Martin Kroeker
|
4297e2ed84
|
fix shgemm parameter references in arm64 branch
|
6 years ago |
Martin Kroeker
|
254a934b57
|
ifdef another group of shgemm parameters
|
6 years ago |
Martin Kroeker
|
9acf45c675
|
Fix overlooked shgemm parameters
|
6 years ago |
Martin Kroeker
|
8d4042d897
|
Make shgemm parameters conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
33059ad1de
|
make bfloat16 functions conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
1377810961
|
fix endif
|
6 years ago |
Martin Kroeker
|
b2f6f76a5a
|
Pass BUILD_HALF as a compiler define for dynamic_arch builds
|
6 years ago |
Martin Kroeker
|
84e5b0c4f8
|
typo
|
6 years ago |
Martin Kroeker
|
75e0495a75
|
Make shgemm kernels conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
fd267b58b2
|
make shgemm kernels conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
f881c697fb
|
pass the BUILD_HALF option to gensymbol
|
6 years ago |
Martin Kroeker
|
48e26bc317
|
make bfloat16 functions conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
34e64d57ab
|
make shgemm functions conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
45881fab58
|
make shgemm functions conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
7bf1865656
|
make building the bfloat16 functions conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
3c37071eef
|
make bfloat16 kernels conditional on BUILD_HALF
|
6 years ago |
Martin Kroeker
|
5d58b11101
|
Merge pull request #52 from xianyi/develop
rebase
|
6 years ago |
Martin Kroeker
|
d394d4e677
|
Merge pull request #2585 from martin-frbg/mips64fix
Increase default BUFFER_SIZE on MIPS64
|
6 years ago |
Martin Kroeker
|
2d89603e9d
|
Increase BUFFER_SIZE on mips64 to match SGEMM parameters
|
6 years ago |
Martin Kroeker
|
26bc15258a
|
Merge pull request #51 from xianyi/develop
rebase
|
6 years ago |
Martin Kroeker
|
141998dce2
|
Merge pull request #2584 from martin-frbg/issue2583
[WIP] Have CMAKE parse conditional lines in KERNEL files
|
6 years ago |
Martin Kroeker
|
3bd56846bb
|
Silence a debug message
|
6 years ago |
Martin Kroeker
|
e7bbdfdf84
|
Have CMAKE parse conditional lines in KERNEL files
Supports ifeq and ifneq, but requires both to have an else branch
|
6 years ago |
Martin Kroeker
|
b6795db731
|
Merge pull request #2582 from martin-frbg/mips32fix
Increase BUFFER_SIZE on MIPS32 to accomodate SGEMM requirements
|
6 years ago |
Martin Kroeker
|
5e0dbf8dfe
|
Increase default BUFFER_SIZE to accomodate SGEMM parameters
in response to compile-time warning from #2551
|
6 years ago |
Martin Kroeker
|
955d73127f
|
Merge pull request #50 from xianyi/develop
rebase
|
6 years ago |
Martin Kroeker
|
a8c1bea7ae
|
Merge pull request #2581 from martin-frbg/raji
Fix travis configuration and update CONTRIBUTORS.md
|
6 years ago |
Martin Kroeker
|
e43b49e064
|
Drop the set -e from travis scripts
|
6 years ago |
Martin Kroeker
|
3e28db7f38
|
Update CONTRIBUTORS.md
|
6 years ago |
Martin Kroeker
|
4b69ee31af
|
Merge pull request #2580 from martin-frbg/issue2538-3
Increase POWER8 ZGEMM_R and use same R values for POWER9
|
6 years ago |
Martin Kroeker
|
03ff213c51
|
Increase POWER8 ZGEMM_R and use same R values for POWER9
fixes lapack-test zger failures seen in #2299 after application of my PR #2551
|
6 years ago |
Martin Kroeker
|
299d1c8de0
|
Merge pull request #2578 from martin-frbg/issue2576
Quote getarch include paths in prebuild.cmake
|
6 years ago |
Martin Kroeker
|
70869d571f
|
Quote include paths for getarch to protect any embedded spaces
|
6 years ago |
Martin Kroeker
|
cba87222b2
|
Merge pull request #49 from xianyi/develop
rebase
|
6 years ago |
Martin Kroeker
|
f80dd2151e
|
xcode 11.4.1 for homebrew ?
|
6 years ago |
Martin Kroeker
|
4412ee1754
|
Switch homebrew build env to new xcode 11.4
default 11.3.1 in the github image is causing brew to fail with "outdated xcode" message
|
6 years ago |
Martin Kroeker
|
f6104b68c1
|
Merge pull request #2571 from martin-frbg/issue2299
Work around IDAMAX/IZAMAX bugs on POWER8BE with ELFv2 FreeBSD
|
6 years ago |
Martin Kroeker
|
84f2c71e93
|
Merge pull request #2573 from martin-frbg/issue2572
Enable cblas interfaces to GEMM3M in CMAKE builds
|
6 years ago |
Martin Kroeker
|
06208c8d01
|
Limit this fix to ELFv2 builds
|
6 years ago |
Martin Kroeker
|
c90b28dee6
|
Export ELF_VERSION for use in powerpc kernel configurations
|
6 years ago |
Martin Kroeker
|
6275b43918
|
Avoid duplicate printout of byte order and report ELF_VERSION
|
6 years ago |
Martin Kroeker
|
2db5178e2d
|
enable cblas interfaces to GEMM3M in CMAKE builds
|
6 years ago |
Martin Kroeker
|
57549f5c92
|
Merge pull request #2569 from martin-frbg/issue2472-2
Fix linker option passing for MSVS and ReLAPACK
|
6 years ago |
Martin Kroeker
|
f5c4c28b98
|
Work around POWER8BE bugs on FreeBSD (ELFv2)
for #2299
|
6 years ago |
Martin Kroeker
|
239282d5e2
|
Use CMAKE_SHARED_LINKER_FLAGS to pass MSVC linker option
target_link_libraries does not work here according to issue 2472
|
6 years ago |
Martin Kroeker
|
568674477c
|
Merge pull request #48 from xianyi/develop
rebase
|
6 years ago |
Martin Kroeker
|
fa42588e1f
|
Merge pull request #2565 from martin-frbg/mips24k
Support MIPS32 24K family as P5600
|
6 years ago |
Martin Kroeker
|
8a6d26458b
|
Merge pull request #2559 from RajalakshmiSR/shgemm
Add half precision gemm for bfloat16 in OpenBLAS
|
6 years ago |
Martin Kroeker
|
db86f516b9
|
Merge pull request #2568 from martin-frbg/azure-win
Add a Windows/CL build job to the Azure CI
|
6 years ago |
Martin Kroeker
|
aec353b5a7
|
Add a Windows/CL build to the Azure Ci configuration
|
6 years ago |