521e585b6
Update .cirrus.yml by
2023-09-26 15:15:16 +0200
fc2e9a306
Update .cirrus.yml by
2023-09-26 14:39:51 +0200
7c30a7b5f
Update .cirrus.yml by
2023-09-26 10:05:07 +0200
4670eb146
(refs/pull/4242/head)
LoongArch64: Add dtrsm kernel by
2023-09-20 09:09:35 +0800
dcd0378ec
Update Mac M1 jobs on Cirrus CI to Ventura by
2023-09-25 22:40:06 +0200
138ed79fe
Merge pull request #4238 from martin-frbg/issue4237 by
2023-09-24 14:31:33 +0200
2a9981a24
(refs/pull/4238/head)
Add -lgomp when IBM xlf is combined with gcc in OPENMP builds by
2023-09-24 10:19:11 +0200
7a96908d0
Add -lgomp when IBM xlf is combined with gcc in OPENMP builds by
2023-09-24 10:18:24 +0200
4de963dc1
Enforce trailing underscores on symbols when IBM xlf is combined with gcc by
2023-09-24 10:16:37 +0200
8012afcab
Avoid using some gcc-specific flags with IBM xlf by
2023-09-24 10:15:12 +0200
bb4718322
Force -qextname for trailing underscore generation when IBM xlf is used with gcc by
2023-09-24 10:13:47 +0200
b926e70eb
Fix typo in build rule of "profiled" sbgemm by
2023-09-21 23:07:32 +0200
2390e0bfb
Quote the BU (underscore) option as it may not be set by
2023-09-21 23:04:25 +0200
44e6e5479
Use the C compiler for the C SBGEMM test source by
2023-09-21 23:01:21 +0200
48b1b7cbc
Merge pull request #4233 from martin-frbg/issue4216 by
2023-09-21 11:12:52 +0200
bb90b6dfc
Merge pull request #4157 from steppi/cirun by
2023-09-21 07:28:40 +0200
db3a43c8e
(refs/pull/4235/head)
Simplify rotg by
2023-09-20 19:42:13 +0200
6876ae0c3
Fix division by zero in zrotg by
2023-09-20 19:10:08 +0200
7e939fb83
(refs/pull/4233/head)
Fix handling of additional buffer structures in case of overflow by
2023-09-19 23:33:39 +0200
bb2f1ec3b
Merge pull request #4222 from dev-zero/bugfix/correct-thread-warning by
2023-09-17 00:02:46 +0200
466e6115d
Merge pull request #4230 from martin-frbg/lapack907 by
2023-09-16 20:13:13 +0200
1285b53e3
(refs/pull/4230/head)
Make IWORK array larger to avoid overflow by
2023-09-14 20:22:11 +0200
7779bb6fb
Make IWORK array larger to avoid overflow by
2023-09-14 20:21:06 +0200
060610246
Merge pull request #4229 from martin-frbg/issue4228 by
2023-09-14 16:15:54 +0200
fb97cc4d5
(refs/pull/4229/head)
Add la_constants.o to SCLAUX/DZLAUX by
2023-09-14 10:46:23 +0200
6a611db56
(refs/pull/4222/head)
memory: show correct number of max threads by
2023-09-10 08:44:07 +0200
6bc079687
Merge pull request #4218 from XiWeiGu/loongarch64_sgemv by
2023-09-08 13:35:35 +0200
cd36b8fff
Merge pull request #4214 from martin-frbg/issue4212 by
2023-09-05 20:43:44 +0200
09911f077
(refs/pull/4214/head)
Disable SVE targets for DYNAMIC_ARCH when compiling with (homebrew)gcc on macOS/arm64 by
2023-09-05 16:33:40 +0200
c3f2a3c0c
Update version to 0.3.24.dev by
2023-09-04 08:40:25 +0200
4867cf5dd
Update version to 0.3.24.dev by
2023-09-04 08:39:40 +0200
f2cf92937
(refs/pull/4218/head)
LoongArch64: Add sgemv kernel by
2023-08-31 16:59:37 +0800
f29a0d1a7
Merge pull request #4211 from xianyi/release-0.3.0 by
2023-09-03 23:25:58 +0200
9f815cf1b
(tag: v0.3.24, refs/pull/4211/head)
Update version to 0.3.24 by
2023-09-03 22:58:32 +0200
3c49711f1
Update version to 0.3.24 by
2023-09-03 22:57:22 +0200
2c68822cd
Merge pull request #4210 from xianyi/develop by
2023-09-03 22:55:22 +0200
3c51bd0fb
(refs/pull/4210/head)
Merge pull request #4209 from martin-frbg/changelog0324 by
2023-09-03 22:51:03 +0200
5d7304106
(refs/pull/4209/head)
Update Changelog for 0.3.24 by
2023-09-03 19:05:53 +0200
8e6d93359
Merge pull request #4196 from TiborGY/obsolete_inlines by
2023-09-03 14:12:42 +0200
33797c44f
Merge pull request #4143 from martin-frbg/issue4130 by
2023-09-01 14:20:25 +0200
ee310e353
Merge pull request #4208 from XiWeiGu/loongarch64_toolchain by
2023-09-01 10:50:01 +0200
42909ce57
(refs/pull/4143/head)
Merge branch 'xianyi:develop' into issue4130 by
2023-09-01 09:05:58 +0200
a2a184572
update zrotg by
2023-08-31 23:42:12 +0200
394a1fd1b
(refs/pull/4208/head)
LoongArch64: Compatible with early internal toolchain by
2023-08-31 15:44:22 +0800
12d8f219d
Merge pull request #4207 from martin-frbg/issue4174-2 by
2023-08-26 12:05:37 +0200
9c4ae4d4f
Merge pull request #4206 from martin-frbg/issue4201-2 by
2023-08-26 10:17:27 +0200
3bb70b8ca
Merge pull request #4205 from martin-frbg/fixintmain by
2023-08-26 08:38:38 +0200
3b6050ac0
(refs/pull/4207/head)
clarify the comment on the out-of-bounds check from #723 by
2023-08-26 02:00:00 +0200
22a402bc2
clarify the comment on the out-of-bounds check from #723 by
2023-08-26 01:58:08 +0200
88435104c
Merge pull request #4204 from martin-frbg/llvm17-2 by
2023-08-26 00:32:18 +0200
fc8894dd9
(refs/pull/4206/head)
Workaround miscompilation by NVIDIA nvc by
2023-08-26 00:30:17 +0200
be57c595a
Merge pull request #4203 from martin-frbg/issue4201 by
2023-08-25 22:55:38 +0200
7a6203ffa
(refs/pull/4203/head)
restore default Neoverse SVE build instructions for non-NVIDIA compilers by
2023-08-25 18:25:51 +0200
7f7d3896d
(refs/pull/4205/head)
Fix missing type declaration for main by
2023-08-25 18:07:47 +0200
2c3034ff7
(refs/pull/4204/head)
Disable the C/ZASUM AVX512 microkernels when compiling with LLVM17 as well by
2023-08-25 17:22:51 +0200
49689fbef
Add support for compiling SVE kernels with the NVIDIA HPC compiler by
2023-08-25 17:11:04 +0200
8794544b4
Add support for compiling the Neoverse SVE kernels with the NVIDIA HPC compiler by
2023-08-25 16:47:32 +0200
e9f1b2d26
Expand the SVE compatibility check for the NVIDIA HPC compiler by
2023-08-25 16:45:56 +0200
d69f57c8c
Merge pull request #4200 from XiWeiGu/loongarch64_sgemm by
2023-08-23 13:05:34 +0200
553cc1372
(refs/pull/4200/head)
LoongArch64: Add sgemm_kernel by
2023-08-18 17:39:44 +0800
12ede72ab
Merge pull request #4192 from imciner2/im/clangfix by
2023-08-21 15:46:35 +0200
76d675bd5
(refs/pull/4191/head)
Add NaN tests by
2023-08-20 14:57:31 +0200
3d10fb003
Add NaN tests by
2023-08-19 12:20:42 +0200
8d9f701fb
Merge pull request #4195 from TiborGY/BF16_ignore by
2023-08-19 12:16:44 +0200
7f67ba914
Merge pull request #4198 from martin-frbg/issue4197 by
2023-08-19 07:51:51 +0200
214be14c1
(refs/pull/4198/head)
Correct INFO returned for lda in non-CBLAS s/dgeadd by
2023-08-18 22:48:30 +0200
1b09f4b2b
Merge pull request #4193 from imciner2/im/ppcgnu by
2023-08-17 22:56:08 +0200
79c15db34
(refs/pull/4193/head)
Fix power10 gcc intrinsic check by
2023-08-14 21:36:35 +0100
b5ba95a6c
(refs/pull/4196/head)
Modernize obsolete inline order by
2023-08-16 00:48:40 +0200
6da9baa55
(refs/pull/1976/head)
upload some buildtests by
2023-08-16 00:24:26 +0200
0d30daa77
(refs/pull/4195/head)
Add junk from BF16 test to .gitignore by
2023-08-16 00:07:17 +0200
2e68d922d
Add NaN tests by
2023-08-14 23:14:32 +0200
f98682969
Add NaN tests by
2023-08-14 23:13:46 +0200
dfacb63b2
Add NaN tests by
2023-08-14 23:13:02 +0200
3e87ac9a4
Add tests for IAMAX with NaN values by
2023-08-14 22:28:02 +0200
9402651ef
Add NaN tests by
2023-08-14 22:26:33 +0200
4f21cdf68
Add NaN tests by
2023-08-14 22:25:50 +0200
9a8d090ea
Add NaN tests by
2023-08-14 22:25:03 +0200
43f5e4251
Add NaN tests by
2023-08-14 17:45:35 +0200
8a8a8479b
(refs/pull/4192/head)
Fix cooperlake and sapphire rapids march flags on clang by
2023-08-14 15:41:28 +0100
82827762c
(refs/pull/4027/head)
Merge branch 'xianyi:develop' into nanobench by
2023-08-14 15:45:22 +0100
95ce0b0c4
Add NaN tests by
2023-08-13 23:45:36 +0200
562ef5fdc
Merge pull request #4169 from felixonmars/patch-1 by
2023-08-12 17:20:56 +0200
0e5d56ae4
Merge pull request #4170 from felixonmars/patch-2 by
2023-08-12 09:21:05 +0200
ebc157fcc
Merge pull request #4190 from martin-frbg/issue4186-2 by
2023-08-10 23:12:59 +0200
34da1a067
(refs/pull/4190/head)
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 17:01:50 +0200
07e32c4cb
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 17:00:18 +0200
c211da068
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:58:57 +0200
a34a0a7ab
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:56:52 +0200
54d3246fc
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:55:17 +0200
7dd441d5d
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:53:33 +0200
f69217879
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:52:09 +0200
d15ffb7fd
Allow negative INCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:50:44 +0200
a2d867f4d
Allow negative iNCX (API change from version 3.10 of the reference implementation) by
2023-08-10 16:49:05 +0200
9a0e9c8b6
Merge pull request #4171 from boomanaiden154/clang-libomp-fixes by
2023-08-10 16:32:33 +0200
7af0f4176
Merge pull request #4189 from martin-frbg/issue4186 by
2023-08-10 14:11:12 +0200
4cc804c75
(refs/pull/4189/head)
Prepare for INCX < 0 in new NRM2 implementation from BLAS 3.10 by
2023-08-09 16:13:23 +0200
4d0f000db
(refs/pull/4185/head)
MIPS: Enable MSA by
2023-08-07 16:55:59 +0800
afdc56a42
Merge pull request #4158 from XiWeiGu/loongarch64_update_dgemm_kernel by
2023-08-07 12:44:09 +0200
91e5513f3
Merge pull request #4184 from XiWeiGu/dgemv by
2023-08-07 08:47:19 +0200