[clblas] 23/67: Merge pull request #138 from guacamoleo/develop-squash2
Ghislain Vaillant
ghisvail-guest at moszumanska.debian.org
Tue Oct 27 08:02:11 UTC 2015
This is an automated email from the git hooks/post-receive script.
ghisvail-guest pushed a commit to branch master
in repository clblas.
commit 33c5ca0d1432146280c0f4795b2619a4317af81f
Merge: f496d1c 40098f4
Author: Timmy <timmy.liu at amd.com>
Date: Thu Sep 10 15:21:00 2015 -0500
Merge pull request #138 from guacamoleo/develop-squash2
AutoGemm main merge
.gitignore | 3 +
doc/performance/clBLAS_2.6.0/S9150/dtrsm_192.csv | 60 +-
doc/performance/clBLAS_2.6.0/S9150/sgemm_32.csv | 360 ++---
doc/performance/cuBLAS_7.0/Tesla_K40/dtrsm.csv | 60 +-
doc/performance/cuBLAS_7.0/Tesla_K40/sgemm.csv | 360 ++---
src/CMakeLists.txt | 85 +-
src/client/clfunc_common.hpp | 18 +-
src/client/clfunc_xgemm.hpp | 192 ++-
src/client/clfunc_xgemv.hpp | 22 +-
src/client/clfunc_xger.hpp | 16 +-
src/client/clfunc_xgerc.hpp | 12 +-
src/client/clfunc_xgeru.hpp | 12 +-
src/client/clfunc_xhemm.hpp | 34 +-
src/client/clfunc_xhemv.hpp | 12 +-
src/client/clfunc_xher.hpp | 10 +-
src/client/clfunc_xher2.hpp | 12 +-
src/client/clfunc_xher2k.hpp | 20 +-
src/client/clfunc_xherk.hpp | 20 +-
src/client/clfunc_xsymm.hpp | 58 +-
src/client/clfunc_xsymv.hpp | 12 +-
src/client/clfunc_xsyr.hpp | 10 +-
src/client/clfunc_xsyr2.hpp | 12 +-
src/client/clfunc_xsyr2k.hpp | 34 +-
src/client/clfunc_xsyrk.hpp | 32 +-
src/client/clfunc_xtrmm.hpp | 48 +-
src/client/clfunc_xtrmv.hpp | 14 +-
src/client/clfunc_xtrsm.hpp | 50 +-
src/client/clfunc_xtrsv.hpp | 14 +-
src/client/client.cpp | 10 +-
src/library/CMakeLists.txt | 400 +++++-
src/library/blas/AutoGemm/.gitignore | 4 +
src/library/blas/AutoGemm/AutoGemm.py | 47 +
src/library/blas/AutoGemm/AutoGemmParameters.py | 149 +++
.../AutoGemmTools/AutoGemmPreCompileKernels.cpp | 924 +++++++++++++
.../blas/AutoGemm/AutoGemmTools/AutoGemmUtil.h | 793 +++++++++++
.../AutoGemm/AutoGemmTools/ProfileAutoGemm.cpp | 1378 ++++++++++++++++++++
.../blas/AutoGemm/AutoGemmTools/TestAutoGemm.cpp | 995 ++++++++++++++
src/library/blas/AutoGemm/Common.py | 60 +
src/library/blas/AutoGemm/Includes.py | 458 +++++++
src/library/blas/AutoGemm/KernelOpenCL.py | 549 ++++++++
src/library/blas/AutoGemm/KernelParameters.py | 253 ++++
src/library/blas/AutoGemm/KernelSelection.py | 683 ++++++++++
src/library/blas/AutoGemm/KernelsToPreCompile.py | 91 ++
src/library/blas/AutoGemm/README.txt | 0
.../UserGemmKernelSources/UserGemmClKernels.h | 18 +
.../UserGemmKernelSourceIncludes.cpp | 57 +
.../UserGemmKernelSourceIncludes.h | 80 ++
.../dgemm_Col_NN_B0_MX048_NX048_KX08_src.cpp | 203 +++
.../dgemm_Col_NN_B1_MX048_NX048_KX08_src.cpp | 203 +++
.../dgemm_Col_NT_B0_MX048_NX048_KX08_src.cpp | 196 +++
.../dgemm_Col_NT_B1_MX048_NX048_KX08_src.cpp | 193 +++
.../dgemm_Col_TN_B0_MX048_NX048_KX08_src.cpp | 195 +++
.../dgemm_Col_TN_B1_MX048_NX048_KX08_src.cpp | 195 +++
.../sgemm_Col_NN_B0_MX032_NX032_KX16_src.cpp | 129 ++
.../sgemm_Col_NN_B0_MX064_NX064_KX16_src.cpp | 160 +++
.../sgemm_Col_NN_B0_MX096_NX096_KX16_src.cpp | 208 +++
...sgemm_Col_NN_B1_MX032_NX032_KX16_BRANCH_src.cpp | 149 +++
.../sgemm_Col_NN_B1_MX032_NX032_KX16_src.cpp | 129 ++
.../sgemm_Col_NN_B1_MX064_NX064_KX16_src.cpp | 161 +++
.../sgemm_Col_NN_B1_MX096_NX096_KX16_src.cpp | 207 +++
.../sgemm_Col_NT_B0_MX032_NX032_KX16_src.cpp | 126 ++
.../sgemm_Col_NT_B0_MX064_NX064_KX16_src.cpp | 165 +++
.../sgemm_Col_NT_B0_MX096_NX096_KX16_src.cpp | 210 +++
...sgemm_Col_NT_B1_MX032_NX032_KX16_BRANCH_src.cpp | 148 +++
...sgemm_Col_NT_B1_MX032_NX032_KX16_SINGLE_src.cpp | 158 +++
.../sgemm_Col_NT_B1_MX032_NX032_KX16_src.cpp | 126 ++
.../sgemm_Col_NT_B1_MX032_NX064_KX16_ROW_src.cpp | 161 +++
.../sgemm_Col_NT_B1_MX064_NX032_KX16_COL_src.cpp | 157 +++
.../sgemm_Col_NT_B1_MX064_NX064_KX16_src.cpp | 160 +++
.../sgemm_Col_NT_B1_MX096_NX096_KX16_src.cpp | 208 +++
.../sgemm_Col_NT_B1_MX128_NX128_KX16_src.cpp | 290 ++++
.../sgemm_Col_TN_B0_MX032_NX032_KX16_src.cpp | 128 ++
.../sgemm_Col_TN_B0_MX064_NX064_KX16_src.cpp | 165 +++
.../sgemm_Col_TN_B0_MX096_NX096_KX16_src.cpp | 209 +++
...sgemm_Col_TN_B1_MX032_NX032_KX16_BRANCH_src.cpp | 148 +++
.../sgemm_Col_TN_B1_MX032_NX032_KX16_src.cpp | 127 ++
.../sgemm_Col_TN_B1_MX064_NX064_KX16_src.cpp | 165 +++
.../sgemm_Col_TN_B1_MX096_NX096_KX16_src.cpp | 209 +++
src/library/blas/include/xgemm.h | 39 +
src/library/blas/specialCases/GemmSpecialCases.cpp | 829 ++++++++++++
.../blas/specialCases/include/GemmSpecialCases.h | 42 +
src/library/blas/xgemm.cc | 855 ++++++++----
src/tests/CMakeLists.txt | 2 +-
src/tests/common.cpp | 29 +-
src/tests/correctness/corr-gemm.cpp | 12 +-
src/tests/include/gemm.h | 6 +-
86 files changed, 14693 insertions(+), 1050 deletions(-)
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-science/packages/clblas.git
More information about the debian-science-commits
mailing list