Martin Kroeker
4c03ed437f
Fix SICORTEX ASUM/ZASUM and SUM/ZSUM for INCX <=0 ( #4640 )
* Exit early if INCX <= 0
1 year ago
Martin Kroeker
23d5a8b16e
Merge pull request #4628 from XiWeiGu/CI-c910v-mips64-loongarch64
CI: add openblas_utest_ext for c910v, mips64 and loongarch64
1 year ago
Martin Kroeker
b8618fa7f6
Merge pull request #4634 from martin-frbg/utest0
Fix uninitialized variables in the extensions utest
1 year ago
Martin Kroeker
b883526a34
Fix uninitialized variables in the extensions utest
1 year ago
Martin Kroeker
83ec1f86ec
Merge pull request #4630 from martin-frbg/issue4178-2
Add another object signature for classic flang
1 year ago
Martin Kroeker
a9703c70f3
Merge pull request #4631 from martin-frbg/issue4626
revert the C/Z NRM2 kernels for NEOVERSEN1 and VORTEX to the base NEON kernel as well
1 year ago
Martin Kroeker
e6ae4b6f38
Merge pull request #4627 from mattip/soname
remove extraneous suffix from shared object SONAME
1 year ago
Martin Kroeker
7cfd433d0c
revert the C/Z NRM2 kernels to the base NEON kernel as well
1 year ago
Martin Kroeker
d26caff60c
Add another object signature for classic flang
1 year ago
Martin Kroeker
45dbf50036
Merge pull request #4629 from tetsuzo-usui/PfSizeTune_forNeoverseV1
Set GEMM_PREFERED_SIZE parameter for Neoverse V1
1 year ago
Usui, Tetsuzo
ca673ca774
Add GEMM_PREFERED_SIZE parameter for Neoverse V1
1 year ago
gxw
d9e2db3735
CI: add openblas_utest_ext for c910v, mips64 and loongarch64
1 year ago
Martin Kroeker
15b9fc3f78
Merge pull request #4624 from ChipKerchner/removeOMPfromXLF
Remove -openmp flag from XLF (since it doesn't support it).
1 year ago
Matti Picus
4d96e0ce18
remove extraneous suffix from shared object SONAME
1 year ago
Chip Kerchner
1c13cda3fc
Remove -openmp flag from XLF (since it doesn't support it).
1 year ago
Martin Kroeker
93d975d8fd
Merge pull request #4593 from XiWeiGu/loongarch_add_buffer_offset
loongarch: Optimizing the performance of the GEMM on servers
1 year ago
gxw
d8c4ea8793
loongarch: Optimizing the performance of the GEMM on servers
1 year ago
Martin Kroeker
3cf57a61d5
Merge pull request #4609 from yu-chen-surf/develop
Get the l2 cache size via environment variable on confidential VM
1 year ago
Martin Kroeker
fbd42e9e0e
Merge pull request #4616 from MehdiChinoune/patch-1
Don't pass `-exhaustive-register-search` directly to clang compiler
1 year ago
Martin Kroeker
03ff65190d
Merge pull request #4614 from martin-frbg/issue4449-2
Retain the bf16 in fallback versions of the NeoverseN2 -march flag
1 year ago
Martin Kroeker
12650c912c
Merge pull request #4613 from martin-frbg/issue4612
Do not run the CBLAS_?GEMM3M tests when cross-compiling with gmake
1 year ago
Martin Kroeker
4eb4b033e5
Merge pull request #4610 from martin-frbg/issue4608
Make the new ZSCAL utest not require CBLAS
1 year ago
مهدي شينون (Mehdi Chinoune)
cda55f2fd2
Don't pass `-exhaustive-register-search` directly to clang compiler
`-exhaustive-register-search` is an LLVM code generation flag that shouldn't be passed directly to clang compiler.
1 year ago
Martin Kroeker
14e71c249d
retain the bf16 capability in fallback versions of the -march option for NeoverseN2
1 year ago
Martin Kroeker
48e017de09
fix position of endif - gemm3m tests should not be run in cross-compiles
1 year ago
Martin Kroeker
9c86838279
use blasint for INTERFACE64 compatibility
1 year ago
Martin Kroeker
d3f93c6015
fix arguments of zscal
1 year ago
Martin Kroeker
1f080b9328
Update test_zscal.c
1 year ago
Martin Kroeker
ec8e9451f0
make independent of CBLAS
1 year ago
Chen Yu
8e39c05efd
Get the l2 cache size via environment variable on confidential VM
The CPUID(leaf:2 or leaf:0x80000006) is not supported on some confidential
VMs. As a result the get_l2_size() returns the default 512M which brings
performance issues.
Introduce the environment variable OPENBLAS_L2_SIZE provided by the user
to get the l2 cache size.
Suggested-by: "Keshavamurthy, Anil S" <anil.s.keshavamurthy@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
1 year ago
Martin Kroeker
bebe5e5399
Merge pull request #4562 from honno/mkdocs-wiki
Fold wiki contents into formal documentation, build-able with `mkdocs`
1 year ago
Martin Kroeker
1c7d27c750
Update version to 0.3.27.dev
1 year ago
Martin Kroeker
17ab724da9
Update version to 0.3.27.dev
1 year ago
Martin Kroeker
5f204bb008
Merge pull request #4607 from OpenMathLib/release-0.3.0
merge back from release branch to copy tag
1 year ago
Martin Kroeker
ce3f668c99
Update version to 0.3.27
1 year ago
Martin Kroeker
8f3bb62254
Merge pull request #4606 from OpenMathLib/develop
Merge develop branch for 0.3.27
1 year ago
Martin Kroeker
c17f5bee81
Merge branch 'release-0.3.0' into develop
1 year ago
Martin Kroeker
0475716e2e
Update version to 0.3.27
1 year ago
Martin Kroeker
1dcbc4e0bb
Merge pull request #4605 from martin-frbg/changelog0327
Update Changelog.txt for 0.3.27
1 year ago
Martin Kroeker
c5184078b4
Update Changelog.txt for 0.3.27
1 year ago
Martin Kroeker
f5e5109318
Merge pull request #4604 from martin-frbg/zenprefsize
Adjust SWITCH_RATIO for ZEN and apply GEMM_PREFERRED_SIZE
1 year ago
Martin Kroeker
ba6d485102
Adjust SWITCH_RATIO for ZEN and apply GEMM_PREFERRED_SIZE
1 year ago
Martin Kroeker
ffedd8a2cb
Merge pull request #4603 from martin-frbg/cleanup4043
Clean up misplaced LAPACK files from PR4043 (in-code documentation changes only)
1 year ago
Martin Kroeker
5e1937531f
Merge pull request #4602 from martin-frbg/gitign_3m
Add GEMM3M tests and logs to .gitignore
1 year ago
Martin Kroeker
20145ca868
Delete misplaced file (move to SRC)
1 year ago
Martin Kroeker
45164fe406
Delete misplaced file (move to SRC)
1 year ago
Martin Kroeker
f58f097a51
Delete misplaced file (move to SRC)
1 year ago
Martin Kroeker
099f10b706
Delete misplaced file (move to SRC)
1 year ago
Martin Kroeker
bdcb5a23f6
Delete misplaced file (move to SRC)
1 year ago
Martin Kroeker
5e510a1289
Delete misplaced file (move to SRC)
1 year ago