsssdr_16i_max_star_horizontal_16i, 0, 0, 204602, 10000, &results, benchmark_mode, kernel_regex);
+ //VOLK_PROFILE(volk_gnsssdr_16i_permute_and_scalar_add, 1e-4, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
+ //VOLK_PROFILE(volk_gnsssdr_16i_x4_quad_max_star_16i, 1e-4, 0, 2046, 10000, &results, benchmark_mode, kernel_regex);
+ // we need a puppet for this one
+ //(VOLK_INIT_TEST(volk_gnsssdr_32fc_s32f_x2_power_spectral_density_32f, test_params))
+ //(VOLK_INIT_TEST(volk_gnsssdr_32f_null_32f, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8i_accumulator_s8i, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8i_index_max_16u, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8i_max_s8i, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8i_x2_add_8i, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8ic_conjugate_8ic, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8ic_magnitude_squared_8i, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8ic_x2_dot_prod_8ic, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8ic_x2_multiply_8ic, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_8u_x2_multiply_8u, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_64f_accumulator_64f, test_params))
+ (VOLK_INIT_TEST(volk_gnsssdr_32fc_convert_8ic, test_params))
+ ;
+
+ return test_cases;
+}
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.cc
deleted file mode 100644
index 3c78a81..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.cc
+++ /dev/null
@@ -1,111 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_16s_add_quad_aligned16.h>
-#include <volk_gnsssdr/volk_gnsssdr_16s_add_quad_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-//test for sse2
-
-#ifndef LV_HAVE_SSE2
-
-void qa_16s_add_quad_aligned16::t1()
-{
- printf("sse2 not available... no test performed\n");
-}
-
-#else
-
-void qa_16s_add_quad_aligned16::t1()
-{
- volk_gnsssdr_environment_init();
- clock_t start, end;
- double total;
- const int vlen = 3200;
- const int ITERS = 100000;
- __VOLK_ATTR_ALIGNED(16) short input0[vlen];
- __VOLK_ATTR_ALIGNED(16) short input1[vlen];
- __VOLK_ATTR_ALIGNED(16) short input2[vlen];
- __VOLK_ATTR_ALIGNED(16) short input3[vlen];
- __VOLK_ATTR_ALIGNED(16) short input4[vlen];
-
- __VOLK_ATTR_ALIGNED(16) short output0[vlen];
- __VOLK_ATTR_ALIGNED(16) short output1[vlen];
- __VOLK_ATTR_ALIGNED(16) short output2[vlen];
- __VOLK_ATTR_ALIGNED(16) short output3[vlen];
- __VOLK_ATTR_ALIGNED(16) short output01[vlen];
- __VOLK_ATTR_ALIGNED(16) short output11[vlen];
- __VOLK_ATTR_ALIGNED(16) short output21[vlen];
- __VOLK_ATTR_ALIGNED(16) short output31[vlen];
-
- for(int i = 0; i < vlen; ++i)
- {
- short plus0 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short minus0 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short plus1 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short minus1 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short plus2 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short minus2 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short plus3 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short minus3 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short plus4 = ((short) (rand() - (RAND_MAX/2))) >> 2;
- short minus4 = ((short) (rand() - (RAND_MAX/2))) >> 2;
-
- input0[i] = plus0 - minus0;
- input1[i] = plus1 - minus1;
- input2[i] = plus2 - minus2;
- input3[i] = plus3 - minus3;
- input4[i] = plus4 - minus4;
-
- }
- printf("16s_add_quad_aligned\n");
-
- start = clock();
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_16s_add_quad_aligned16_manual(output0, output1, output2, output3, input0, input1, input2, input3, input4, vlen << 1 , "generic");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("generic_time: %f\n", total);
- start = clock();
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_16s_add_quad_aligned16_manual(output01, output11, output21, output31, input0, input1, input2, input3, input4, vlen << 1 , "sse2");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse2_time: %f\n", total);
- for(int i = 0; i < 1; ++i)
- {
- //printf("inputs: %d, %d\n", input0[i*2], input0[i*2 + 1]);
- //printf("generic... %d, ssse3... %d\n", output0[i], output1[i]);
- }
-
- for(int i = 0; i < vlen; ++i)
- {
- //printf("%d...%d\n", output0[i], output01[i]);
- CPPUNIT_ASSERT_EQUAL(output0[i], output01[i]);
- CPPUNIT_ASSERT_EQUAL(output1[i], output11[i]);
- CPPUNIT_ASSERT_EQUAL(output2[i], output21[i]);
- CPPUNIT_ASSERT_EQUAL(output3[i], output31[i]);
- }
-}
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.h
deleted file mode 100644
index b8a8118..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_add_quad_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_16S_ADD_QUAD_ALIGNED16_H
-#define INCLUDED_QA_16S_ADD_QUAD_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_16s_add_quad_aligned16 : public CppUnit::TestCase
-{
- CPPUNIT_TEST_SUITE (qa_16s_add_quad_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
-private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_16S_ADD_QUAD_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.cc
deleted file mode 100644
index e07d7ea..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.cc
+++ /dev/null
@@ -1,123 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_16s_branch_4_state_8_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-
-//test for ssse3
-
-#ifndef LV_HAVE_SSSE3
-
-void qa_16s_branch_4_state_8_aligned16::t1()
-{
- printf("ssse3 not available... no test performed\n");
-}
-
-#else
-
-void qa_16s_branch_4_state_8_aligned16::t1()
-{
- const int num_iters = 1000000;
- const int vlen = 32;
-
- static char permute0[16]__attribute__((aligned(16))) = {0x0e, 0x0f, 0x0a, 0x0b, 0x04, 0x05, 0x00, 0x01, 0x0c, 0x0d, 0x08, 0x09, 0x06, 0x07, 0x02, 0x03};
- static char permute1[16]__attribute__((aligned(16))) = {0x0c, 0x0d, 0x08, 0x09, 0x06, 0x07, 0x02, 0x03, 0x0e, 0x0f, 0x0a, 0x0b, 0x04, 0x05, 0x00, 0x01};
- static char permute2[16]__attribute__((aligned(16))) = {0x02, 0x03, 0x06, 0x07, 0x08, 0x09, 0x0c, 0x0d, 0x00, 0x01, 0x04, 0x05, 0x0a, 0x0b, 0x0e, 0x0f};
- static char permute3[16]__attribute__((aligned(16))) = {0x00, 0x01, 0x04, 0x05, 0x0a, 0x0b, 0x0e, 0x0f, 0x02, 0x03, 0x06, 0x07, 0x08, 0x09, 0x0c, 0x0d};
- static char* permuters[4] = {permute0, permute1, permute2, permute3};
-
- unsigned int num_bytes = vlen << 1;
-
- volk_gnsssdr_environment_init();
- clock_t start, end;
- double total;
-
- __VOLK_ATTR_ALIGNED(16) short target[vlen];
- __VOLK_ATTR_ALIGNED(16) short target2[vlen];
- __VOLK_ATTR_ALIGNED(16) short target3[vlen];
-
- __VOLK_ATTR_ALIGNED(16) short src0[vlen];
- __VOLK_ATTR_ALIGNED(16) short permute_indexes[vlen] = {
- 7, 5, 2, 0, 6, 4, 3, 1, 6, 4, 3, 1, 7, 5, 2, 0, 1, 3, 4, 6, 0, 2, 5, 7, 0, 2, 5, 7, 1, 3, 4, 6 };
- __VOLK_ATTR_ALIGNED(16) short cntl0[vlen] = {
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 };
- __VOLK_ATTR_ALIGNED(16) short cntl1[vlen] = {
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000 };
- __VOLK_ATTR_ALIGNED(16) short cntl2[vlen] = {
- 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000 };
- __VOLK_ATTR_ALIGNED(16) short cntl3[vlen] = {
- 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0x0000, 0x0000, 0xffff, 0xffff, 0x0000, 0x0000, 0xffff, 0xffff };
- __VOLK_ATTR_ALIGNED(16) short scalars[4] = {1, 2, 3, 4};
-
- for(int i = 0; i < vlen; ++i)
- {
- src0[i] = i;
- }
-
- printf("16s_branch_4_state_8_aligned\n");
-
- start = clock();
- for(int i = 0; i < num_iters; ++i)
- {
- volk_gnsssdr_16s_permute_and_scalar_add_aligned16_manual(target, src0, permute_indexes, cntl0, cntl1, cntl2, cntl3, scalars, num_bytes, "sse2");
- }
- end = clock();
-
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
-
- printf("permute_and_scalar_add_time: %f\n", total);
-
- start = clock();
- for(int i = 0; i < num_iters; ++i)
- {
- volk_gnsssdr_16s_branch_4_state_8_aligned16_manual(target2, src0, permuters, cntl2, cntl3, scalars, "ssse3");
- }
- end = clock();
-
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
-
- printf("branch_4_state_8_time, ssse3: %f\n", total);
-
- start = clock();
- for(int i = 0; i < num_iters; ++i)
- {
- volk_gnsssdr_16s_branch_4_state_8_aligned16_manual(target3, src0, permuters, cntl2, cntl3, scalars, "generic");
- }
- end = clock();
-
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
-
- printf("permute_and_scalar_add_time, generic: %f\n", total);
-
- for(int i = 0; i < vlen; ++i)
- {
- printf("psa... %d, b4s8... %d\n", target[i], target3[i]);
- }
-
- for(int i = 0; i < vlen; ++i)
- {
-
- CPPUNIT_ASSERT(target[i] == target2[i]);
- CPPUNIT_ASSERT(target[i] == target3[i]);
- }
-}
-
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.h
deleted file mode 100644
index 7167fa8..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_branch_4_state_8_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_16S_BRANCH_4_STATE_8_ALIGNED16_H
-#define INCLUDED_QA_16S_BRANCH_4_STATE_8_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_16s_branch_4_state_8_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_16s_branch_4_state_8_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_16S_BRANCH_4_STATE_8_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.cc
deleted file mode 100644
index 48afc66..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.cc
+++ /dev/null
@@ -1,101 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_16s_permute_and_scalar_add_aligned16.h>
-#include <volk_gnsssdr/volk_gnsssdr_16s_permute_and_scalar_add_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-
-//test for sse2
-
-#ifndef LV_HAVE_SSE2
-
-void qa_16s_permute_and_scalar_add_aligned16::t1()
-{
- printf("sse2 not available... no test performed\n");
-}
-
-#else
-
-void qa_16s_permute_and_scalar_add_aligned16::t1()
-{
- const int vlen = 64;
-
- unsigned int num_bytes = vlen << 1;
-
- volk_gnsssdr_environment_init();
- clock_t start, end;
- double total;
-
- __VOLK_ATTR_ALIGNED(16) short target[vlen];
- __VOLK_ATTR_ALIGNED(16) short target2[vlen];
- __VOLK_ATTR_ALIGNED(16) short src0[vlen];
- __VOLK_ATTR_ALIGNED(16) short permute_indexes[vlen];
- __VOLK_ATTR_ALIGNED(16) short cntl0[vlen];
- __VOLK_ATTR_ALIGNED(16) short cntl1[vlen];
- __VOLK_ATTR_ALIGNED(16) short cntl2[vlen];
- __VOLK_ATTR_ALIGNED(16) short cntl3[vlen];
- __VOLK_ATTR_ALIGNED(16) short scalars[4] = {1, 2, 3, 4};
-
- for(int i = 0; i < vlen; ++i)
- {
- src0[i] = i;
- permute_indexes[i] = (3 * i)%vlen;
- cntl0[i] = 0xff;
- cntl1[i] = 0xff * (i%2);
- cntl2[i] = 0xff * ((i>>1)%2);
- cntl3[i] = 0xff * ((i%4) == 3);
- }
-
- printf("16s_permute_and_scalar_add_aligned\n");
-
- start = clock();
- for(int i = 0; i < 100000; ++i)
- {
- volk_gnsssdr_16s_permute_and_scalar_add_aligned16_manual(target, src0, permute_indexes, cntl0, cntl1, cntl2, cntl3, scalars, num_bytes, "generic");
- }
- end = clock();
-
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
-
- printf("generic_time: %f\n", total);
-
- start = clock();
- for(int i = 0; i < 100000; ++i)
- {
- volk_gnsssdr_16s_permute_and_scalar_add_aligned16_manual(target2, src0, permute_indexes, cntl0, cntl1, cntl2, cntl3, scalars, num_bytes, "sse2");
- }
- end = clock();
-
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
-
- printf("sse2_time: %f\n", total);
-
- //for(int i = 0; i < vlen; ++i) {
- //printf("generic... %d, sse2... %d\n", target[i], target2[i]);
- //}
-
- for(int i = 0; i < vlen; ++i)
- {
- CPPUNIT_ASSERT(target[i] == target2[i]);
- }
-}
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.h
deleted file mode 100644
index 7bb192e..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_permute_and_scalar_add_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_16S_PERMUTE_AND_SCALAR_ADD_ALIGNED16_H
-#define INCLUDED_QA_16S_PERMUTE_AND_SCALAR_ADD_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_16s_permute_and_scalar_add_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_16s_permute_and_scalar_add_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_16S_PERMUTE_AND_SCALAR_ADD_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.cc
deleted file mode 100644
index a60b155..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.cc
+++ /dev/null
@@ -1,82 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_16s_quad_max_star_aligned16.h>
-#include <volk_gnsssdr/volk_gnsssdr_16s_quad_max_star_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-
-//test for sse2
-
-#ifndef LV_HAVE_SSE2
-
-void qa_16s_quad_max_star_aligned16::t1()
-{
- printf("sse2 not available... no test performed\n");
-}
-
-#else
-
-void qa_16s_quad_max_star_aligned16::t1()
-{
- const int vlen = 34;
-
- __VOLK_ATTR_ALIGNED(16) short input0[vlen];
- __VOLK_ATTR_ALIGNED(16) short input1[vlen];
- __VOLK_ATTR_ALIGNED(16) short input2[vlen];
- __VOLK_ATTR_ALIGNED(16) short input3[vlen];
-
- __VOLK_ATTR_ALIGNED(16) short output0[vlen];
- __VOLK_ATTR_ALIGNED(16) short output1[vlen];
-
- for(int i = 0; i < vlen; ++i)
- {
- short plus0 = (short) (rand() - (RAND_MAX/2));
- short plus1 = (short) (rand() - (RAND_MAX/2));
- short plus2 = (short) (rand() - (RAND_MAX/2));
- short plus3 = (short) (rand() - (RAND_MAX/2));
-
- short minus0 = (short) (rand() - (RAND_MAX/2));
- short minus1 = (short) (rand() - (RAND_MAX/2));
- short minus2 = (short) (rand() - (RAND_MAX/2));
- short minus3 = (short) (rand() - (RAND_MAX/2));
-
- input0[i] = plus0 - minus0;
- input1[i] = plus1 - minus1;
- input2[i] = plus2 - minus2;
- input3[i] = plus3 - minus3;
- }
-
- volk_gnsssdr_16s_quad_max_star_aligned16_manual(output0, input0, input1, input2, input3, 2*vlen, "generic");
-
- volk_gnsssdr_16s_quad_max_star_aligned16_manual(output1, input0, input1, input2, input3, 2*vlen, "sse2");
-
- printf("16s_quad_max_star_aligned\n");
- for(int i = 0; i < vlen; ++i)
- {
- printf("generic... %d, sse2... %d, inputs: %d, %d, %d, %d\n", output0[i], output1[i], input0[i], input1[i], input2[i], input3[i]);
- }
-
- for(int i = 0; i < vlen; ++i)
- {
- CPPUNIT_ASSERT_EQUAL(output0[i], output1[i]);
- }
-}
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.h
deleted file mode 100644
index 4db9bc4..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_16s_quad_max_star_aligned16.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#ifndef INCLUDED_QA_16S_QUAD_MAX_STAR_ALIGNED16_H
-#define INCLUDED_QA_16S_QUAD_MAX_STAR_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_16s_quad_max_star_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_16s_quad_max_star_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_16S_QUAD_MAX_STAR_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.cc
deleted file mode 100644
index 846db28..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.cc
+++ /dev/null
@@ -1,86 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_32f_fm_detect_aligned16.h>
-#include <volk_gnsssdr/volk_gnsssdr_32f_fm_detect_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-
-//test for sse
-
-#ifndef LV_HAVE_SSE
-
-void qa_32f_fm_detect_aligned16::t1()
-{
- printf("sse not available... no test performed\n");
-}
-
-#else
-
-void qa_32f_fm_detect_aligned16::t1()
-{
- volk_gnsssdr_environment_init();
- clock_t start, end;
- double total;
- const int vlen = 3201;
- const int ITERS = 10000;
- __VOLK_ATTR_ALIGNED(16) float input0[vlen];
-
- __VOLK_ATTR_ALIGNED(16) float output0[vlen];
- __VOLK_ATTR_ALIGNED(16) float output01[vlen];
-
- for(int i = 0; i < vlen; ++i)
- {
- input0[i] = ((float) (rand() - (RAND_MAX/2))) / static_cast<float>((RAND_MAX/2));
- }
- printf("32f_fm_detect_aligned\n");
-
- start = clock();
- float save = 0.1;
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_32f_fm_detect_aligned16_manual(output0, input0, 1.0, &save, vlen, "generic");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("generic_time: %f\n", total);
- start = clock();
- save = 0.1;
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_32f_fm_detect_aligned16_manual(output01, input0, 1.0, &save, vlen, "sse");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse_time: %f\n", total);
- //for(int i = 0; i < 1; ++i)
- // {
- //printf("inputs: %d, %d\n", input0[i*2], input0[i*2 + 1]);
- //printf("generic... %d, ssse3... %d\n", output0[i], output1[i]);
- //}
-
- for(int i = 0; i < vlen; ++i)
- {
- //printf("%d...%d\n", output0[i], output01[i]);
- CPPUNIT_ASSERT_DOUBLES_EQUAL(output0[i], output01[i], fabs(output0[i]) * 1e-4);
- }
-}
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.h
deleted file mode 100644
index aef29ee..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_fm_detect_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_32F_FM_DETECT_ALIGNED16_H
-#define INCLUDED_QA_32F_FM_DETECT_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_32f_fm_detect_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_32f_fm_detect_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_32F_FM_DETECT_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.cc
deleted file mode 100644
index ccd0ac5..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.cc
+++ /dev/null
@@ -1,122 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr_runtime.h>
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_32f_index_max_aligned16.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <time.h>
-
-#define ERR_DELTA (1e-4)
-#define NUM_ITERS 1000000
-#define VEC_LEN 3097
-
-static float uniform()
-{
- return 2.0 * ((float) rand() / RAND_MAX - 0.5); // uniformly (-1, 1)
-}
-
-static void
-random_floats (float *buf, unsigned n)
-{
- unsigned int i = 0;
- for (; i < n; i++)
- {
- buf[i] = uniform () * 32767;
- }
-}
-
-
-#ifndef LV_HAVE_SSE
-
-void qa_32f_index_max_aligned16::t1()
-{
- printf("sse not available... no test performed\n");
-}
-
-#else
-
-
-void qa_32f_index_max_aligned16::t1()
-{
- const int vlen = VEC_LEN;
-
- volk_gnsssdr_runtime_init();
-
- volk_gnsssdr_environment_init();
- int ret;
-
- unsigned int* target_sse4_1;
- unsigned int* target_sse;
- unsigned int* target_generic;
- float* src0 ;
-
- unsigned int i_target_sse4_1;
- target_sse4_1 = &i_target_sse4_1;
- unsigned int i_target_sse;
- target_sse = &i_target_sse;
- unsigned int i_target_generic;
- target_generic = &i_target_generic;
-
- ret = posix_memalign((void**)&src0, 16, vlen *sizeof(float));
-
- random_floats((float*)src0, vlen);
-
- printf("32f_index_max_aligned16\n");
-
- clock_t start, end;
- double total;
-
- start = clock();
- for(int k = 0; k < NUM_ITERS; ++k)
- {
- volk_gnsssdr_32f_index_max_aligned16_manual(target_generic, src0, vlen, "generic");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("generic time: %f\n", total);
-
- start = clock();
- for(int k = 0; k < NUM_ITERS; ++k)
- {
- volk_gnsssdr_32f_index_max_aligned16_manual(target_sse, src0, vlen, "sse2");
- }
-
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse time: %f\n", total);
-
- start = clock();
- for(int k = 0; k < NUM_ITERS; ++k)
- {
- get_volk_gnsssdr_runtime()->volk_gnsssdr_32f_index_max_aligned16(target_sse4_1, src0, vlen);
- }
-
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse4.1 time: %f\n", total);
-
- printf("generic: %u, sse: %u, sse4.1: %u\n", target_generic[0], target_sse[0], target_sse4_1[0]);
- CPPUNIT_ASSERT_EQUAL(target_generic[0], target_sse[0]);
- CPPUNIT_ASSERT_EQUAL(target_generic[0], target_sse4_1[0]);
-
- free(src0);
-}
-
-#endif /*LV_HAVE_SSE3*/
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.h
deleted file mode 100644
index b5121af..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32f_index_max_aligned16.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#ifndef INCLUDED_QA_32F_INDEX_MAX_ALIGNED16_H
-#define INCLUDED_QA_32F_INDEX_MAX_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_32f_index_max_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_32f_index_max_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_32F_INDEX_MAX_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.cc
deleted file mode 100644
index f86ae08..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.cc
+++ /dev/null
@@ -1,104 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_32fc_index_max_aligned16.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <time.h>
-
-#define ERR_DELTA (1e-4)
-#define NUM_ITERS 1000000
-#define VEC_LEN 3096
-
-static float uniform()
-{
- return 2.0 * ((float) rand() / RAND_MAX - 0.5); // uniformly (-1, 1)
-}
-
-static void
-random_floats (float *buf, unsigned n)
-{
- unsigned int i = 0;
- for (; i < n; i++)
- {
- buf[i] = uniform () * 32767;
-
- }
-}
-
-
-#ifndef LV_HAVE_SSE3
-
-void qa_32fc_index_max_aligned16::t1()
-{
- printf("sse3 not available... no test performed\n");
-}
-
-#else
-
-void qa_32fc_index_max_aligned16::t1()
-{
- const int vlen = VEC_LEN;
-
- volk_gnsssdr_environment_init();
- int ret;
-
- unsigned int* target;
- unsigned int* target_generic;
- std::complex<float>* src0 ;
-
- unsigned int i_target;
- target = &i_target;
- unsigned int i_target_generic;
- target_generic = &i_target_generic;
- ret = posix_memalign((void**)&src0, 16, vlen << 3);
-
- random_floats((float*)src0, vlen * 2);
-
- printf("32fc_index_max_aligned16\n");
-
- clock_t start, end;
- double total;
-
- start = clock();
- for(int k = 0; k < NUM_ITERS; ++k)
- {
- volk_gnsssdr_32fc_index_max_aligned16_manual(target_generic, src0, vlen << 3, "generic");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("generic time: %f\n", total);
-
- start = clock();
- for(int k = 0; k < NUM_ITERS; ++k)
- {
- volk_gnsssdr_32fc_index_max_aligned16_manual(target, src0, vlen << 3, "sse3");
- }
-
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse3 time: %f\n", total);
-
- printf("generic: %u, sse3: %u\n", target_generic[0], target[0]);
- CPPUNIT_ASSERT_DOUBLES_EQUAL(target_generic[0], target[0], 1.1);
-
- free(src0);
-}
-
-#endif /*LV_HAVE_SSE3*/
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.h
deleted file mode 100644
index f17708c..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_index_max_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_32FC_INDEX_MAX_ALIGNED16_H
-#define INCLUDED_QA_32FC_INDEX_MAX_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_32fc_index_max_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_32fc_index_max_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_32FC_INDEX_MAX_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.cc
deleted file mode 100644
index 1839e03..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.cc
+++ /dev/null
@@ -1,87 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <qa_32fc_power_spectral_density_32f_aligned16.h>
-#include <volk_gnsssdr/volk_gnsssdr_32fc_power_spectral_density_32f_aligned16.h>
-#include <cstdlib>
-#include <ctime>
-
-//test for sse3
-
-#ifndef LV_HAVE_SSE3
-
-void qa_32fc_power_spectral_density_32f_aligned16::t1()
-{
- printf("sse3 not available... no test performed\n");
-}
-
-#else
-
-void qa_32fc_power_spectral_density_32f_aligned16::t1()
-{
- volk_gnsssdr_environment_init();
- clock_t start, end;
- double total;
- const int vlen = 3201;
- const int ITERS = 10000;
- __VOLK_ATTR_ALIGNED(16) std::complex<float> input0[vlen];
-
- __VOLK_ATTR_ALIGNED(16) float output_generic[vlen];
- __VOLK_ATTR_ALIGNED(16) float output_sse3[vlen];
-
- const float scalar = vlen;
- const float rbw = 1.7;
-
- float* inputLoad = (float*)input0;
- for(int i = 0; i < 2*vlen; ++i)
- {
- inputLoad[i] = (((float) (rand() - (RAND_MAX/2))) / static_cast<float>((RAND_MAX/2)));
- }
- printf("32fc_power_spectral_density_32f_aligned\n");
-
- start = clock();
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_32fc_power_spectral_density_32f_aligned16_manual(output_generic, input0, scalar, rbw, vlen, "generic");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("generic_time: %f\n", total);
- start = clock();
- for(int count = 0; count < ITERS; ++count)
- {
- volk_gnsssdr_32fc_power_spectral_density_32f_aligned16_manual(output_sse3, input0, scalar, rbw, vlen, "sse3");
- }
- end = clock();
- total = (double)(end-start)/(double)CLOCKS_PER_SEC;
- printf("sse3_time: %f\n", total);
-
- //for(int i = 0; i < 1; ++i) {
- //printf("inputs: %d, %d\n", input0[i*2], input0[i*2 + 1]);
- //printf("generic... %d, ssse3... %d\n", output0[i], output1[i]);
- //}
-
- for(int i = 0; i < vlen; ++i)
- {
- //printf("%d...%d\n", output0[i], output01[i]);
- CPPUNIT_ASSERT_DOUBLES_EQUAL(output_generic[i], output_sse3[i], fabs(output_generic[i]*1e-4));
- }
-}
-
-#endif
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.h
deleted file mode 100644
index dbdfc59..0000000
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_32fc_power_spectral_density_32f_aligned16.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
- *
- * This file is part of GNSS-SDR.
- *
- * GNSS-SDR is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * GNSS-SDR is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with GNSS-SDR. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef INCLUDED_QA_32FC_POWER_SPECTRAL_DENSITY_32F_ALIGNED16_H
-#define INCLUDED_QA_32FC_POWER_SPECTRAL_DENSITY_32F_ALIGNED16_H
-
-#include <cppunit/extensions/HelperMacros.h>
-#include <cppunit/TestCase.h>
-
-class qa_32fc_power_spectral_density_32f_aligned16 : public CppUnit::TestCase {
-
- CPPUNIT_TEST_SUITE (qa_32fc_power_spectral_density_32f_aligned16);
- CPPUNIT_TEST (t1);
- CPPUNIT_TEST_SUITE_END ();
-
- private:
- void t1 ();
-};
-
-
-#endif /* INCLUDED_QA_32FC_POWER_SPECTRAL_DENSITY_32F_ALIGNED16_H */
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.cc
index acb5097..3bf8141 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.cc
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.cc
@@ -17,12 +17,14 @@
*/
#include "qa_utils.h"
-#include <cstring>
#include <boost/foreach.hpp>
-#include <boost/assign/list_of.hpp>
#include <boost/tokenizer.hpp>
-#include <boost/xpressive/xpressive.hpp>
+#include <boost/lexical_cast.hpp>
+#include <boost/typeof/typeof.hpp>
+#include <boost/type_traits.hpp>
+
#include <iostream>
+#include <cstring>
#include <fstream>
#include <vector>
#include <map>
@@ -30,83 +32,69 @@
#include <ctime>
#include <cmath>
#include <limits>
-#include <boost/lexical_cast.hpp>
+
#include <volk_gnsssdr/volk_gnsssdr.h>
#include <volk_gnsssdr/volk_gnsssdr_cpu.h>
#include <volk_gnsssdr/volk_gnsssdr_common.h>
#include <volk_gnsssdr/volk_gnsssdr_malloc.h>
-#include <boost/typeof/typeof.hpp>
-#include <boost/type_traits.hpp>
-#include <stdio.h>
-float uniform()
-{
- return 2.0 * ((float) rand() / RAND_MAX - 0.5); // uniformly (-1, 1)
+float uniform() {
+ return M_PI*2.0f * ((float) rand() / RAND_MAX - 0.5f); // uniformly (-1, 1)
}
template <class t>
void random_floats (t *buf, unsigned n)
{
- for (unsigned i = 0; i < n; i++)
- buf[i] = uniform ();
+ for (unsigned i = 0; i < n; i++)
+ buf[i] = uniform ();
}
-void load_random_data(void *data, volk_gnsssdr_type_t type, unsigned int n)
-{
+void load_random_data(void *data, volk_gnsssdr_type_t type, unsigned int n) {
if(type.is_complex) n *= 2;
- if(type.is_float)
- {
- if(type.size == 8) random_floats<double>((double *)data, n);
- else random_floats<float>((float *)data, n);
- }
- else
- {
- float int_max = float(uint64_t(2) << (type.size*8));
- if(type.is_signed) int_max /= 2.0;
- for(unsigned int i=0; i<n; i++)
- {
- float scaled_rand = (((float)(rand() - (RAND_MAX / 2.0))) / (float)((RAND_MAX / 2.0))) * int_max;
- //man i really don't know how to do this in a more clever way, you have to cast down at some point
- switch(type.size)
- {
- case 8:
- if(type.is_signed) ((int64_t *)data)[i] = (int64_t) scaled_rand;
- else ((uint64_t *)data)[i] = (uint64_t) scaled_rand;
- break;
- case 4:
- if(type.is_signed) ((int32_t *)data)[i] = (int32_t) scaled_rand;
- else ((uint32_t *)data)[i] = (uint32_t) scaled_rand;
- break;
- case 2:
- if(type.is_signed) ((int16_t *)data)[i] = (int16_t) scaled_rand;
- else ((uint16_t *)data)[i] = (uint16_t) scaled_rand;
- break;
- case 1:
- if(type.is_signed) ((int8_t *)data)[i] = (int8_t) scaled_rand;
- else ((uint8_t *)data)[i] = (uint8_t) scaled_rand;
- break;
- default:
- throw "load_random_data: no support for data size > 8 or < 1"; //no shenanigans here
- }
- }
+ if(type.is_float) {
+ if(type.size == 8) random_floats<double>((double *)data, n);
+ else random_floats<float>((float *)data, n);
+ } else {
+ float int_max = float(uint64_t(2) << (type.size*8));
+ if(type.is_signed) int_max /= 2.0;
+ for(unsigned int i=0; i<n; i++) {
+ float scaled_rand = (((float) (rand() - (RAND_MAX/2))) / static_cast<float>((RAND_MAX/2))) * int_max;
+ //man i really don't know how to do this in a more clever way, you have to cast down at some point
+ switch(type.size) {
+ case 8:
+ if(type.is_signed) ((int64_t *)data)[i] = (int64_t) scaled_rand;
+ else ((uint64_t *)data)[i] = (uint64_t) scaled_rand;
+ break;
+ case 4:
+ if(type.is_signed) ((int32_t *)data)[i] = (int32_t) scaled_rand;
+ else ((uint32_t *)data)[i] = (uint32_t) scaled_rand;
+ break;
+ case 2:
+ if(type.is_signed) ((int16_t *)data)[i] = (int16_t) scaled_rand;
+ else ((uint16_t *)data)[i] = (uint16_t) scaled_rand;
+ break;
+ case 1:
+ if(type.is_signed) ((int8_t *)data)[i] = (int8_t) scaled_rand;
+ else ((uint8_t *)data)[i] = (uint8_t) scaled_rand;
+ break;
+ default:
+ throw "load_random_data: no support for data size > 8 or < 1"; //no shenanigans here
+ }
}
+ }
}
-static std::vector<std::string> get_arch_list(volk_gnsssdr_func_desc_t desc)
-{
+static std::vector<std::string> get_arch_list(volk_gnsssdr_func_desc_t desc) {
std::vector<std::string> archlist;
- for(size_t i = 0; i < desc.n_impls; i++)
- {
- //if(!(archs[i+1] & volk_gnsssdr_get_lvarch())) continue; //this arch isn't available on this pc
- archlist.push_back(std::string(desc.impl_names[i]));
- }
+ for(size_t i = 0; i < desc.n_impls; i++) {
+ archlist.push_back(std::string(desc.impl_names[i]));
+ }
return archlist;
}
-volk_gnsssdr_type_t volk_gnsssdr_type_from_string(std::string name)
-{
+volk_gnsssdr_type_t volk_gnsssdr_type_from_string(std::string name) {
volk_gnsssdr_type_t type;
type.is_float = false;
type.is_scalar = false;
@@ -115,53 +103,52 @@ volk_gnsssdr_type_t volk_gnsssdr_type_from_string(std::string name)
type.size = 0;
type.str = name;
- if(name.size() < 2) throw std::string("name too short to be a datatype");
+ if(name.size() < 2) {
+ throw std::string("name too short to be a datatype");
+ }
//is it a scalar?
- if(name[0] == 's')
- {
- type.is_scalar = true;
- name = name.substr(1, name.size()-1);
- }
+ if(name[0] == 's') {
+ type.is_scalar = true;
+ name = name.substr(1, name.size()-1);
+ }
//get the data size
size_t last_size_pos = name.find_last_of("0123456789");
- if(last_size_pos == std::string::npos)
+ if(last_size_pos == std::string::npos) {
throw std::string("no size spec in type ").append(name);
+ }
//will throw if malformed
int size = boost::lexical_cast<int>(name.substr(0, last_size_pos+1));
assert(((size % 8) == 0) && (size <= 64) && (size != 0));
type.size = size/8; //in bytes
- for(size_t i=last_size_pos+1; i < name.size(); i++)
- {
- switch (name[i])
- {
- case 'f':
- type.is_float = true;
- break;
- case 'i':
- type.is_signed = true;
- break;
- case 'c':
- type.is_complex = true;
- break;
- case 'u':
- type.is_signed = false;
- break;
- default:
- throw;
- }
+ for(size_t i=last_size_pos+1; i < name.size(); i++) {
+ switch (name[i]) {
+ case 'f':
+ type.is_float = true;
+ break;
+ case 'i':
+ type.is_signed = true;
+ break;
+ case 'c':
+ type.is_complex = true;
+ break;
+ case 'u':
+ type.is_signed = false;
+ break;
+ default:
+ throw;
}
+ }
return type;
}
static void get_signatures_from_name(std::vector<volk_gnsssdr_type_t> &inputsig,
- std::vector<volk_gnsssdr_type_t> &outputsig,
- std::string name)
-{
+ std::vector<volk_gnsssdr_type_t> &outputsig,
+ std::string name) {
boost::char_separator<char> sep("_");
boost::tokenizer<boost::char_separator<char> > tok(name, sep);
std::vector<std::string> toked;
@@ -177,92 +164,75 @@ static void get_signatures_from_name(std::vector<volk_gnsssdr_type_t> &inputsig,
enum { SIDE_INPUT, SIDE_NAME, SIDE_OUTPUT } side = SIDE_INPUT;
std::string fn_name;
volk_gnsssdr_type_t type;
- BOOST_FOREACH(std::string token, toked)
- {
- try
- {
- type = volk_gnsssdr_type_from_string(token);
- if(side == SIDE_NAME) side = SIDE_OUTPUT; //if this is the first one after the name...
-
- if(side == SIDE_INPUT) inputsig.push_back(type);
- else outputsig.push_back(type);
- }
- catch (...)
- {
- if(token[0] == 'x')
- { //it's a multiplier
- if(side == SIDE_INPUT) assert(inputsig.size() > 0);
- else assert(outputsig.size() > 0);
- int multiplier = boost::lexical_cast<int>(token.substr(1, token.size()-1)); //will throw if invalid
- for(int i=1; i<multiplier; i++)
- {
- if(side == SIDE_INPUT) inputsig.push_back(inputsig.back());
- else outputsig.push_back(outputsig.back());
- }
- }
- else if(side == SIDE_INPUT)
- { //it's the function name, at least it better be
- side = SIDE_NAME;
- fn_name.append("_");
- fn_name.append(token);
- }
- else if(side == SIDE_OUTPUT)
- {
- if(token != toked.back()) throw; //the last token in the name is the alignment
- }
+ BOOST_FOREACH(std::string token, toked) {
+ try {
+ type = volk_gnsssdr_type_from_string(token);
+ if(side == SIDE_NAME) side = SIDE_OUTPUT; //if this is the first one after the name...
+
+ if(side == SIDE_INPUT) inputsig.push_back(type);
+ else outputsig.push_back(type);
+ } catch (...){
+ if(token[0] == 'x' && (token.size() > 1) && (token[1] > '0' || token[1] < '9')) { //it's a multiplier
+ if(side == SIDE_INPUT) assert(inputsig.size() > 0);
+ else assert(outputsig.size() > 0);
+ int multiplier = boost::lexical_cast<int>(token.substr(1, token.size()-1)); //will throw if invalid
+ for(int i=1; i<multiplier; i++) {
+ if(side == SIDE_INPUT) inputsig.push_back(inputsig.back());
+ else outputsig.push_back(outputsig.back());
+ }
+ }
+ else if(side == SIDE_INPUT) { //it's the function name, at least it better be
+ side = SIDE_NAME;
+ fn_name.append("_");
+ fn_name.append(token);
+ }
+ else if(side == SIDE_OUTPUT) {
+ if(token != toked.back()) throw; //the last token in the name is the alignment
+ }
}
}
//we don't need an output signature (some fn's operate on the input data, "in place"), but we do need at least one input!
assert(inputsig.size() != 0);
+
}
-inline void run_cast_test1(volk_gnsssdr_fn_1arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test1(volk_gnsssdr_fn_1arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], vlen, arch.c_str());
}
-inline void run_cast_test2(volk_gnsssdr_fn_2arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test2(volk_gnsssdr_fn_2arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], vlen, arch.c_str());
}
-inline void run_cast_test3(volk_gnsssdr_fn_3arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test3(volk_gnsssdr_fn_3arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], buffs[2], vlen, arch.c_str());
}
-inline void run_cast_test4(volk_gnsssdr_fn_4arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test4(volk_gnsssdr_fn_4arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], buffs[2], buffs[3], vlen, arch.c_str());
}
-inline void run_cast_test1_s32f(volk_gnsssdr_fn_1arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test1_s32f(volk_gnsssdr_fn_1arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], scalar, vlen, arch.c_str());
}
-inline void run_cast_test2_s32f(volk_gnsssdr_fn_2arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test2_s32f(volk_gnsssdr_fn_2arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], scalar, vlen, arch.c_str());
}
-inline void run_cast_test3_s32f(volk_gnsssdr_fn_3arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test3_s32f(volk_gnsssdr_fn_3arg_s32f func, std::vector<void *> &buffs, float scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], buffs[2], scalar, vlen, arch.c_str());
}
-inline void run_cast_test1_s32fc(volk_gnsssdr_fn_1arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test1_s32fc(volk_gnsssdr_fn_1arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], scalar, vlen, arch.c_str());
}
-inline void run_cast_test2_s32fc(volk_gnsssdr_fn_2arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test2_s32fc(volk_gnsssdr_fn_2arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], scalar, vlen, arch.c_str());
}
-inline void run_cast_test3_s32fc(volk_gnsssdr_fn_3arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch)
-{
+inline void run_cast_test3_s32fc(volk_gnsssdr_fn_3arg_s32fc func, std::vector<void *> &buffs, lv_32fc_t scalar, unsigned int vlen, unsigned int iter, std::string arch) {
while(iter--) func(buffs[0], buffs[1], buffs[2], scalar, vlen, arch.c_str());
}
@@ -297,6 +267,7 @@ inline void run_cast_test3_s8ic(volk_gnsssdr_fn_3arg_s8ic func, std::vector<void
while(iter--) func(buffs[0], buffs[1], buffs[2], scalar, vlen, arch.c_str());
}
+
inline void run_cast_test8(volk_gnsssdr_fn_8arg func, std::vector<void *> &buffs, unsigned int vlen, unsigned int iter, std::string arch)
{
while(iter--) func(buffs[0], buffs[1], buffs[2], buffs[3], buffs[4], buffs[5], buffs[6], buffs[7], vlen, arch.c_str());
@@ -348,422 +319,335 @@ inline void run_cast_test12_s32fc(volk_gnsssdr_fn_12arg_s32fc func, std::vector<
}
//ADDED BY GNSS-SDR. END
-// This function is a nop that helps resolve GNU Radio bugs 582 and 583.
-// Without this the cast in run_volk_gnsssdr_tests for tol_i = static_cast<int>(float tol)
-// won't happen on armhf (reported on cortex A9 and A15).
-void lv_force_cast_hf( int tol_i, float tol_f)
-{
- int diff_i = 1;
- float diff_f = 1;
- if( diff_i > tol_i )
- std::cout << "" ;
- if( diff_f > tol_f )
- std::cout << "" ;
-}
-
template <class t>
-bool fcompare(t *in1, t *in2, unsigned int vlen, float tol)
-{
+bool fcompare(t *in1, t *in2, unsigned int vlen, float tol) {
bool fail = false;
int print_max_errs = 10;
- for(unsigned int i=0; i<vlen; i++)
- {
- // for very small numbers we'll see round off errors due to limited
- // precision. So a special test case...
- if(fabs(((t *)(in1))[i]) < 1e-30)
- {
- if( fabs( ((t *)(in2))[i] ) > tol )
- {
- fail = true;
- if(print_max_errs-- > 0)
- {
- std::cout << "offset " << i << " in1: " << t(((t *)(in1))[i]) << " in2: " << t(((t *)(in2))[i]) << std::endl;
- }
- }
- }
- // the primary test is the percent different greater than given tol
- else if(fabs(((t *)(in1))[i] - ((t *)(in2))[i])/(((t *)in1)[i]) > tol)
- {
- fail = true;
- if(print_max_errs-- > 0)
- {
- std::cout << "offset " << i << " in1: " << t(((t *)(in1))[i]) << " in2: " << t(((t *)(in2))[i]) << std::endl;
- }
+ for(unsigned int i=0; i<vlen; i++) {
+ // for very small numbers we'll see round off errors due to limited
+ // precision. So a special test case...
+ if(fabs(((t *)(in1))[i]) < 1e-30) {
+ if( fabs( ((t *)(in2))[i] ) > tol )
+ {
+ fail=true;
+ if(print_max_errs-- > 0) {
+ std::cout << "offset " << i << " in1: " << t(((t *)(in1))[i]) << " in2: " << t(((t *)(in2))[i]);
+ std::cout << " tolerance was: " << tol << std::endl;
}
+ }
}
+ // the primary test is the percent different greater than given tol
+ else if(fabs(((t *)(in1))[i] - ((t *)(in2))[i])/fabs(((t *)in1)[i]) > tol) {
+ fail=true;
+ if(print_max_errs-- > 0) {
+ std::cout << "offset " << i << " in1: " << t(((t *)(in1))[i]) << " in2: " << t(((t *)(in2))[i]);
+ std::cout << " tolerance was: " << tol << std::endl;
+ }
+ }
+ }
return fail;
}
template <class t>
-bool ccompare(t *in1, t *in2, unsigned int vlen, float tol)
-{
+bool ccompare(t *in1, t *in2, unsigned int vlen, float tol) {
bool fail = false;
int print_max_errs = 10;
- for(unsigned int i=0; i<2*vlen; i+=2)
- {
- t diff[2] = { in1[i] - in2[i], in1[i+1] - in2[i+1] };
- t err = std::sqrt(diff[0] * diff[0] + diff[1] * diff[1]);
- t norm = std::sqrt(in1[i] * in1[i] + in1[i+1] * in1[i+1]);
-
- // for very small numbers we'll see round off errors due to limited
- // precision. So a special test case...
- if (norm < 1e-30)
- {
- if (err > tol)
- {
- fail = true;
- if(print_max_errs-- > 0) {
- std::cout << "offset " << i/2 << " in1: " << in1[i] << " + " << in1[i+1] << "j in2: " << in2[i] << " + " << in2[i+1] << "j" << std::endl;
- }
- }
- }
- // the primary test is the percent different greater than given tol
- else if((err / norm) > tol)
- {
- fail = true;
- if(print_max_errs-- > 0)
- {
- std::cout << "offset " << i/2 << " in1: " << in1[i] << " + " << in1[i+1] << "j in2: " << in2[i] << " + " << in2[i+1] << "j" << std::endl;
- }
+ for(unsigned int i=0; i<2*vlen; i+=2) {
+ t diff[2] = { in1[i] - in2[i], in1[i+1] - in2[i+1] };
+ t err = std::sqrt(diff[0] * diff[0] + diff[1] * diff[1]);
+ t norm = std::sqrt(in1[i] * in1[i] + in1[i+1] * in1[i+1]);
+
+ // for very small numbers we'll see round off errors due to limited
+ // precision. So a special test case...
+ if (norm < 1e-30) {
+ if (err > tol)
+ {
+ fail=true;
+ if(print_max_errs-- > 0) {
+ std::cout << "offset " << i/2 << " in1: " << in1[i] << " + " << in1[i+1] << "j in2: " << in2[i] << " + " << in2[i+1] << "j";
+ std::cout << " tolerance was: " << tol << std::endl;
}
+ }
+ }
+ // the primary test is the percent different greater than given tol
+ else if((err / norm) > tol) {
+ fail=true;
+ if(print_max_errs-- > 0) {
+ std::cout << "offset " << i/2 << " in1: " << in1[i] << " + " << in1[i+1] << "j in2: " << in2[i] << " + " << in2[i+1] << "j";
+ std::cout << " tolerance was: " << tol << std::endl;
+ }
}
+ }
return fail;
}
template <class t>
-bool icompare(t *in1, t *in2, unsigned int vlen, unsigned int tol)
-{
+bool icompare(t *in1, t *in2, unsigned int vlen, unsigned int tol) {
bool fail = false;
int print_max_errs = 10;
- for(unsigned int i=0; i<vlen; i++)
- {
- if(abs(int(((t *)(in1))[i]) - int(((t *)(in2))[i])) > tol)
- {
- fail = true;
- if(print_max_errs-- > 0)
- {
- std::cout << "offset " << i << " in1: " << static_cast<int>(t(((t *)(in1))[i])) << " in2: " << static_cast<int>(t(((t *)(in2))[i])) << std::endl;
- }
- }
+ for(unsigned int i=0; i<vlen; i++) {
+ if(((unsigned int)abs(int(((t *)(in1))[i]) - int(((t *)(in2))[i]))) > tol) {
+ fail=true;
+ if(print_max_errs-- > 0) {
+ std::cout << "offset " << i << " in1: " << static_cast<int>(t(((t *)(in1))[i])) << " in2: " << static_cast<int>(t(((t *)(in2))[i]));
+ std::cout << " tolerance was: " << tol << std::endl;
+ }
}
+ }
return fail;
}
-class volk_gnsssdr_qa_aligned_mem_pool
-{
+class volk_gnsssdr_qa_aligned_mem_pool{
public:
- void *get_new(size_t size)
- {
+ void *get_new(size_t size){
size_t alignment = volk_gnsssdr_get_alignment();
void* ptr = volk_gnsssdr_malloc(size, alignment);
memset(ptr, 0x00, size);
_mems.push_back(ptr);
return ptr;
}
- ~volk_gnsssdr_qa_aligned_mem_pool()
- {
- for(unsigned int ii = 0; ii < _mems.size(); ++ii)
- {
- volk_gnsssdr_free(_mems[ii]);
- }
+ ~volk_gnsssdr_qa_aligned_mem_pool() {
+ for(unsigned int ii = 0; ii < _mems.size(); ++ii) {
+ volk_gnsssdr_free(_mems[ii]);
+ }
}
private: std::vector<void * > _mems;
};
bool run_volk_gnsssdr_tests(volk_gnsssdr_func_desc_t desc,
- void (*manual_func)(),
- std::string name,
- float tol,
- lv_32fc_t scalar,
- int vlen,
- int iter,
- std::vector<volk_gnsssdr_test_results_t> *results,
- std::string puppet_master_name,
- bool benchmark_mode,
- std::string kernel_regex
- )
+ void (*manual_func)(),
+ std::string name,
+ volk_gnsssdr_test_params_t test_params,
+ std::vector<volk_gnsssdr_test_results_t> *results,
+ std::string puppet_master_name
+)
{
- boost::xpressive::sregex kernel_expression = boost::xpressive::sregex::compile(kernel_regex);
- if( !boost::xpressive::regex_search(name, kernel_expression) )
- {
- // in this case we have a regex and are only looking to test one kernel
- return false;
- }
- if(results)
- {
- results->push_back(volk_gnsssdr_test_results_t());
- results->back().name = name;
- results->back().vlen = vlen;
- results->back().iter = iter;
- }
+ return run_volk_gnsssdr_tests(desc, manual_func, name, test_params.tol(), test_params.scalar(),
+ test_params.vlen(), test_params.iter(), results, puppet_master_name,
+ test_params.benchmark_mode());
+}
+
+bool run_volk_gnsssdr_tests(volk_gnsssdr_func_desc_t desc,
+ void (*manual_func)(),
+ std::string name,
+ float tol,
+ lv_32fc_t scalar,
+ unsigned int vlen,
+ unsigned int iter,
+ std::vector<volk_gnsssdr_test_results_t> *results,
+ std::string puppet_master_name,
+ bool benchmark_mode
+) {
+ // Initialize this entry in results vector
+ results->push_back(volk_gnsssdr_test_results_t());
+ results->back().name = name;
+ results->back().vlen = vlen;
+ results->back().iter = iter;
std::cout << "RUN_VOLK_TESTS: " << name << "(" << vlen << "," << iter << ")" << std::endl;
- // The multiply and lv_force_cast_hf are work arounds for GNU Radio bugs 582 and 583
- // The bug is the casting/assignment below do not happen, which results in false
- // positives when testing for errors in fcompare and icompare.
- // Since this only happens on armhf (reported for Cortex A9 and A15) combined with
- // the following fixes it is suspected to be a compiler bug.
- // Bug 1272024 on launchpad has been filed with Linaro GCC.
- const float tol_f = tol*1.0000001;
+ // vlen_twiddle will increase vlen for malloc and data generation
+ // but kernels will still be called with the user provided vlen.
+ // This is useful for causing errors in kernels that do bad reads
+ const unsigned int vlen_twiddle = 5;
+ vlen = vlen + vlen_twiddle;
+
+ const float tol_f = tol;
const unsigned int tol_i = static_cast<const unsigned int>(tol);
- lv_force_cast_hf( tol_i, tol_f );
//first let's get a list of available architectures for the test
std::vector<std::string> arch_list = get_arch_list(desc);
- if((!benchmark_mode) && (arch_list.size() < 2))
- {
- std::cout << "no architectures to test" << std::endl;
- return false;
- }
+ if((!benchmark_mode) && (arch_list.size() < 2)) {
+ std::cout << "no architectures to test" << std::endl;
+ return false;
+ }
//something that can hang onto memory and cleanup when this function exits
volk_gnsssdr_qa_aligned_mem_pool mem_pool;
//now we have to get a function signature by parsing the name
std::vector<volk_gnsssdr_type_t> inputsig, outputsig;
- get_signatures_from_name(inputsig, outputsig, name);
+ try {
+ get_signatures_from_name(inputsig, outputsig, name);
+ }
+ catch (boost::bad_lexical_cast& error) {
+ std::cerr << "Error: unable to get function signature from kernel name" << std::endl;
+ std::cerr << " - " << name << std::endl;
+ return false;
+ }
//pull the input scalars into their own vector
std::vector<volk_gnsssdr_type_t> inputsc;
- for(size_t i=0; i<inputsig.size(); i++)
- {
- if(inputsig[i].is_scalar)
- {
- inputsc.push_back(inputsig[i]);
- inputsig.erase(inputsig.begin() + i);
- i -= 1;
- }
+ for(size_t i=0; i<inputsig.size(); i++) {
+ if(inputsig[i].is_scalar) {
+ inputsc.push_back(inputsig[i]);
+ inputsig.erase(inputsig.begin() + i);
+ i -= 1;
}
- //for(int i=0; i<inputsig.size(); i++) std::cout << "Input: " << inputsig[i].str << std::endl;
- //for(int i=0; i<outputsig.size(); i++) std::cout << "Output: " << outputsig[i].str << std::endl;
+ }
std::vector<void *> inbuffs;
- BOOST_FOREACH(volk_gnsssdr_type_t sig, inputsig)
- {
+ BOOST_FOREACH(volk_gnsssdr_type_t sig, inputsig) {
if(!sig.is_scalar) //we don't make buffers for scalars
- inbuffs.push_back(mem_pool.get_new(vlen*sig.size*(sig.is_complex ? 2 : 1)));
+ inbuffs.push_back(mem_pool.get_new(vlen*sig.size*(sig.is_complex ? 2 : 1)));
+ }
+ for(size_t i=0; i<inbuffs.size(); i++) {
+ load_random_data(inbuffs[i], inputsig[i], vlen);
}
- for(size_t i=0; i<inbuffs.size(); i++)
- {
- load_random_data(inbuffs[i], inputsig[i], vlen);
- }
//ok let's make a vector of vector of void buffers, which holds the input/output vectors for each arch
std::vector<std::vector<void *> > test_data;
- for(size_t i=0; i<arch_list.size(); i++)
- {
- std::vector<void *> arch_buffs;
- for(size_t j=0; j<outputsig.size(); j++)
- {
- arch_buffs.push_back(mem_pool.get_new(vlen*outputsig[j].size*(outputsig[j].is_complex ? 2 : 1)));
- }
- for(size_t j=0; j<inputsig.size(); j++)
- {
- arch_buffs.push_back(inbuffs[j]);
- }
- test_data.push_back(arch_buffs);
+ for(size_t i=0; i<arch_list.size(); i++) {
+ std::vector<void *> arch_buffs;
+ for(size_t j=0; j<outputsig.size(); j++) {
+ arch_buffs.push_back(mem_pool.get_new(vlen*outputsig[j].size*(outputsig[j].is_complex ? 2 : 1)));
}
+ for(size_t j=0; j<inputsig.size(); j++) {
+ void *arch_inbuff = mem_pool.get_new(vlen*inputsig[j].size*(inputsig[j].is_complex ? 2 : 1));
+ memcpy(arch_inbuff, inbuffs[j], vlen * inputsig[j].size * (inputsig[j].is_complex ? 2 : 1));
+ arch_buffs.push_back(arch_inbuff);
+ }
+ test_data.push_back(arch_buffs);
+ }
std::vector<volk_gnsssdr_type_t> both_sigs;
both_sigs.insert(both_sigs.end(), outputsig.begin(), outputsig.end());
both_sigs.insert(both_sigs.end(), inputsig.begin(), inputsig.end());
//now run the test
+ vlen = vlen - vlen_twiddle;
clock_t start, end;
std::vector<double> profile_times;
- for(size_t i = 0; i < arch_list.size(); i++)
- {
- start = clock();
+ for(size_t i = 0; i < arch_list.size(); i++) {
+ start = clock();
- switch(both_sigs.size())
- {
- case 1:
- if(inputsc.size() == 0)
- {
- run_cast_test1((volk_gnsssdr_fn_1arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- }
- else if(inputsc.size() == 1 && inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test1_s32fc((volk_gnsssdr_fn_1arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test1_s32f((volk_gnsssdr_fn_1arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. START
- else if(inputsc.size() == 1 && !inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test1_s8ic((volk_gnsssdr_fn_1arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test1_s8i((volk_gnsssdr_fn_1arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. END
- else throw "unsupported 1 arg function >1 scalars";
- break;
- case 2:
- if(inputsc.size() == 0)
- {
- run_cast_test2((volk_gnsssdr_fn_2arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- }
- else if(inputsc.size() == 1 && inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test2_s32fc((volk_gnsssdr_fn_2arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test2_s32f((volk_gnsssdr_fn_2arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. START
- else if(inputsc.size() == 1 && !inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test2_s8ic((volk_gnsssdr_fn_2arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test2_s8i((volk_gnsssdr_fn_2arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. END
- else throw "unsupported 2 arg function >1 scalars";
- break;
- case 3:
- if(inputsc.size() == 0)
- {
- run_cast_test3((volk_gnsssdr_fn_3arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- }
- else if(inputsc.size() == 1 && inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test3_s32fc((volk_gnsssdr_fn_3arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test3_s32f((volk_gnsssdr_fn_3arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. START
- else if(inputsc.size() == 1 && !inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test3_s8ic((volk_gnsssdr_fn_3arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test3_s8i((volk_gnsssdr_fn_3arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- //ADDED BY GNSS-SDR. END
- else throw "unsupported 3 arg function >1 scalars";
- break;
- case 4:
- run_cast_test4((volk_gnsssdr_fn_4arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- break;
- //ADDED BY GNSS-SDR. START
- case 8:
- if(inputsc.size() == 0)
- {
- run_cast_test8((volk_gnsssdr_fn_8arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- }
- else if(inputsc.size() == 1 && inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test8_s32fc((volk_gnsssdr_fn_8arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test8_s32f((volk_gnsssdr_fn_8arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- else if(inputsc.size() == 1 && !inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test8_s8ic((volk_gnsssdr_fn_8arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test8_s8i((volk_gnsssdr_fn_8arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- else throw "unsupported 8 arg function >1 scalars";
- break;
- case 12:
- if(inputsc.size() == 0)
- {
- run_cast_test12((volk_gnsssdr_fn_12arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
- }
- else if(inputsc.size() == 1 && inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test12_s32fc((volk_gnsssdr_fn_12arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- }
- else
- {
- run_cast_test12_s32f((volk_gnsssdr_fn_12arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- else if(inputsc.size() == 1 && !inputsc[0].is_float)
- {
- if(inputsc[0].is_complex)
- {
- run_cast_test12_s8ic((volk_gnsssdr_fn_12arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
- } else {
- run_cast_test12_s8i((volk_gnsssdr_fn_12arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
- }
- }
- else throw "unsupported 12 arg function >1 scalars";
- break;
- //ADDED BY GNSS-SDR. END
+ switch(both_sigs.size())
+ {
+ case 1:
+ if(inputsc.size() == 0)
+ {
+ run_cast_test1((volk_gnsssdr_fn_1arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
+ }
+ else if(inputsc.size() == 1 && inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test1_s32fc((volk_gnsssdr_fn_1arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test1_s32f((volk_gnsssdr_fn_1arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. START
+ else if(inputsc.size() == 1 && !inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test1_s8ic((volk_gnsssdr_fn_1arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test1_s8i((volk_gnsssdr_fn_1arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. END
+ else throw "unsupported 1 arg function >1 scalars";
+ break;
+ case 2:
+ if(inputsc.size() == 0)
+ {
+ run_cast_test2((volk_gnsssdr_fn_2arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
+ }
+ else if(inputsc.size() == 1 && inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test2_s32fc((volk_gnsssdr_fn_2arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test2_s32f((volk_gnsssdr_fn_2arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. START
+ else if(inputsc.size() == 1 && !inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test2_s8ic((volk_gnsssdr_fn_2arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test2_s8i((volk_gnsssdr_fn_2arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. END
+ else throw "unsupported 2 arg function >1 scalars";
+ break;
+ case 3:
+ if(inputsc.size() == 0)
+ {
+ run_cast_test3((volk_gnsssdr_fn_3arg)(manual_func), test_data[i], vlen, iter, arch_list[i]);
+ }
+ else if(inputsc.size() == 1 && inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test3_s32fc((volk_gnsssdr_fn_3arg_s32fc)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test3_s32f((volk_gnsssdr_fn_3arg_s32f)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. START
+ else if(inputsc.size() == 1 && !inputsc[0].is_float)
+ {
+ if(inputsc[0].is_complex)
+ {
+ run_cast_test3_s8ic((volk_gnsssdr_fn_3arg_s8ic)(manual_func), test_data[i], scalar, vlen, iter, arch_list[i]);
+ }
+ else
+ {
+ run_cast_test3_s8i((volk_gnsssdr_fn_3arg_s8i)(manual_func), test_data[i], scalar.real(), vlen, iter, arch_list[i]);
+ }
+ }
+ //ADDED BY GNSS-SDR. END
+ else throw "unsupported 3 arg function >1 scalars";
+ break;
default:
throw "no function handler for this signature";
break;
- }
-
- end = clock();
- double arch_time = 1000.0 * (double)(end-start)/(double)CLOCKS_PER_SEC;
- std::cout << arch_list[i] << " completed in " << arch_time << "ms" << std::endl;
- if(results)
- {
- volk_gnsssdr_test_time_t result;
- result.name = arch_list[i];
- result.time = arch_time;
- result.units = "ms";
- results->back().results[result.name] = result;
- }
-
- profile_times.push_back(arch_time);
}
+ end = clock();
+ double arch_time = 1000.0 * (double)(end-start)/(double)CLOCKS_PER_SEC;
+ std::cout << arch_list[i] << " completed in " << arch_time << "ms" << std::endl;
+ volk_gnsssdr_test_time_t result;
+ result.name = arch_list[i];
+ result.time = arch_time;
+ result.units = "ms";
+ result.pass = true;
+ results->back().results[result.name] = result;
+
+ profile_times.push_back(arch_time);
+ }
+
//and now compare each output to the generic output
//first we have to know which output is the generic one, they aren't in order...
size_t generic_offset=0;
- for(size_t i=0; i<arch_list.size(); i++)
- if(arch_list[i] == "generic") generic_offset=i;
-
- //now compare
- //if(outputsig.size() == 0) outputsig = inputsig; //a hack, i know
+ for(size_t i=0; i<arch_list.size(); i++) {
+ if (arch_list[i] == "generic") {
+ generic_offset = i;
+ }
+ }
- bool fail = false;
+ // Just in case a kernel wrote to OOB memory, use the twiddled vlen
+ vlen = vlen + vlen_twiddle;
+ bool fail;
bool fail_global = false;
std::vector<bool> arch_results;
for(size_t i=0; i<arch_list.size(); i++)
@@ -780,7 +664,6 @@ bool run_volk_gnsssdr_tests(volk_gnsssdr_func_desc_t desc,
if (both_sigs[j].is_complex)
{
fail = ccompare((double *) test_data[generic_offset][j], (double *) test_data[i][j], vlen, tol_f);
-
}
else
{
@@ -850,10 +733,11 @@ bool run_volk_gnsssdr_tests(volk_gnsssdr_func_desc_t desc,
}
if(fail)
{
+ volk_gnsssdr_test_time_t *result = &results->back().results[arch_list[i]];
+ result->pass = !fail;
fail_global = true;
std::cout << name << ": fail on arch " << arch_list[i] << std::endl;
}
- //fail = memcmp(outbuffs[generic_offset], outbuffs[i], outputsig[0].size * vlen * (outputsig[0].is_complex ? 2:1));
}
}
arch_results.push_back(!fail);
@@ -879,21 +763,16 @@ bool run_volk_gnsssdr_tests(volk_gnsssdr_func_desc_t desc,
std::cout << "Best aligned arch: " << best_arch_a << std::endl;
std::cout << "Best unaligned arch: " << best_arch_u << std::endl;
- if(results)
+
+ if(puppet_master_name == "NULL") {
+ results->back().config_name = name;
+ }
+ else
{
- if(puppet_master_name == "NULL")
- {
- results->back().config_name = name;
- }
- else
- {
- results->back().config_name = puppet_master_name;
- }
- results->back().best_arch_a = best_arch_a;
- results->back().best_arch_u = best_arch_u;
+ results->back().config_name = puppet_master_name;
}
+ results->back().best_arch_a = best_arch_a;
+ results->back().best_arch_u = best_arch_u;
return fail_global;
}
-
-
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.h
index ae05939..3163129 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/qa_utils.h
@@ -28,6 +28,9 @@
#include <volk_gnsssdr/volk_gnsssdr.h>
#include <volk_gnsssdr/volk_gnsssdr_common.h>
+/************************************************
+ * VOLK QA type definitions *
+ ************************************************/
struct volk_gnsssdr_type_t {
bool is_float;
bool is_scalar;
@@ -37,45 +40,105 @@ struct volk_gnsssdr_type_t {
std::string str;
};
-volk_gnsssdr_type_t volk_gnsssdr_type_from_string(std::string);
+class volk_gnsssdr_test_time_t {
+ public:
+ std::string name;
+ double time;
+ std::string units;
+ bool pass;
+};
-float uniform(void);
-void random_floats(float *buf, unsigned n);
+class volk_gnsssdr_test_results_t {
+ public:
+ std::string name;
+ std::string config_name;
+ unsigned int vlen;
+ unsigned int iter;
+ std::map<std::string, volk_gnsssdr_test_time_t> results;
+ std::string best_arch_a;
+ std::string best_arch_u;
+};
-class volk_gnsssdr_test_time_t
-{
-public:
- std::string name;
- double time;
- std::string units;
+class volk_gnsssdr_test_params_t {
+ private:
+ float _tol;
+ lv_32fc_t _scalar;
+ unsigned int _vlen;
+ unsigned int _iter;
+ bool _benchmark_mode;
+ std::string _kernel_regex;
+ public:
+ // ctor
+ volk_gnsssdr_test_params_t(float tol, lv_32fc_t scalar, unsigned int vlen, unsigned int iter,
+ bool benchmark_mode, std::string kernel_regex) :
+ _tol(tol), _scalar(scalar), _vlen(vlen), _iter(iter),
+ _benchmark_mode(benchmark_mode), _kernel_regex(kernel_regex) {};
+ // getters
+ float tol() {return _tol;};
+ lv_32fc_t scalar() {return _scalar;};
+ unsigned int vlen() {return _vlen;};
+ unsigned int iter() {return _iter;};
+ bool benchmark_mode() {return _benchmark_mode;};
+ std::string kernel_regex() {return _kernel_regex;};
};
-class volk_gnsssdr_test_results_t
-{
-public:
- std::string name;
- std::string config_name;
- int vlen;
- int iter;
- std::map<std::string, volk_gnsssdr_test_time_t> results;
- std::string best_arch_a;
- std::string best_arch_u;
+class volk_gnsssdr_test_case_t {
+ private:
+ volk_gnsssdr_func_desc_t _desc;
+ void(*_kernel_ptr)();
+ std::string _name;
+ volk_gnsssdr_test_params_t _test_parameters;
+ std::string _puppet_master_name;
+ public:
+ volk_gnsssdr_func_desc_t desc() {return _desc;};
+ void (*kernel_ptr()) () {return _kernel_ptr;};
+ std::string name() {return _name;};
+ std::string puppet_master_name() {return _puppet_master_name;};
+ volk_gnsssdr_test_params_t test_parameters() {return _test_parameters;};
+ // normal ctor
+ volk_gnsssdr_test_case_t(volk_gnsssdr_func_desc_t desc, void(*kernel_ptr)(), std::string name,
+ volk_gnsssdr_test_params_t test_parameters) :
+ _desc(desc), _kernel_ptr(kernel_ptr), _name(name), _test_parameters(test_parameters),
+ _puppet_master_name("NULL")
+ {};
+ // ctor for puppets
+ volk_gnsssdr_test_case_t(volk_gnsssdr_func_desc_t desc, void(*kernel_ptr)(), std::string name,
+ std::string puppet_master_name, volk_gnsssdr_test_params_t test_parameters) :
+ _desc(desc), _kernel_ptr(kernel_ptr), _name(name), _test_parameters(test_parameters),
+ _puppet_master_name(puppet_master_name)
+ {};
};
+/************************************************
+ * VOLK QA functions *
+ ************************************************/
+volk_gnsssdr_type_t volk_gnsssdr_type_from_string(std::string);
+
+float uniform(void);
+void random_floats(float *buf, unsigned n);
+
bool run_volk_gnsssdr_tests(
- volk_gnsssdr_func_desc_t,
- void(*)(),
- std::string,
- float,
- lv_32fc_t,
- int,
- int,
- std::vector<volk_gnsssdr_test_results_t> *results = NULL,
- std::string puppet_master_name = "NULL",
- bool benchmark_mode=false,
- std::string kernel_regex=""
+ volk_gnsssdr_func_desc_t,
+ void(*)(),
+ std::string,
+ volk_gnsssdr_test_params_t,
+ std::vector<volk_gnsssdr_test_results_t> *results = NULL,
+ std::string puppet_master_name = "NULL"
);
+bool run_volk_gnsssdr_tests(
+ volk_gnsssdr_func_desc_t,
+ void(*)(),
+ std::string,
+ float,
+ lv_32fc_t,
+ unsigned int,
+ unsigned int,
+ std::vector<volk_gnsssdr_test_results_t> *results = NULL,
+ std::string puppet_master_name = "NULL",
+ bool benchmark_mode = false
+);
+
#define VOLK_RUN_TESTS(func, tol, scalar, len, iter) \
BOOST_AUTO_TEST_CASE(func##_test) { \
@@ -84,8 +147,8 @@ bool run_volk_gnsssdr_tests(
std::string(#func), tol, scalar, len, iter, 0, "NULL"), \
0); \
}
-#define VOLK_PROFILE(func, tol, scalar, len, iter, results, bnmode, kernel_regex) run_volk_gnsssdr_tests(func##_get_func_desc(), (void (*)())func##_manual, std::string(#func), tol, scalar, len, iter, results, "NULL", bnmode, kernel_regex)
-#define VOLK_PUPPET_PROFILE(func, puppet_master_func, tol, scalar, len, iter, results, bnmode, kernel_regex) run_volk_gnsssdr_tests(func##_get_func_desc(), (void (*)())func##_manual, std::string(#func), tol, scalar, len, iter, results, std::string(#puppet_master_func), bnmode, kernel_regex)
+#define VOLK_PROFILE(func, test_params, results) run_volk_gnsssdr_tests(func##_get_func_desc(), (void (*)())func##_manual, std::string(#func), test_params, results, "NULL")
+#define VOLK_PUPPET_PROFILE(func, puppet_master_func, test_params, results) run_volk_gnsssdr_tests(func##_get_func_desc(), (void (*)())func##_manual, std::string(#func), test_params, results, std::string(#puppet_master_func))
typedef void (*volk_gnsssdr_fn_1arg)(void *, unsigned int, const char*); //one input, operate in place
typedef void (*volk_gnsssdr_fn_2arg)(void *, void *, unsigned int, const char*);
typedef void (*volk_gnsssdr_fn_3arg)(void *, void *, void *, unsigned int, const char*);
@@ -97,6 +160,8 @@ typedef void (*volk_gnsssdr_fn_1arg_s32fc)(void *, lv_32fc_t, unsigned int, cons
typedef void (*volk_gnsssdr_fn_2arg_s32fc)(void *, void *, lv_32fc_t, unsigned int, const char*);
typedef void (*volk_gnsssdr_fn_3arg_s32fc)(void *, void *, void *, lv_32fc_t, unsigned int, const char*);
+
+
//ADDED BY GNSS-SDR. START
typedef void (*volk_gnsssdr_fn_1arg_s8i)(void *, char, unsigned int, const char*); //one input vector, one scalar char input
typedef void (*volk_gnsssdr_fn_2arg_s8i)(void *, void *, char, unsigned int, const char*);
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/testqa.cc b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/testqa.cc
index 7e0f624..946aab4 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/testqa.cc
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/lib/testqa.cc
@@ -19,42 +19,111 @@
#include "qa_utils.h"
+#include "kernel_tests.h"
+
#include <volk_gnsssdr/volk_gnsssdr.h>
-#include <boost/test/unit_test.hpp>
-
-//GNSS-SDR PROTO-KERNELS
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x2_multiply_8ic, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8u_x2_multiply_8u, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x2_dot_prod_8ic, 1e-4, 0, 204603, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_s8ic_multiply_8ic, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_conjugate_8ic, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8i_x2_add_8i, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8i_index_max_16u, 3, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8i_accumulator_s8i, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_magnitude_squared_8i, 1e-4, 0, 20462, 1);
-
-VOLK_RUN_TESTS(volk_gnsssdr_8i_max_s8i, 3, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_64f_accumulator_64f, 3, 0, 20462, 1);
-
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_convert_16ic, 3, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_s32f_convert_8ic, 3, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_convert_8ic, 3, 0, 20462, 1);
-
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x5_cw_epl_corr_8ic_x3, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_16ic_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_16ic_x5_cw_epl_corr_TEST_32fc_x3, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x5_cw_epl_corr_32fc_x3, 1e-4, 0, 20462, 1);
-
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_16ic_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x7_cw_vepl_corr_safe_32fc_x5, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x7_cw_vepl_corr_unsafe_32fc_x5, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x7_cw_vepl_corr_32fc_x5, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_8ic_x7_cw_vepl_corr_TEST_32fc_x5, 1e-4, 0, 20462, 1);
-
-VOLK_RUN_TESTS(volk_gnsssdr_32fc_s32f_x4_update_local_code_32fc, 1e-4, 0, 20462, 1);
-VOLK_RUN_TESTS(volk_gnsssdr_s32f_x2_update_local_carrier_32fc, 1e-4, 0, 20462, 1);
+
+#include <vector>
+#include <utility>
+#include <iostream>
+#include <fstream>
+
+void print_qa_xml(std::vector<volk_gnsssdr_test_results_t> results, unsigned int nfails);
+
+int main()
+{
+ bool qa_ret_val = 0;
+
+ float def_tol = 1e-6;
+ lv_32fc_t def_scalar = 327.0;
+ int def_iter = 1;
+ int def_vlen = 131071;
+ bool def_benchmark_mode = true;
+ std::string def_kernel_regex = "";
+
+ volk_gnsssdr_test_params_t test_params(def_tol, def_scalar, def_vlen, def_iter,
+ def_benchmark_mode, def_kernel_regex);
+ std::vector<volk_gnsssdr_test_case_t> test_cases = init_test_list(test_params);
+
+ std::vector<std::string> qa_failures;
+ std::vector<volk_gnsssdr_test_results_t> results;
+ // Test every kernel reporting failures when they occur
+ for(unsigned int ii = 0; ii < test_cases.size(); ++ii) {
+ bool qa_result = false;
+ volk_gnsssdr_test_case_t test_case = test_cases[ii];
+ try {
+ qa_result = run_volk_gnsssdr_tests(test_case.desc(), test_case.kernel_ptr(), test_case.name(),
+ test_case.test_parameters(), &results, test_case.puppet_master_name());
+ }
+ catch(...) {
+ // TODO: what exceptions might we need to catch and how do we handle them?
+ std::cerr << "Exception found on kernel: " << test_case.name() << std::endl;
+ qa_result = false;
+ }
+
+ if(qa_result) {
+ std::cerr << "Failure on " << test_case.name() << std::endl;
+ qa_failures.push_back(test_case.name());
+ }
+ }
+
+ // Generate XML results
+ print_qa_xml(results, qa_failures.size());
+
+ // Summarize QA results
+ std::cerr << "Kernel QA finished: " << qa_failures.size() << " failures out of "
+ << test_cases.size() << " tests." << std::endl;
+ if(qa_failures.size() > 0) {
+ std::cerr << "The following kernels failed QA:" << std::endl;
+ for(unsigned int ii = 0; ii < qa_failures.size(); ++ii) {
+ std::cerr << " " << qa_failures[ii] << std::endl;
+ }
+ qa_ret_val = 1;
+ }
+
+ return qa_ret_val;
+}
+
+/*
+ * This function prints qa results as XML output similar to output
+ * from Junit. For reference output see http://llg.cubic.org/docs/junit/
+ */
+void print_qa_xml(std::vector<volk_gnsssdr_test_results_t> results, unsigned int nfails)
+{
+ std::ofstream qa_file;
+ qa_file.open(".unittest/kernels.xml");
+
+ qa_file << "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" << std::endl;
+ qa_file << "<testsuites name=\"kernels\" " <<
+ "tests=\"" << results.size() << "\" " <<
+ "failures=\"" << nfails << "\" id=\"1\">" << std::endl;
+
+ // Results are in a vector by kernel. Each element has a result
+ // map containing time and arch name with test result
+ for(unsigned int ii=0; ii < results.size(); ++ii) {
+ volk_gnsssdr_test_results_t result = results[ii];
+ qa_file << " <testsuite name=\"" << result.name << "\">" << std::endl;
+
+ std::map<std::string, volk_gnsssdr_test_time_t>::iterator kernel_time_pair;
+ for(kernel_time_pair = result.results.begin(); kernel_time_pair != result.results.end(); ++kernel_time_pair) {
+ volk_gnsssdr_test_time_t test_time = kernel_time_pair->second;
+ qa_file << " <testcase name=\"" << test_time.name << "\" " <<
+ "classname=\"" << result.name << "\" " <<
+ "time=\"" << test_time.time << "\">" << std::endl;
+ if(!test_time.pass)
+ qa_file << " <failure " <<
+ "message=\"fail on arch " << test_time.name << "\">" <<
+ "</failure>" << std::endl;
+ qa_file << " </testcase>" << std::endl;
+ }
+ qa_file << " </testsuite>" << std::endl;
+ }
+
+
+ qa_file << "</testsuites>" << std::endl;
+ qa_file.close();
+
+}
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/CMakeLists.txt b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/CMakeLists.txt
index a7cf1e6..1a3a8c8 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/CMakeLists.txt
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/CMakeLists.txt
@@ -19,7 +19,7 @@
########################################################################
# Install python files and apps
########################################################################
-include(GrPython)
+include(VolkPython)
VOLK_PYTHON_INSTALL(
FILES
@@ -35,4 +35,4 @@ VOLK_PYTHON_INSTALL(
volk_gnsssdr_modtool
DESTINATION ${VOLK_RUNTIME_DIR}
COMPONENT "volk_gnsssdr"
-)
+)
\ No newline at end of file
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/volk_gnsssdr_modtool_generate.py b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/volk_gnsssdr_modtool_generate.py
index a613a21..8928e7c 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/volk_gnsssdr_modtool_generate.py
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/python/volk_gnsssdr_modtool/volk_gnsssdr_modtool_generate.py
@@ -1,9 +1,9 @@
#
-# Copyright 2013 Free Software Foundation, Inc.
+# Copyright (C) 2010-2015 (see AUTHORS file for a list of contributors)
#
-# This file is part of GNU Radio
+# This file is part of GNSS-SDR.
#
-# GNU Radio is free software; you can redistribute it and/or modify
+# GNSS-SDR is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr.tmpl.h b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr.tmpl.h
index a532ffe..283f56d 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr.tmpl.h
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr.tmpl.h
@@ -88,4 +88,5 @@ extern VOLK_API volk_gnsssdr_func_desc_t $(kern.name)_get_func_desc(void);
__VOLK_DECL_END
+
#endif /*INCLUDED_VOLK_GNSSSDR_RUNTIME*/
diff --git a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr_cpu.tmpl.c b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr_cpu.tmpl.c
index 2b9e787..72cbd0f 100644
--- a/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr_cpu.tmpl.c
+++ b/src/algorithms/libs/volk_gnsssdr_module/volk_gnsssdr/tmpl/volk_gnsssdr_cpu.tmpl.c
@@ -19,6 +19,7 @@
#include <volk_gnsssdr/volk_gnsssdr_cpu.h>
#include <volk_gnsssdr/volk_gnsssdr_config_fixed.h>
#include <stdlib.h>
+#include <string.h>
struct VOLK_CPU volk_gnsssdr_cpu;
@@ -30,11 +31,7 @@ struct VOLK_CPU volk_gnsssdr_cpu;
//implement get cpuid for gcc compilers using a system or local copy of cpuid.h
#if defined(__GNUC__)
- #if defined(HAVE_CPUID_H)
- #include <cpuid.h>
- #else
- #include "gcc_x86_cpuid.h"
- #endif
+ #include <cpuid.h>
#define cpuid_x86(op, r) __get_cpuid(op, (unsigned int *)r+0, (unsigned int *)r+1, (unsigned int *)r+2, (unsigned int *)r+3)
/* Return Intel AVX extended CPU capabilities register.
@@ -69,9 +66,20 @@ struct VOLK_CPU volk_gnsssdr_cpu;
#endif //defined(VOLK_CPU_x86)
+static inline unsigned int cpuid_count_x86_bit(unsigned int level, unsigned int count, unsigned int reg, unsigned int bit) {
+#if defined(VOLK_CPU_x86)
+ unsigned int regs[4];
+ __cpuid_count(level, count, regs[0], regs[1], regs[2], regs[3]);
+ return regs[reg] >> bit & 0x01;
+#else
+ return 0;
+#endif
+}
+
static inline unsigned int cpuid_x86_bit(unsigned int reg, unsigned int op, unsigned int bit) {
#if defined(VOLK_CPU_x86)
unsigned int regs[4];
+ memset(regs, 0, sizeof(unsigned int)*4);
cpuid_x86(op, regs);
return regs[reg] >> bit & 0x01;
#else
@@ -82,6 +90,7 @@ static inline unsigned int cpuid_x86_bit(unsigned int reg, unsigned int op, unsi
static inline unsigned int check_extended_cpuid(unsigned int val) {
#if defined(VOLK_CPU_x86)
unsigned int regs[4];
+ memset(regs, 0, sizeof(unsigned int)*4);
cpuid_x86(0x80000000, regs);
return regs[0] >= val;
#else
@@ -97,6 +106,14 @@ static inline unsigned int get_avx_enabled(void) {
#endif
}
+static inline unsigned int get_avx2_enabled(void) {
+#if defined(VOLK_CPU_x86)
+ return __xgetbv() & 0x6;
+#else
+ return 0;
+#endif
+}
+
//neon detection is linux specific
#if defined(__arm__) && defined(__linux__)
#include <asm/hwcap.h>
@@ -129,14 +146,6 @@ static int has_neon(void){
#endif
}
-static int has_ppc(void){
-#ifdef __PPC__
- return 1;
-#else
- return 0;
-#endif
-}
-
#for $arch in $archs
static int i_can_has_$arch.name (void) {
#for $check, $params in $arch.checks
diff --git a/src/algorithms/tracking/adapters/CMakeLists.txt b/src/algorithms/tracking/adapters/CMakeLists.txt
index 993c578..fe3bd60 100644
--- a/src/algorithms/tracking/adapters/CMakeLists.txt
+++ b/src/algorithms/tracking/adapters/CMakeLists.txt
@@ -23,7 +23,7 @@ endif(ENABLE_CUDA)
set(TRACKING_ADAPTER_SOURCES
galileo_e1_dll_pll_veml_tracking.cc
- galileo_volk_e1_dll_pll_veml_tracking.cc
+ #galileo_volk_e1_dll_pll_veml_tracking.cc
galileo_e1_tcp_connector_tracking.cc
gps_l1_ca_dll_fll_pll_tracking.cc
gps_l1_ca_dll_pll_optim_tracking.cc
diff --git a/src/algorithms/tracking/gnuradio_blocks/CMakeLists.txt b/src/algorithms/tracking/gnuradio_blocks/CMakeLists.txt
index 6e9029e..6a4bc62 100644
--- a/src/algorithms/tracking/gnuradio_blocks/CMakeLists.txt
+++ b/src/algorithms/tracking/gnuradio_blocks/CMakeLists.txt
@@ -25,7 +25,7 @@ endif(ENABLE_CUDA)
set(TRACKING_GR_BLOCKS_SOURCES
galileo_e1_dll_pll_veml_tracking_cc.cc
- galileo_volk_e1_dll_pll_veml_tracking_cc.cc
+ #galileo_volk_e1_dll_pll_veml_tracking_cc.cc
galileo_e1_tcp_connector_tracking_cc.cc
gps_l1_ca_dll_fll_pll_tracking_cc.cc
gps_l1_ca_dll_pll_optim_tracking_cc.cc
diff --git a/src/core/receiver/gnss_block_factory.cc b/src/core/receiver/gnss_block_factory.cc
index c5c74f3..198a36d 100644
--- a/src/core/receiver/gnss_block_factory.cc
+++ b/src/core/receiver/gnss_block_factory.cc
@@ -83,7 +83,7 @@
#include "gps_l1_ca_dll_fll_pll_tracking.h"
#include "gps_l1_ca_tcp_connector_tracking.h"
#include "galileo_e1_dll_pll_veml_tracking.h"
-#include "galileo_volk_e1_dll_pll_veml_tracking.h"
+//#include "galileo_volk_e1_dll_pll_veml_tracking.h"
#include "galileo_e1_tcp_connector_tracking.h"
#include "galileo_e5a_dll_pll_tracking.h"
#include "gps_l2_m_dll_pll_tracking.h"
@@ -1342,12 +1342,12 @@ std::unique_ptr<GNSSBlockInterface> GNSSBlockFactory::GetBlock(
out_streams, queue));
block = std::move(block_);
}
- else if (implementation.compare("Galileo_volk_E1_DLL_PLL_VEML_Tracking") == 0)
- {
- std::unique_ptr<GNSSBlockInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
- out_streams, queue));
- block = std::move(block_);
- }
+// else if (implementation.compare("Galileo_volk_E1_DLL_PLL_VEML_Tracking") == 0)
+// {
+// std::unique_ptr<GNSSBlockInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
+// out_streams, queue));
+// block = std::move(block_);
+// }
else if (implementation.compare("Galileo_E1_TCP_CONNECTOR_Tracking") == 0)
{
std::unique_ptr<GNSSBlockInterface> block_(new GalileoE1TcpConnectorTracking(configuration.get(), role, in_streams,
@@ -1613,12 +1613,12 @@ std::unique_ptr<TrackingInterface> GNSSBlockFactory::GetTrkBlock(
out_streams, queue));
block = std::move(block_);
}
- else if (implementation.compare("Galileo_Volk_E1_DLL_PLL_VEML_Tracking") == 0)
- {
- std::unique_ptr<TrackingInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
- out_streams, queue));
- block = std::move(block_);
- }
+// else if (implementation.compare("Galileo_Volk_E1_DLL_PLL_VEML_Tracking") == 0)
+// {
+// std::unique_ptr<TrackingInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
+// out_streams, queue));
+// block = std::move(block_);
+// }
else if (implementation.compare("Galileo_E1_TCP_CONNECTOR_Tracking") == 0)
{
std::unique_ptr<TrackingInterface> block_(new GalileoE1TcpConnectorTracking(configuration.get(), role, in_streams,
@@ -1631,12 +1631,12 @@ std::unique_ptr<TrackingInterface> GNSSBlockFactory::GetTrkBlock(
out_streams, queue));
block = std::move(block_);
}
- else if (implementation.compare("Galileo_volk_E1_DLL_PLL_VEML_Tracking") == 0)
- {
- std::unique_ptr<TrackingInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
- out_streams, queue));
- block = std::move(block_);
- }
+// else if (implementation.compare("Galileo_volk_E1_DLL_PLL_VEML_Tracking") == 0)
+// {
+// std::unique_ptr<TrackingInterface> block_(new GalileoVolkE1DllPllVemlTracking(configuration.get(), role, in_streams,
+// out_streams, queue));
+// block = std::move(block_);
+// }
else if (implementation.compare("GPS_L2_M_DLL_PLL_Tracking") == 0)
{
std::unique_ptr<TrackingInterface> block_(new GpsL2MDllPllTracking(configuration.get(), role, in_streams,
diff --git a/src/core/system_parameters/rtcm.h b/src/core/system_parameters/rtcm.h
index e8f0b51..2e7bd4e 100644
--- a/src/core/system_parameters/rtcm.h
+++ b/src/core/system_parameters/rtcm.h
@@ -696,7 +696,7 @@ private:
{
std::string message;
Rtcm_Message msg;
- queue_->wait_and_pop(message);
+ queue_->wait_and_pop(message); //message += '\n';
if(message.compare("Goodbye") == 0) break;
const char *char_msg = message.c_str();
msg.body_length(message.length());
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-hamradio/gnss-sdr.git
More information about the pkg-hamradio-commits
mailing list