[libclc] annotated tag upstream/0.2.0+git20171106 created (now 4fa8953)
Andreas Boll
aboll-guest at moszumanska.debian.org
Mon Nov 6 15:12:13 UTC 2017
This is an automated email from the git hooks/post-receive script.
aboll-guest pushed a change to annotated tag upstream/0.2.0+git20171106
in repository libclc.
at 4fa8953 (tag)
tagging f07a10170a91a461e5ea1579ccb025526a372b7a (commit)
replaces upstream/0.2.0+git20170330
tagged by Andreas Boll
on Mon Nov 6 15:19:26 2017 +0100
- Log -----------------------------------------------------------------
upstream 0.2.0+git20171106
Aaron Watry (5):
Add halfN types and enable fp16 when generating builtin declarations
relational: Implement shuffle builtin
relational: Implement shuffle2 builtin
integer: Add popcount implementation using ctpop intrinsic
Add native_recip(x) as ((1)/(x))
Jan Vesely (73):
generic: add missing get_work_dim include
add __kernel_exec macros
configure.py: Make python3 friendly
configure.py: Drop explicit import of int builtin
amdgcn: Implement {read_,write_,}mem_fence builtin
amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier
Fixup clc.h comment
r600: Cleanup barrier implementation.
amdgcn,waitcnt: Add datalayout info
configure.py: Simplify compatibility sources
vstore: Cleanup and add vstore(half)
Implement vload_half{,n} and vload(half)
Add travis CI configuration file
Implement cl_khr_int64_base_atomics builtins
Implement cl_khr_int64_extended_atomics builtins
prepare_builtins: Fix compile breakage with older LLVM
Rework atomic ops to use clang builtins rather than llvm asm
Add missing HAVE_LLVM define to fix build with latest llvm
Restore support for llvm-3.9
travis: add build using llvm-3.9
geometric: geometric functions are only supported for vector lengths <=4
Add script to check for unresolved function calls
travis: Check built libraries on llvm-3.9
Fix amdgcn-amdhsa on llvm-3.9
integer/clz: Use clang builtin instead of llvm asm
integer/add_sat: Use clang builtin instead of llvm asm
integer/sub_sat: Use clang builtin instead of llvm asm
configure: Fix handling of directories with compats only source lists
ldexp: Fix double precision function return type
math/binary_decl.inc: Do not declare mixed float/double functions
math/nextafter: Use custom declaration inc file
Do not include clc_nextafter header globally
ptx: Use __clc_nextafter to implement nextafter
check_external_calls.sh: Print number of calls in tested file.
travis: Make sure we report failure even if only earlier checked files fail
Make image builtins r600/llvm-3.9 only
travis: Enable external function call checks on llvm-{4,5}
travis: enable checks of nvptx libraries
r600: Add missing datalayout to .ll files
amdgcn: Add missing datalayout info to .ll files
shared: Implement aligned vector loads (vloada_half)
shared: Implement aligned vector stores (vstorea_half)
amdgpu/math: Don't use llvm instrinsic for native_log
math: Implement native_log10
acos: Use unary_decl instead of custom inc file
acosh: Use unary_decl instead of custom inc file
acospi: Use unary_decl instead of custom inc file
asin: Use unary_decl instead of custom inc file
asinh: Use unary_dec instead of custom inc file
asinpi: Use unary_decl instead of custom inc file
atan: Use unary_decl instead of custom inc file
atanh: Use unary_decl instead of custom inc file
atanpi: Use unary_decl instead of custom inc file
cbrt: Use unary_decl instead of custom inc file
cos: Use unary_decl instead of custom inc file
cosh: Use unary_decl instead of custom inc file
cospi: Use unary_decl instead of custom inc file
exp2: Use unary_decl instead of custom inc file
lgamma: Use unary_decl instead of custom inc file
log1p: Use unary_decl instead of custom inc file
log2: Use unary_decl instead of custom inc file
logb: Use unary_decl instead of custom inc file
log: Use unary_decl instead of custom inc file
native_log10: Use unary_decl instead of custom inc file
native_log2: Use unary_decl instead of custom inc file
native_log: Use unary_decl instead of custom inc file
sin: Use unary_decl instead of custom inc file
sinh: Use unary_decl instead of custom inc file
sinpi: Use unary_decl instead of custom inc file
sqrt: Use unary_decl instead of custom inc file
tan: Use unary_decl instead of custom inc file
tanh: Use unary_decl instead of custom inc file
tgamma: Use unary_decl instead of custom inc file
Jeroen Ketema (7):
Do no circularly define NULL
Let get_work_dim take exactly 0 arguments
Add vstore_half helpers for ptx
Add vload_half helpers for ptx
Delete empy directory
Make ptx barrier work irrespective of the cl_mem_fence_flags
Implement mem_fence on ptx
Reid Kleckner (1):
[Support] Rename tool_output_file to ToolOutputFile, NFC
-----------------------------------------------------------------------
This annotated tag includes the following new commits:
new 1cb3fbf generic: add missing get_work_dim include
new 7331b0a add __kernel_exec macros
new 3078dd1 configure.py: Make python3 friendly
new b73df29 configure.py: Drop explicit import of int builtin
new 6633bab amdgcn: Implement {read_,write_,}mem_fence builtin
new 7d4c1a3 amdgcn: rewrite barrier() using fence and clang __builtin_amdgcn_s_barrier
new 84fe1c0 Add halfN types and enable fp16 when generating builtin declarations
new 66361b6 relational: Implement shuffle builtin
new 86edeb7 relational: Implement shuffle2 builtin
new c22cd31 Fixup clc.h comment
new da9472b r600: Cleanup barrier implementation.
new 58f9eef amdgcn,waitcnt: Add datalayout info
new 95aafb1 configure.py: Simplify compatibility sources
new 52106a2 vstore: Cleanup and add vstore(half)
new 424b23a Implement vload_half{,n} and vload(half)
new 3ab9165 integer: Add popcount implementation using ctpop intrinsic
new ab060bb Add native_recip(x) as ((1)/(x))
new b9d0d3f Add travis CI configuration file
new 7dd7811 Implement cl_khr_int64_base_atomics builtins
new fb79355 Implement cl_khr_int64_extended_atomics builtins
new df9db2a [Support] Rename tool_output_file to ToolOutputFile, NFC
new 1f54d3e prepare_builtins: Fix compile breakage with older LLVM
new 80aa034 Rework atomic ops to use clang builtins rather than llvm asm
new 81f74b2 Add missing HAVE_LLVM define to fix build with latest llvm
new 419632b Restore support for llvm-3.9
new b559ed8 travis: add build using llvm-3.9
new 1595f22 geometric: geometric functions are only supported for vector lengths <=4
new 7f08009 Add script to check for unresolved function calls
new bdd9d71 travis: Check built libraries on llvm-3.9
new 0c31bd5 Fix amdgcn-amdhsa on llvm-3.9
new 5a3d04c Do no circularly define NULL
new d36efd2 Let get_work_dim take exactly 0 arguments
new 0ad45e2 integer/clz: Use clang builtin instead of llvm asm
new a9c272b integer/add_sat: Use clang builtin instead of llvm asm
new 028b813 integer/sub_sat: Use clang builtin instead of llvm asm
new ad4ee18 Add vstore_half helpers for ptx
new 1440465 Add vload_half helpers for ptx
new 8043f28 configure: Fix handling of directories with compats only source lists
new 33f76ff Delete empy directory
new afe1e6b ldexp: Fix double precision function return type
new a618e78 math/binary_decl.inc: Do not declare mixed float/double functions
new d7e6160 math/nextafter: Use custom declaration inc file
new 9251ce4 Do not include clc_nextafter header globally
new 129de63 ptx: Use __clc_nextafter to implement nextafter
new 4962167 check_external_calls.sh: Print number of calls in tested file.
new 50e9302 travis: Make sure we report failure even if only earlier checked files fail
new ba746aa Make ptx barrier work irrespective of the cl_mem_fence_flags
new 7b3a840 Implement mem_fence on ptx
new b9687f1 Make image builtins r600/llvm-3.9 only
new 2bb15f4 travis: Enable external function call checks on llvm-{4,5}
new b61116b travis: enable checks of nvptx libraries
new 404e255 r600: Add missing datalayout to .ll files
new fff6e78 amdgcn: Add missing datalayout info to .ll files
new c3e3853 shared: Implement aligned vector loads (vloada_half)
new fabea1e shared: Implement aligned vector stores (vstorea_half)
new 93364d6 amdgpu/math: Don't use llvm instrinsic for native_log
new 2930d00 math: Implement native_log10
new a6cce07 acos: Use unary_decl instead of custom inc file
new 89869f4 acosh: Use unary_decl instead of custom inc file
new 5233091 acospi: Use unary_decl instead of custom inc file
new c619fd4 asin: Use unary_decl instead of custom inc file
new 681ea90 asinh: Use unary_dec instead of custom inc file
new ec4caed asinpi: Use unary_decl instead of custom inc file
new 9c04148 atan: Use unary_decl instead of custom inc file
new 9f34fa3 atanh: Use unary_decl instead of custom inc file
new 6fb1f75 atanpi: Use unary_decl instead of custom inc file
new 8c7c865 cbrt: Use unary_decl instead of custom inc file
new ed8ed00 cos: Use unary_decl instead of custom inc file
new 4047763 cosh: Use unary_decl instead of custom inc file
new f6ea0be cospi: Use unary_decl instead of custom inc file
new e3dbfa9 exp2: Use unary_decl instead of custom inc file
new 31b2940 lgamma: Use unary_decl instead of custom inc file
new 2342d15 log1p: Use unary_decl instead of custom inc file
new 6e2bc07 log2: Use unary_decl instead of custom inc file
new b985a2a logb: Use unary_decl instead of custom inc file
new 70bf547 log: Use unary_decl instead of custom inc file
new 8289f8c native_log10: Use unary_decl instead of custom inc file
new 397331d native_log2: Use unary_decl instead of custom inc file
new 998ab5c native_log: Use unary_decl instead of custom inc file
new a07ec9d sin: Use unary_decl instead of custom inc file
new 5ccaeab sinh: Use unary_decl instead of custom inc file
new 8bd387e sinpi: Use unary_decl instead of custom inc file
new 12aa25f sqrt: Use unary_decl instead of custom inc file
new 26a9203 tan: Use unary_decl instead of custom inc file
new 7931965 tanh: Use unary_decl instead of custom inc file
new f07a101 tgamma: Use unary_decl instead of custom inc file
The 86 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "adds" were already present in the repository and have only
been added to this reference.
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-opencl/libclc.git
More information about the Pkg-opencl-commits
mailing list