Commit Graph

  • c270c7b01c fix bug in zscal function Wu Zhigang 2021-12-15 00:22:19 -0800
  • a0cc119f26 Makefile: also consider -O, -Og and -Os when stripping flags Thomas De Schampheleire 2021-12-14 23:36:16 +0100
  • c8d05aa7a5
    Move the threads overflow flag under the protection of the local blas lock (#3476) Martin Kroeker 2021-12-13 08:34:52 +0100
  • 2f220fdcf9
    Add files via upload Martin Kroeker 2021-12-12 21:39:02 +0100
  • 89e1a67dac
    Update .travis.yml Martin Kroeker 2021-12-12 20:06:28 +0100
  • 23290003f2
    Update .travis.yml Martin Kroeker 2021-12-12 19:11:54 +0100
  • b0a590f4fe
    Merge pull request #3475 from wjc404/optimize-A53-dgemm Martin Kroeker 2021-12-12 19:09:08 +0100
  • f4d1f0333b
    Merge pull request #3474 from rafaelcfsousa/rafael/cmake_power Martin Kroeker 2021-12-12 19:08:27 +0100
  • 6a0497c3ed
    Move accesses to the overflow flag into the scope of the blas lock Martin Kroeker 2021-12-12 14:24:01 +0100
  • b610d2de37 optimize cgemm on ARM cortex A53 & cortex A55 Jia-Chen 2021-12-12 17:22:52 +0800
  • 697e2752d7
    Merge pull request #3464 from binebrank/arm_sve_sgemm Martin Kroeker 2021-12-11 20:35:22 +0100
  • 60684d636b
    Update .travis.yml Martin Kroeker 2021-12-11 19:11:17 +0100
  • ffb3893266
    Update .travis.yml Martin Kroeker 2021-12-11 18:26:35 +0100
  • a8f62a347b fix UNROLL_MN and add to targets for SVE Bine Brank 2021-12-11 16:37:23 +0100
  • 774267fdac adjust Makefile.L3 for SVE Bine Brank 2021-12-11 16:35:08 +0100
  • d38110a5ce Use CMake variables instead of as Rafael Cardoso Fernandes Sousa 2021-12-10 17:35:28 -0600
  • 23a7561353 Fix error cmake (small kernels) Rafael Cardoso Fernandes Sousa 2021-12-09 09:57:39 -0600
  • 214fbcee15 Fix cmake for power Rafael Cardoso Fernandes Sousa 2021-12-09 08:28:17 -0600
  • f7f7fea0dc
    Merge pull request #3472 from kavanabhat/p10_aixas_p8 Martin Kroeker 2021-12-09 07:28:57 +0100
  • 2241068c26
    Merge pull request #3469 from martin-frbg/issue2986 Martin Kroeker 2021-12-08 22:19:32 +0100
  • 3e9a52869c
    Fix ar path in ARMV7 Darwin NDK build on Azure (#3473) Martin Kroeker 2021-12-08 22:18:44 +0100
  • 847e335aac
    Update azure-pipelines.yml Martin Kroeker 2021-12-08 18:13:26 +0100
  • c0cb437bd3
    Update azure-pipelines.yml Martin Kroeker 2021-12-08 16:33:27 +0100
  • f215011496
    Fix ar path in ARMV7 Darwin NDK build Martin Kroeker 2021-12-08 15:46:05 +0100
  • eee3381cbe Fallback for Power kernels kavanabhat 2021-12-08 03:52:23 -0600
  • 02c7390aff
    Update .travis.yml Martin Kroeker 2021-12-07 13:50:41 +0100
  • 5378046abd
    roll back DGEMM kernels to 4x8 when compiling for DYNAMIC_ARCH Martin Kroeker 2021-12-06 19:43:54 +0100
  • dd1f645371
    switch DGEMM unroll parameters for SkylakeX if DYNAMIC_ARCH Martin Kroeker 2021-12-06 19:42:51 +0100
  • a1fea1fe2a sgemm v2x8 SVE kernel Bine Brank 2021-12-05 18:47:29 +0100
  • 2ae73a2b34
    Merge pull request #3468 from martin-frbg/issue3467 Martin Kroeker 2021-12-05 15:52:44 +0100
  • 8d11278e28
    Fix hardcoded library name Martin Kroeker 2021-12-05 14:38:41 +0100
  • abe1ce3434 strmm sve v1x8 kernel Bine Brank 2021-12-05 14:03:08 +0100
  • ea09355eae
    Fix DYNAMIC_ARCH builds with CMAKE on OSX and add corresponding test to Azure CI (#3409) Martin Kroeker 2021-12-04 22:24:02 +0100
  • d62dc3e854
    Update azure-pipelines.yml Martin Kroeker 2021-12-04 19:28:47 +0100
  • 7986da09d4
    Update CMakeLists.txt Martin Kroeker 2021-12-04 14:45:45 +0100
  • 8fe42d719e
    Update CMakeLists.txt Martin Kroeker 2021-12-04 10:21:38 +0100
  • 54d321d742
    Merge pull request #3466 from rafaelcfsousa/rafael/small_matrix_p10 Martin Kroeker 2021-12-03 12:12:20 +0100
  • c248442df4
    Merge pull request #3465 from kavanabhat/develop Martin Kroeker 2021-12-03 12:11:43 +0100
  • 1470b7e4de
    Delete test_zhemv.c Martin Kroeker 2021-12-03 11:41:53 +0100
  • 0882db30a2
    Merge pull request #3455 from cenewcombe/develop Martin Kroeker 2021-12-03 10:01:20 +0100
  • db7f6e1b4c
    Update CMakeLists.txt Martin Kroeker 2021-12-03 10:00:27 +0100
  • 9a45b5123f
    Update Makefile.system kavanabhat 2021-12-02 13:29:38 +0530
  • 4e4297f5e5
    Update CMakeLists.txt Martin Kroeker 2021-12-01 21:57:31 +0100
  • e2a78c083f
    Update CMakeLists.txt Martin Kroeker 2021-12-01 19:29:48 +0100
  • 84125e4035
    Merge pull request #1 from kavanabhat/as_check_fix kavanabhat 2021-12-01 20:30:43 +0530
  • af4ec2653b
    Update CMakeLists.txt Martin Kroeker 2021-12-01 15:06:18 +0100
  • 7b5b93037d
    Fix truncated assembler checks kavanabhat 2021-12-01 19:30:40 +0530
  • ff3f78d2e5
    Update CMakeLists.txt Martin Kroeker 2021-12-01 11:22:02 +0100
  • 0628233ccf
    Update CMakeLists.txt Martin Kroeker 2021-11-30 22:25:49 +0100
  • a140f1801f
    Update CMakeLists.txt Martin Kroeker 2021-11-30 17:33:52 +0100
  • c21bf68909
    Update CMakeLists.txt Martin Kroeker 2021-11-30 13:20:09 +0100
  • f52ff40606
    Update CMakeLists.txt Martin Kroeker 2021-11-30 10:29:14 +0100
  • 0de36f7b5c trmm sve copy fucntions for single precision Bine Brank 2021-11-29 21:25:05 +0100
  • 9d855c0ab7
    Update CMakeLists.txt Martin Kroeker 2021-11-29 20:41:52 +0100
  • 21501f7bc3
    Update CMakeLists.txt Martin Kroeker 2021-11-28 23:55:25 +0100
  • fa7dc9ecf7
    Update CMakeLists.txt Martin Kroeker 2021-11-28 23:37:07 +0100
  • c78fdcc80d [POWER] Add support for SMALL_MATRIX_OPT Rafael Cardoso Fernandes Sousa 2021-11-16 14:47:41 -0600
  • 86ae89bf33 add sgemm kernel and copy functions for sgemm and ssymm Bine Brank 2021-11-28 18:12:47 +0100
  • 454edd741c
    Merge pull request #3425 from binebrank/arm_sve_dgemm Martin Kroeker 2021-11-26 16:14:55 +0100
  • bcfbdc81b2
    Merge pull request #3459 from rafaelcfsousa/fix_cmake Martin Kroeker 2021-11-26 15:19:24 +0100
  • 7c6370cbfd
    Merge pull request #3462 from martin-frbg/azure-alpine2 Martin Kroeker 2021-11-26 13:40:23 +0100
  • fbfc8b1b83
    Update alpine-chroot-install again Martin Kroeker 2021-11-26 13:39:49 +0100
  • ca65a4e91d update CONTRIBUTORS.md Bine Brank 2021-11-26 13:11:19 +0100
  • 1af73ce38e Adapt CMake for SVE Bine Brank 2021-11-26 10:35:01 +0100
  • e7fca060db
    Merge pull request #3457 from wjc404/optimize-A53-dgemm Martin Kroeker 2021-11-26 10:30:47 +0100
  • bc4c98de26
    Merge pull request #3456 from martin-frbg/issue3444 Martin Kroeker 2021-11-26 10:29:28 +0100
  • c3b1e55bdc
    AzureCI: Fetch alpine-chroot-install from master to get key updates (#3460) Martin Kroeker 2021-11-26 09:38:41 +0100
  • fcddd32cbc
    Update azure-pipelines.yml Martin Kroeker 2021-11-25 23:03:33 +0100
  • 359dc11cf3
    Update azure-pipelines.yml Martin Kroeker 2021-11-25 22:04:47 +0100
  • d6af505bd6
    Update azure-pipelines.yml Martin Kroeker 2021-11-25 20:33:28 +0100
  • ed688a1e4a
    Fetch alpine-chroot-install from master to get key updates Martin Kroeker 2021-11-25 20:01:21 +0100
  • 5c1cd5e0c2 MOD: add comments to a53 zgemm kernel Jia-Chen 2021-11-25 22:48:48 +0800
  • d5c9353f1b Modify the order that cmake set the KERNEL variables (generic now is fallback) Rafael Cardoso Fernandes Sousa 2021-11-24 20:07:20 -0600
  • fb891f33da Fix the cmake parser to identify more patterns Rafael Cardoso Fernandes Sousa 2021-11-24 14:07:28 -0600
  • 9f59b19fcd MOD: optimize zgemm on cortex-A53/cortex-A55 Jia-Chen 2021-11-24 21:51:45 +0800
  • f4da23dcb6 reduced dgemm_unroll_m to work with 128-bit sve Bine Brank 2021-11-23 21:18:08 +0100
  • 531a28b6a0 removed unused code (compiler warnings) Bine Brank 2021-11-22 10:12:34 +0100
  • 9b9cb90bb1 modify Makefile for SVE copy Bine Brank 2021-11-22 09:54:20 +0100
  • 9388f05a3c configure SVE Makefile Bine Brank 2021-11-21 18:33:43 +0100
  • b58d4f31ab some clean-up & commentary Bine Brank 2021-11-21 14:56:27 +0100
  • 52a3f004a0
    Fix unintended reversion of recent CortexA53 changes Martin Kroeker 2021-11-20 23:54:48 +0100
  • a3cd36acff
    Add CMAKE support for cross-compiling to MIPS32 Martin Kroeker 2021-11-20 17:34:28 +0100
  • b7df500106
    Add generic mips32 target Martin Kroeker 2021-11-20 17:31:51 +0100
  • 19ccef5fb1
    Add generic MIPS32 target Martin Kroeker 2021-11-20 17:31:11 +0100
  • e6ed4be02e symm SVE copy rutines Bine Brank 2021-11-20 16:35:29 +0100
  • feeb8283a5 Fix unsafe read during final iteration of zsymv_L_sse2.S Caroline Newcombe 2021-11-19 14:29:32 -0600
  • ec4daf420f
    Merge pull request #3451 from wjc404/optimize-A53-dgemm Martin Kroeker 2021-11-18 18:17:27 +0100
  • 302f22693a MOD: optimize normal DGEMM on ARMV8 cortex-A53 & cortex-A55 Jia-Chen 2021-11-18 21:14:43 +0800
  • a3d41cbbed
    Update dgemm_kernel_4x4_cortexA53.c Martin Kroeker 2021-11-18 11:54:42 +0100
  • 9605ba5b5a
    Update dgemm_kernel_4x4_cortexA53.c Martin Kroeker 2021-11-18 10:43:02 +0100
  • 12b03acffb
    Add files via upload Martin Kroeker 2021-11-18 10:15:23 +0100
  • 941ac120d8
    Add files via upload Martin Kroeker 2021-11-18 10:00:28 +0100
  • 62ae58851a
    Add files via upload Martin Kroeker 2021-11-18 09:59:33 +0100
  • e086462e50
    Update CMakeLists.txt Martin Kroeker 2021-11-17 18:49:28 +0100
  • 75890a8aae
    Update CMakeLists.txt Martin Kroeker 2021-11-17 17:22:58 +0100
  • 06ada5be0f
    Update CMakeLists.txt Martin Kroeker 2021-11-17 16:39:54 +0100
  • 7b825531a6
    Merge pull request #3450 from mmuetzel/suffix-nofortran Martin Kroeker 2021-11-16 23:58:09 +0100
  • de2ed66596 cmake: Set SUFFIX64 also for NOFORTRAN Markus Mützel 2021-11-15 08:53:52 +0100
  • dfa4194615
    Update CMakeLists.txt Martin Kroeker 2021-11-14 23:28:55 +0100
  • f7fecfff04
    Update azure-pipelines.yml Martin Kroeker 2021-11-14 22:23:34 +0100