Chip-Kerchner
|
99384933ff
|
Revert "Merge pull request #4532 from austinpagan/cgemm_zgemm_c_code"
This reverts commit accea15551 , reversing
changes made to b925353006 .
|
2024-03-01 07:57:39 -06:00 |
Chip-Kerchner
|
edb7ab5ccf
|
Merge branch 'develop' of https://github.com/openmathlib/openblas into develop
|
2024-03-01 07:43:41 -06:00 |
shivammonaka
|
d49ebc54e1
|
Merge branch 'shivam-develop' into shivam-Locks
|
2024-02-29 11:58:14 +05:30 |
shivammonaka
|
bc191015e3
|
Using OpenMP locks with NUM_PARALLEL
|
2024-02-29 11:47:05 +05:30 |
Martin Kroeker
|
577d480c62
|
Merge pull request #4529 from ErnstPeng/feature-branch
Optimized sgemv and dgemv kernel LSX for LoongArch
|
2024-02-28 13:49:54 +01:00 |
pengxu
|
b2db064285
|
Optimized sgemv and dgemv kernel LSX for LoongArch
|
2024-02-28 18:07:27 +08:00 |
Martin Kroeker
|
cfbb701497
|
Merge pull request #4536 from XiWeiGu/loongarch64-cgemv-zgemv-opt
Loongarch64 cgemv zgemv opt
|
2024-02-28 10:15:34 +01:00 |
gxw
|
8e05c053be
|
LoongArch64:Fixed the failed test cases test_{c/z}gemv_n in test_extensions
|
2024-02-27 22:19:26 -05:00 |
gxw
|
3f22fc2233
|
LoongArch64: Add zgemv LSX opt
|
2024-02-27 22:19:04 -05:00 |
gxw
|
c508a10cf2
|
LoongArch64: Add cgemv LSX opt
|
2024-02-27 22:17:30 -05:00 |
Martin Kroeker
|
5fbe25954b
|
Merge pull request #4534 from martin-frbg/issue4528
Omit redundant prefixes or suffixes in library naming
|
2024-02-27 22:29:44 +01:00 |
Martin Kroeker
|
accea15551
|
Merge pull request #4532 from austinpagan/cgemm_zgemm_c_code
Cgemm zgemm c code
|
2024-02-27 22:07:07 +01:00 |
Martin Kroeker
|
d1409407a0
|
Omit redundant prefixes or suffixes in library naming
|
2024-02-27 21:05:59 +01:00 |
Martin Kroeker
|
b925353006
|
Merge pull request #4533 from martin-frbg/fixup4501
CMake: add option for building benchmarks and handle their dependencies
|
2024-02-27 19:55:39 +01:00 |
Martin Kroeker
|
cfc28c586e
|
Exclude LAPACK testsuite and LAPACK-dependent benchmarks in no-LAPACK builds
|
2024-02-27 19:55:12 +01:00 |
Martin Kroeker
|
4266b39304
|
Make building the benchmarks optional and handle dependency on other options
|
2024-02-27 17:52:45 +01:00 |
Martin Kroeker
|
96e4218daf
|
Merge pull request #4501 from dmikushin/add-benchmarks-to-cmake
Adding basic support of benchmarks into CMake
|
2024-02-27 16:25:04 +01:00 |
Martin Kroeker
|
5a57cbf92d
|
Merge pull request #4531 from martin-frbg/issue4530
Fix erroneous mapping of Z13 SUM kernels to ASUM
|
2024-02-27 13:10:40 +01:00 |
Martin Kroeker
|
8e872a91a9
|
Fix erroneous mapping of SUM kernels to ASUM
|
2024-02-27 11:28:50 +01:00 |
Martin Kroeker
|
608effee7b
|
Merge pull request #4524 from martin-frbg/test3m
Enable GEMM3M tests when the architecture supports GEMM3M
|
2024-02-27 10:39:28 +01:00 |
Martin Kroeker
|
f81c1d4b59
|
Fix portability problem
|
2024-02-27 07:19:52 +01:00 |
Martin Kroeker
|
f7ffab870b
|
fix missing malloc
|
2024-02-26 23:03:10 +01:00 |
Martin Kroeker
|
38283f678e
|
Fix portability problems
|
2024-02-26 22:22:48 +01:00 |
Chip-Kerchner
|
ac08e3148d
|
Remove max num threads in AIX build. Use MAX_NB_JOBS instead.
|
2024-02-26 14:57:53 -06:00 |
Martin Kroeker
|
28f151808e
|
Avoid overriding the global USE_GEMM3M
|
2024-02-26 21:01:46 +01:00 |
Martin Kroeker
|
5d929d2706
|
avoid overriding the global USE_GEMM3M
|
2024-02-26 21:00:57 +01:00 |
Chip-Kerchner
|
ccc7bfa1f3
|
Merge branch 'develop' of github.com:ChipKerchner/OpenBLAS into develop
|
2024-02-26 12:47:51 -06:00 |
Chip-Kerchner
|
3e030cc5fe
|
Fix LAPACK unit testing build issues. Limit AIX builds to 32 threads (to eliminate failures of some systems).
|
2024-02-26 12:46:05 -06:00 |
Martin Kroeker
|
a1ec94c258
|
Readd proper f2c'd sources for the GEMM3M tests
|
2024-02-26 17:46:07 +01:00 |
Martin Kroeker
|
175e357f5d
|
run apt-get update before fetching Ubuntu packages
|
2024-02-26 14:19:50 +01:00 |
Martin Kroeker
|
ea167328f1
|
Add f2c-converted sources for GEMM3M tests
|
2024-02-26 14:14:58 +01:00 |
Martin Kroeker
|
6699227d45
|
Merge pull request #4525 from XiWeiGu/loongarch64_fixed_kernel_regress_skx_avx
LoongArch64: Fixed utest kernel_regress:skx_avx
|
2024-02-26 09:49:34 +01:00 |
Martin Kroeker
|
5aaeca2896
|
fix name
|
2024-02-26 09:26:14 +01:00 |
gxw
|
8dea25ffff
|
LoongArch64: Fixed utest kernel_regress:skx_avx
|
2024-02-26 02:04:37 -05:00 |
Martin Kroeker
|
87dd1c710e
|
fix conditional gemm3m build
|
2024-02-26 07:37:30 +01:00 |
Martin Kroeker
|
ba201c1939
|
Enable GEMM3M tests on supported platforms
|
2024-02-25 23:39:24 +01:00 |
Martin Kroeker
|
0ce794f0c3
|
Enable GEMM3M tests on supported platforms
|
2024-02-25 23:38:36 +01:00 |
Martin Kroeker
|
cb8131cfd9
|
Merge pull request #4499 from kseniyazaytseva/new-tests
Tests for BLAS-like and BLAS API
|
2024-02-25 22:40:59 +01:00 |
Martin Kroeker
|
07e62a4619
|
Merge pull request #4523 from martin-frbg/gemmtstack
Fix a potential buffer overflow in GEMMT
|
2024-02-25 21:26:21 +01:00 |
Martin Kroeker
|
baf88564bc
|
Fix potential buffer overflow
|
2024-02-25 19:23:41 +01:00 |
Martin Kroeker
|
f860e82166
|
Merge pull request #4522 from martin-frbg/arm64scsum
Fix SCSUM on ARMV8 and add optimized CSUM/ZSUM for ARMV8SVE
|
2024-02-25 19:20:11 +01:00 |
Martin Kroeker
|
7d506984fa
|
fix assignment of default CSUM kernel
|
2024-02-25 17:57:11 +01:00 |
Martin Kroeker
|
12787775d9
|
add csum/zsum kernels (trivially derived from the asum ones)s)
|
2024-02-25 17:55:36 +01:00 |
Martin Kroeker
|
1c93e6a5e4
|
Merge pull request #4521 from martin-frbg/fixczsum
Fix BLAS extension kernels for SCSUM and DZSUM on x86_64 targets
|
2024-02-25 10:46:51 +01:00 |
Martin Kroeker
|
8f8ef3492a
|
Add CSUM and ZSUM kernels (trivially derived from their existing ASUM counterparts)
|
2024-02-24 23:57:50 +01:00 |
Martin Kroeker
|
be5e18c6f9
|
Add kernel definitions for CSUM and ZSUM
|
2024-02-24 23:55:43 +01:00 |
Martin Kroeker
|
5403900539
|
Merge pull request #4520 from frjohnst/new_branch
fix conlict between PR 4515 and AIX shared obj support
|
2024-02-23 20:58:27 +01:00 |
frjohnst
|
bdaa6705ca
|
fix conlict between PR 4515 and AIX shared obj support
|
2024-02-23 10:20:48 -05:00 |
Martin Kroeker
|
0d976acdd7
|
Merge pull request #4485 from martin-frbg/issue4468
[WIP] Add a build option to suppress versioning and softlinking of the library
|
2024-02-23 14:54:12 +01:00 |
Martin Kroeker
|
2e86faa657
|
Merge branch 'develop' into issue4468
|
2024-02-23 11:39:49 +01:00 |