Commit Graph

  • *
  • | *
  • |/
  • *
  • |\
  • * \
  • |\ \
  • | | | *
  • | | * |
  • | | * |
  • | |/ /
  • |/| |
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | |/
  • |/|
  • | *
  • | *
  • * |
  • |/
  • | *
  • | *
  • | *
  • | *
  • | | *
  • | | | *
  • | | | *
  • | | * |
  • | | * |
  • | | * |
  • | | * |
  • | | * |
  • | | * |
  • * | | |
  • |\ \ \ \
  • | * | | |
  • * | | | |
  • |\ \ \ \ \
  • | * | | | |
  • | * | | | |
  • |/ / / / /
  • | | | * |
  • * | | | |
  • |\ \ \ \ \
  • | | | | * |
  • | * | | | |
  • |/ / / / /
  • | | | * |
  • | | * | |
  • | | | * |
  • | | | * |
  • | | * | |
  • | | * | |
  • | | * | |
  • | | * | |
  • | | |/ /
  • | | * |
  • * | | |
  • |\ \ \ \
  • | |_|/ /
  • |/| | |
  • | * | |
  • |/ / /
  • * | |
  • |\ \ \
  • * \ \ \
  • |\ \ \ \
  • | | | | *
  • | | | | *
  • | * | | |
  • |/ / / /
  • | | | *
  • | | | *
  • | | | *
  • | | | *
  • | * | |
  • |/ / /
  • | | *
  • * | |
  • |\ \ \
  • | |/ /
  • |/| |
  • | * |
  • | * |
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • | | *
  • 7d1becc57 Allocate an auxiliary struct when running out of preconfigured threads by Martin Kroeker 2021-08-28 14:18:36 +0200
  • b09c6f2ab (refs/pull/3350/head) create a new control structure on the stack when we run out of preconfigured threads by Martin Kroeker 2021-08-26 14:37:43 +0200
  • 6bb1805ed Merge pull request #3348 from guowangy/skylakex-sgemv_t-fix by Martin Kroeker 2021-08-25 22:43:45 +0200
  • 0f0a0be95 Merge pull request #3345 from nsait-linaro/windows_on_arm64 by Martin Kroeker 2021-08-25 15:49:55 +0200
  • 874bead8b (refs/pull/3347/head) Update .drone.yml by Martin Kroeker 2021-08-25 10:47:06 +0200
  • dbbb39199 (refs/pull/3348/head) sgemv: skylakex: fix build warning by Wangyang Guo 2021-08-25 07:13:00 +0000
  • e9acb4643 sgemv: skylakex: bug fix for sgemv_t kernel in corner case by Wangyang Guo 2021-08-25 07:07:27 +0000
  • 3ebeb74c8 Update .drone.yml by Martin Kroeker 2021-08-24 23:53:57 +0200
  • fbf36e315 Update .drone.yml by Martin Kroeker 2021-08-24 22:58:08 +0200
  • 2ac2551fa Update .drone.yml by Martin Kroeker 2021-08-24 22:06:32 +0200
  • d4e4bd3dc Update .drone.yml by Martin Kroeker 2021-08-24 19:45:01 +0200
  • 68f48b3f6 Update .drone.yml by Martin Kroeker 2021-08-24 19:29:20 +0200
  • ac552a5e3 Update .drone.yml by Martin Kroeker 2021-08-24 15:18:07 +0200
  • 95bf655be Update Makefile.rule by Martin Kroeker 2021-08-24 13:29:31 +0200
  • 0beb35ba7 Update .drone.yml by Martin Kroeker 2021-08-23 21:49:15 +0200
  • 69f4d032a Update .drone.yml by Martin Kroeker 2021-08-23 19:44:23 +0200
  • eb9f4f297 Update .drone.yml by Martin Kroeker 2021-08-23 08:19:32 +0200
  • b931a998b Update .drone.yml by Martin Kroeker 2021-08-23 01:13:17 +0200
  • a35a436ff Update .drone.yml by Martin Kroeker 2021-08-22 22:35:55 +0200
  • f0973d14e need python3 for this test by Martin Kroeker 2021-08-22 20:19:01 +0200
  • 29f13cc8b fix url by Martin Kroeker 2021-08-22 18:20:13 +0200
  • ccccdc49b Update .drone.yml by Martin Kroeker 2021-08-22 16:30:52 +0200
  • 90ee2302a fix formatting by Martin Kroeker 2021-08-22 15:13:53 +0200
  • 97d802e3e add testcase for external caller exceeding our thread limit by Martin Kroeker 2021-08-22 15:05:08 +0200
  • c6c2a71fb (refs/pull/3345/head) Fix ctest.h to build using clang on windows by Niyas Sait 2021-08-16 11:25:07 +0100
  • cdb5d2737 add support for building on windows/arm64 target by Niyas Sait 2021-08-16 11:22:51 +0100
  • 13d411677 Add more OSX build jobs to Azure CI (#3338) by Martin Kroeker 2021-08-15 00:17:23 +0200
  • 4c93f2e25 (refs/pull/3338/head) Update azure-pipelines.yml by Martin Kroeker 2021-08-14 21:24:07 +0200
  • 1eef884fa Update azure-pipelines.yml by Martin Kroeker 2021-08-14 19:38:57 +0200
  • 6c6651f20 Update azure-pipelines.yml by Martin Kroeker 2021-08-14 19:28:09 +0200
  • f413ff46f move IOS xbuilds from travis to azure by Martin Kroeker 2021-08-14 18:48:17 +0200
  • d19af01f5 (refs/pull/3340/head) Update .drone.yml by Martin Kroeker 2021-08-13 07:08:48 +0200
  • f9dba63c2 (refs/pull/3335/head) Small Matrix: skylakex: remove unnecessary b0 source files by Wangyang Guo 2021-08-13 03:28:44 +0000
  • 989e6bbdd Small Matrix: reduce generic kernel source files by Wangyang Guo 2021-08-13 03:17:38 +0000
  • 68b2b5038 Update .drone.yml by Martin Kroeker 2021-08-13 01:44:45 +0200
  • a5a7892fa Update .drone.yml by Martin Kroeker 2021-08-12 23:40:53 +0200
  • 2fb65d062 Update .drone.yml by Martin Kroeker 2021-08-12 22:50:36 +0200
  • 3bd81e9b9 Update .drone.yml by Martin Kroeker 2021-08-12 21:20:11 +0200
  • 0161aba5d Update .drone.yml by Martin Kroeker 2021-08-12 19:13:11 +0200
  • 3f021a1b7 try to force installation of a specific version of gcc by Martin Kroeker 2021-08-12 16:03:41 +0200
  • 04255be94 Merge pull request #3344 from gxw-loongson/develop by Martin Kroeker 2021-08-12 15:16:46 +0200
  • a7bc8ec1f (refs/pull/3344/head) Delete the macro instruction "li" and use "li.d" instead by gxw 2021-08-10 16:42:57 +0800
  • 8cd2b32fe Merge pull request #3343 from cianciosa/develop by Martin Kroeker 2021-08-12 01:28:18 +0200
  • 4c766cd11 (refs/pull/3343/head) Fix a small syntax error. A ( was accidently deleted. by cianciosa 2021-08-11 12:08:34 -0400
  • c28560129 Check the total number of arguments passed insead of if the ARGV# is defined. This fixes a problem when compling openblas as a subproject of another code. by cianciosa 2021-08-11 12:00:07 -0400
  • 6667aa5bc Update .drone.yml by Martin Kroeker 2021-08-11 16:47:26 +0200
  • b9e4fb206 Merge pull request #3341 from RajalakshmiSR/dasump10 by Martin Kroeker 2021-08-11 09:39:10 +0200
  • 3bdca029b Update .drone.yml by Martin Kroeker 2021-08-11 09:28:53 +0200
  • b06880c2c (refs/pull/3341/head) POWER10: Improving dasum performance by Rajalakshmi Srinivasaraghavan 2021-08-10 22:06:04 -0500
  • b33002365 Update .drone.yml by Martin Kroeker 2021-08-10 18:39:44 +0200
  • 3da6a5d7c Add mixed clang/gfortran build with cmake on OSX by Martin Kroeker 2021-08-10 11:24:22 +0200
  • ea48bbac6 Update .drone.yml by Martin Kroeker 2021-08-09 16:23:09 +0200
  • 3cbbb3a37 run blas-tester on ThunderX/Falkor by Martin Kroeker 2021-08-09 15:11:15 +0200
  • fa71b9fea Check install step on OSX/gcc by Martin Kroeker 2021-08-08 13:03:34 +0200
  • bb2916d1e Update azure-pipelines.yml by Martin Kroeker 2021-08-07 22:23:10 +0200
  • 7d2cd3d80 Update azure-pipelines.yml by Martin Kroeker 2021-08-07 18:45:28 +0200
  • e8e285511 set cmake build type to debug to ease register pressure for LLVM SKX build by Martin Kroeker 2021-08-07 17:32:08 +0200
  • a0c6350f4 Add OSX build job with Homebrew OpenMP in a CMAKE build by Martin Kroeker 2021-08-07 16:59:53 +0200
  • cbc583eb5 Merge pull request #3336 from martin-frbg/traviscom by Zhang Xianyi 2021-08-05 19:13:19 +0800
  • e5ba7c323 (refs/pull/3336/head) Disable all x86 jobs by Martin Kroeker 2021-08-05 11:08:18 +0200
  • 435d84a7c Merge pull request #3332 from martin-frbg/travisbadge by Martin Kroeker 2021-08-05 09:36:59 +0200
  • 139f632ca Merge pull request #3334 from Guobing-Chen/BF16_gemm_full_kernel by Martin Kroeker 2021-08-05 08:01:13 +0200
  • c17d6dacb Small Matrix: skip compile in unimplemented data type by Wangyang Guo 2021-08-05 05:46:13 +0000
  • 44d0032f3 Small Matrix: skylakex: fix build error in old compiler by Wangyang Guo 2021-08-05 04:43:47 +0000
  • 5d86becda (refs/pull/3334/head) Add all SBGEMM kernels for IA AVX512-BF16 based platforms by Chen, Guobing 2021-08-05 11:11:14 +0800
  • 76ea8db4d Small Matrix: enable by default for x86_64 arch by Wangyang Guo 2021-08-05 02:57:58 +0000
  • aa5018564 Small Matrix: better handle with GEMM3M marco by Wangyang Guo 2021-08-05 02:45:53 +0000
  • fee5abd84 Small Matrix: support cmake build by Wangyang Guo 2021-08-04 08:50:15 +0000
  • 478d1086c Small Matrix: support DYNAMIC_ARCH build by Wangyang Guo 2021-08-04 03:12:41 +0000
  • 93c8bafff (refs/pull/3332/head) Update Travis badge in README by Martin Kroeker 2021-08-03 10:45:45 +0200
  • 6b58bca18 Small Matrix: disable low performance default kernel by Wangyang Guo 2021-06-15 16:09:51 +0000
  • b5858c447 Merge pull request #3330 from xianyi/issue3321 by Martin Kroeker 2021-08-02 22:36:05 +0200
  • 898212efc (refs/pull/3330/head, issue3321) Actually add the message to the TLS section by Martin Kroeker 2021-08-02 14:50:14 +0200
  • 210a1584c Rebase source and edit TLS version of the message as well by Martin Kroeker 2021-08-02 14:19:16 +0200
  • fa777f551 Small Matrix: skylakex: add DGEMM_SMALL_M_PERMIT and tune for TN kernel by Wangyang Guo 2021-06-02 14:55:54 +0000
  • 8592c21af Small Matrix: skylakex: dgemm nn: fix typo in idx load by Wangyang Guo 2021-06-02 13:57:39 +0000
  • 3e79f6d89 Small Matrix: skylakex: add dgemm tn kernel by Wangyang Guo 2021-06-02 13:56:40 +0000
  • 323d7da4f Small Matrix: skylakex: add dgemm tt kernel by Wangyang Guo 2021-06-02 11:45:44 +0000
  • f57fc932a Small Matrix: skylakex: add dgemm nt kernel by Wangyang Guo 2021-06-01 14:23:56 +0000
  • 91ec21202 Small Matrix: skylakex: add dgemm nn kernel by Wangyang Guo 2021-06-01 11:31:50 +0000
  • 72e070539 Small Matrix: skylakex: add sgemm tt kernel by Wangyang Guo 2021-05-31 14:53:03 +0000
  • 02c6e764f Small Matrix: skylakex: add SGEMM_SMALL_M_PERMIT and tune for TN kernel by Wangyang Guo 2021-05-27 11:26:49 +0000
  • 5dc7c3c8e Small Matrix: add GEMM_SMALL_MATRIX_PERMIT to tune small matrics case by Wangyang Guo 2021-05-27 11:03:56 +0000
  • 642c39387 Small Matrix: skylakex: add sgemm tn kernel by Wangyang Guo 2021-05-26 16:30:57 +0000
  • ae3f5c737 Small Matrix: skylakex: sgemm nt: optimize for M < 12 by Wangyang Guo 2021-05-21 13:31:31 +0000
  • 0d72d75bf Small Matrix: skylakex: add sgemm nt kernel by Wangyang Guo 2021-05-20 11:47:10 +0000
  • ca7682e3a Small Matrix: skylakex: sgemm nn: fix n6 conflicts with n4 by Wangyang Guo 2021-05-20 11:24:31 +0000
  • 9967e61ab Small Matrix: skylakex: sgemm nn: fix error when beta not zero by Wangyang Guo 2021-05-19 10:50:03 +0000
  • a87736346 Small Matrix: skylakex: sgemm nn: add n6 to improve performance by Wangyang Guo 2021-05-13 10:16:54 +0000
  • 4c9d9940f Small Matrix: skylakex: sgemm nn: reduce store 4 N at a time by Wangyang Guo 2021-05-13 09:41:51 +0000
  • 13b32f69b Small Matrix: skylakex: sgemm nn: reduce store 4 M at a time by Wangyang Guo 2021-05-12 17:08:18 +0000
  • 3d8c6d960 Small Matrix: skylakex: sgemm nn: clean up unused code by Wangyang Guo 2021-05-11 10:33:07 +0000
  • 49b61a3f3 Small Matrix: skylakex: sgemm_nn: optimize for M <= 8 by Wangyang Guo 2021-05-11 10:24:10 +0000
  • f88470323 Optimize M < 16 using AVX512 mask by Wangyang Guo 2021-05-08 15:59:14 +0000
  • 9186456a1 small matrix: SkylakeX: add SGEMM NN kernel by Wangyang Guo 2021-05-08 10:45:10 +0000
  • 6022e5629 Refs #2587 fix small matrix c/zgemm bug. by Xianyi Zhang 2020-08-28 22:36:36 +0800
  • 57ed58cef Refs #2587 Add small matrix optimization reference kernel for c/zgemm. by Xianyi Zhang 2020-08-28 21:00:54 +0800
  • 17d32a4a8 Change a1b0 gemm to b0 gemm. by Xianyi Zhang 2020-08-28 07:55:27 +0800
  • 59cb5de46 Refs #2587 Fix typos. by Xianyi Zhang 2020-04-29 00:19:19 +0800
  • 4271cfcc6 Fix gemm interface bug for small matrix. by Xianyi Zhang 2020-04-28 23:15:20 +0800