Commit Graph

  • 5e4f1e3677
    Remove BFLOAT16 from the task list of GenerateNamedObject Martin Kroeker 2021-09-14 16:09:46 +0200
  • af8843875a
    Merge pull request #3376 from martin-frbg/issue3370 Martin Kroeker 2021-09-12 00:01:31 +0200
  • d1ee2e9c7d
    Merge pull request #3375 from martin-frbg/issue3369 Martin Kroeker 2021-09-12 00:01:20 +0200
  • 0925dfe2c9
    One instance of kernel_4x1 is used even on SKX Martin Kroeker 2021-09-11 15:30:19 +0200
  • 1085775bc6
    really remove the unused variable Martin Kroeker 2021-09-11 15:05:55 +0200
  • 7d873a329f
    Add ifdefs around conditionally used functions Martin Kroeker 2021-09-11 14:38:47 +0200
  • ef24712030
    Move a conditionally used variable Martin Kroeker 2021-09-11 14:37:44 +0200
  • 20581bf303
    Remove unused variable Martin Kroeker 2021-09-11 14:36:27 +0200
  • d17238599b
    Add casts Martin Kroeker 2021-09-11 13:38:28 +0200
  • 3742611aa9
    remove BFLOAT16 from FLOAT_TYPES to avoid creating bogus objects for unimplemented functions Martin Kroeker 2021-09-10 13:38:16 +0200
  • acfa013126
    Add separate handling for sbgemm Martin Kroeker 2021-09-10 13:35:39 +0200
  • 5bfdbd1a39
    Fix generation of sbgemv drivers Martin Kroeker 2021-09-10 11:32:43 +0200
  • 0a4a07ff58
    fix cmake generation of bfloat16 interfaces Martin Kroeker 2021-09-10 11:18:18 +0200
  • 1f4fe48be9
    add defaults for sbgemv kernels Martin Kroeker 2021-09-10 11:17:16 +0200
  • f8d57df56c
    pass BUILD_BFLOAT16 to the compiler Martin Kroeker 2021-09-10 11:15:24 +0200
  • 3e8c448696
    Merge pull request #3367 from RajalakshmiSR/makesyntax Martin Kroeker 2021-09-08 20:19:39 +0200
  • 7f4aa106f2 Fixing syntax error in makefile Rajalakshmi Srinivasaraghavan 2021-09-08 07:04:13 -0500
  • a6ed4f0d37
    Merge pull request #3366 from martin-frbg/azure-ubuntu Martin Kroeker 2021-09-08 13:57:35 +0200
  • b858e65476
    migrate from deprecated ubuntu-16.04 vmImage Martin Kroeker 2021-09-08 10:51:59 +0200
  • d3d6601727
    Merge pull request #3365 from martin-frbg/travis-lx Martin Kroeker 2021-09-07 16:24:33 +0200
  • da5bd8b5e3
    Merge pull request #3364 from guowangy/bf16-cooperlake Martin Kroeker 2021-09-07 13:57:40 +0200
  • 045ed5c91d sbgemm: fix build error in BFLOAT16 disabled Wangyang Guo 2021-09-07 23:37:08 +0800
  • 4289cf048d sbgemm: avoid falling into SGEMM_KERNEL_DIRECT Wangyang Guo 2021-09-07 18:34:26 +0800
  • 59a1114d03 sbgemm: cooperlake: tuning for small matrix Wangyang Guo 2021-09-07 18:12:40 +0800
  • 682d66555d sbgemm: cooperlake: implement ncopy_16 Wangyang Guo 2021-08-20 22:01:00 +0800
  • beccb83b16 sbgemm: cooperlake: add n24 kernel for tcopy_4 Wangyang Guo 2021-08-19 19:46:08 +0800
  • 5fcacad32b sbgemm: cooperlake: implement tcopy_4 Wangyang Guo 2021-08-19 00:08:06 +0800
  • bb1c4fa5bd sbgemm: cooperlake: prefetch A & B Wangyang Guo 2021-08-18 21:17:08 +0800
  • 7a2d1601ec sbgemm: cooperlake: unroll core loop by 2 Wangyang Guo 2021-08-17 23:21:19 +0800
  • 45fdf951b6 sbgemm: cooperlake: reorder ptr increase for performance Wangyang Guo 2021-08-17 22:08:24 +0800
  • cece3541ab sbgemm: cooperlake: fix bug in m64n12 Wangyang Guo 2021-08-17 21:13:29 +0800
  • 8356a604f0 sbgemm: cooperlake: tuning for block params Wangyang Guo 2021-08-17 19:35:40 +0800
  • 9df0953cde sbgemm: cooperlake: kernel works for NN Wangyang Guo 2021-08-16 19:39:24 +0800
  • 2ec9f3a8aa sbgemm: cooperlake: change kernel size to 16x4 Wangyang Guo 2021-08-12 01:46:49 +0000
  • ef8f5fecc8 sbgemm: cooperlake: implement sbgemm_tcopy_32 Wangyang Guo 2021-08-10 06:14:45 +0000
  • 4c294336e6 sbgemm: cooperlake: add dummy source files Wangyang Guo 2021-08-10 03:23:45 +0000
  • 8c68b6f26d
    Update .travis.yml Martin Kroeker 2021-09-07 11:40:40 +0200
  • 349fb4910b
    Disable the remaining x86_64 job on Travis Martin Kroeker 2021-09-07 11:19:51 +0200
  • 7c72c45be6
    Merge pull request #3363 from martin-frbg/fixpr3360 Martin Kroeker 2021-09-07 08:02:53 +0200
  • 32fee86033
    Correct misplaced ifdef lines Martin Kroeker 2021-09-06 23:44:20 +0200
  • 272acc3f18 mention TARGET=GENERIC Isuru Fernando 2021-09-06 11:58:05 -0500
  • ffb0793ff8
    Update azure-pipelines.yml Martin Kroeker 2021-09-05 23:04:46 +0200
  • b89b82d7ca
    Update azure-pipelines.yml Martin Kroeker 2021-09-05 20:56:13 +0200
  • 72f3ce5f08
    Add NO_AVX=1 fallbacks to newer generation x86_64 for completeness (#3360) Martin Kroeker 2021-09-05 20:35:48 +0200
  • 80e67e4b9e
    Update azure-pipelines.yml Martin Kroeker 2021-09-05 19:06:48 +0200
  • 5e7eaff3ff
    Update .travis.yml Martin Kroeker 2021-09-05 17:13:41 +0200
  • a555153383
    Add NO_AVX=1 fallbacks to newer generation x86_64 for completeness Martin Kroeker 2021-09-05 13:35:34 +0200
  • 311a2b69cd
    Update azure-pipelines.yml Martin Kroeker 2021-09-04 23:47:38 +0200
  • 735faf8819
    Update azure-pipelines.yml Martin Kroeker 2021-09-04 23:31:39 +0200
  • af19cda65a
    Add "recursive" option for IBM xlf compiler (#3359) Martin Kroeker 2021-09-04 18:26:59 +0200
  • 3590039ef3
    fix misedit Martin Kroeker 2021-09-04 14:46:53 +0200
  • 726a185f43
    Add "recursive" option for IBM xlf Martin Kroeker 2021-09-04 13:22:15 +0200
  • cd1a307ed1
    Add correct "recursive" option for xlf (from reference-lapack issue 606) Martin Kroeker 2021-09-04 13:18:04 +0200
  • fdc0317294
    Update azure-pipelines.yml Martin Kroeker 2021-09-04 13:00:12 +0200
  • e7b970f728
    Update azure-pipelines.yml Martin Kroeker 2021-09-04 12:42:56 +0200
  • 9489643019
    Update azure-pipelines.yml Martin Kroeker 2021-09-04 09:30:35 +0200
  • 41ee2b3d8f
    Update azure-pipelines.yml Martin Kroeker 2021-09-03 22:49:14 +0200
  • 215310f4f0
    Update azure-pipelines.yml Martin Kroeker 2021-09-03 22:21:26 +0200
  • 7406eabee9
    Update azure-pipelines.yml Martin Kroeker 2021-09-03 16:27:50 +0200
  • b0d3c6dbc2
    Update azure-pipelines.yml Martin Kroeker 2021-09-03 14:39:52 +0200
  • c5122dd770
    Add DYNAMIC_LIST as the Windows build is surprisingly slow Martin Kroeker 2021-09-02 18:40:24 +0200
  • 184d362e4e
    Update azure-pipelines.yml Martin Kroeker 2021-09-02 17:26:11 +0200
  • 2790773136
    Add a Windows build with mingw gcc and make Martin Kroeker 2021-09-02 14:37:34 +0200
  • a3e80069fb
    Merge pull request #3355 from martin-frbg/smallgemmcr Martin Kroeker 2021-09-02 00:27:23 +0200
  • f1e3305974
    Add workaround for Windows10 macro name clash Martin Kroeker 2021-09-01 21:36:50 +0200
  • 3cdfe33610
    Merge pull request #3352 from martin-frbg/3321-2n Martin Kroeker 2021-09-01 13:52:40 +0200
  • 47171e4b93
    Merge pull request #3354 from nsait-linaro/fix_gmemm_align_win_arm Martin Kroeker 2021-08-31 21:47:21 +0200
  • 7cddbf99b1 Make explicit conversion condition on _WIN64 flag Niyas Sait 2021-08-31 14:36:44 +0100
  • d1ed72fa87 [win/arm64]: Explicit casting for GMEMM_DEFAULT_ALIGN to create 64-bit value Niyas Sait 2021-08-24 06:09:29 +0100
  • 806221440b
    Merge pull request #3353 from guowangy/bf16-small-matrix-cooperlake Martin Kroeker 2021-08-30 20:39:51 +0200
  • cd10d1c03b
    Fix typo Martin Kroeker 2021-08-30 14:38:28 +0200
  • 2db1a99aca
    Clean up debug messages Martin Kroeker 2021-08-30 14:21:25 +0200
  • 619588fbab sbgemm: remove unnecessary b0 files Wangyang Guo 2021-08-30 17:48:11 +0800
  • f39301935c sbgemm: cooperlake: make sure hot buffer aligned to 64 Wangyang Guo 2021-08-13 18:43:41 +0800
  • 2e44ca0136 sbgemm: add missing cblas_sbgemm definition Wangyang Guo 2021-08-13 00:51:24 +0800
  • 7d27b182fc sbgemm: cooperlake: enable SBGEMM by small matrix path Wangyang Guo 2021-08-12 06:10:51 +0000
  • 1d83ca4bca Small Matrix: support BFLOAT16 data type Wangyang Guo 2021-08-12 03:14:18 +0000
  • bec9d9f63d
    Merge pull request #3335 from guowangy/small-matrix-latest Martin Kroeker 2021-08-29 22:33:33 +0200
  • 89fc5b8f4f
    Fix unmap logic Martin Kroeker 2021-08-29 19:50:24 +0200
  • 7fd12a5e69
    Add likely() hints for gcc Martin Kroeker 2021-08-29 13:54:51 +0200
  • 2ba9a567aa
    Fix typo Martin Kroeker 2021-08-28 17:14:59 +0200
  • b4b952eece
    Add auxiliary tracking space for thread buffer frees too Martin Kroeker 2021-08-28 17:03:53 +0200
  • 7d1becc575
    Allocate an auxiliary struct when running out of preconfigured threads Martin Kroeker 2021-08-28 14:18:36 +0200
  • b09c6f2ab2
    create a new control structure on the stack when we run out of preconfigured threads Martin Kroeker 2021-08-26 14:37:43 +0200
  • 6bb1805ed6
    Merge pull request #3348 from guowangy/skylakex-sgemv_t-fix Martin Kroeker 2021-08-25 22:43:45 +0200
  • 0f0a0be95d
    Merge pull request #3345 from nsait-linaro/windows_on_arm64 Martin Kroeker 2021-08-25 15:49:55 +0200
  • 874bead8b6
    Update .drone.yml Martin Kroeker 2021-08-25 10:47:06 +0200
  • dbbb39199f sgemv: skylakex: fix build warning Wangyang Guo 2021-08-25 07:13:00 +0000
  • e9acb46431 sgemv: skylakex: bug fix for sgemv_t kernel in corner case Wangyang Guo 2021-08-25 07:07:27 +0000
  • 3ebeb74c80
    Update .drone.yml Martin Kroeker 2021-08-24 23:53:57 +0200
  • fbf36e3157
    Update .drone.yml Martin Kroeker 2021-08-24 22:58:08 +0200
  • 2ac2551fa6
    Update .drone.yml Martin Kroeker 2021-08-24 22:06:32 +0200
  • d4e4bd3dcf
    Update .drone.yml Martin Kroeker 2021-08-24 19:45:01 +0200
  • 68f48b3f62
    Update .drone.yml Martin Kroeker 2021-08-24 19:29:20 +0200
  • ac552a5e34
    Update .drone.yml Martin Kroeker 2021-08-24 15:18:07 +0200
  • 95bf655be0
    Update Makefile.rule Martin Kroeker 2021-08-24 13:29:31 +0200
  • 0beb35ba7e
    Update .drone.yml Martin Kroeker 2021-08-23 21:49:15 +0200
  • 69f4d032a9
    Update .drone.yml Martin Kroeker 2021-08-23 19:44:23 +0200
  • eb9f4f297f
    Update .drone.yml Martin Kroeker 2021-08-23 08:19:32 +0200
  • b931a998b4
    Update .drone.yml Martin Kroeker 2021-08-23 01:13:17 +0200