Commit Graph

  • 1937b4e435
    Add Elbrus e2k architecture detection Martin Kroeker 2022-01-22 18:27:38 +0100
  • 00f44bfff7 cmake: Check if Fortran compiler is usable before enabling it. Markus Mützel 2022-01-21 13:27:17 +0100
  • c1c0d5ce1d
    Merge pull request #3492 from binebrank/arm_sve_zgemm Martin Kroeker 2022-01-18 21:36:33 +0100
  • 19d435b1b3 update armv8sve + contributors Bine Brank 2022-01-18 08:28:31 +0100
  • f158d59087 adapt CMake Bine Brank 2022-01-17 22:36:48 +0100
  • 8ac2c1daf0
    Merge pull request #3514 from martin-frbg/issue3513 Martin Kroeker 2022-01-17 19:22:18 +0100
  • 40003f8edb
    Fix pivot offset calculation for negative incx Martin Kroeker 2022-01-17 00:11:18 +0100
  • 57e2a72f40
    Fix pivot offset calculation for negative incx Martin Kroeker 2022-01-17 00:10:21 +0100
  • 3b6293f5a0
    Fix offset calculation for negative incx Martin Kroeker 2022-01-17 00:09:14 +0100
  • afa0cece5c
    Fix pivot offset calculation for negative incx Martin Kroeker 2022-01-17 00:08:20 +0100
  • eca2f50b48
    Fix pivot offset calculation for negative incx Martin Kroeker 2022-01-17 00:07:33 +0100
  • 0e9e951306
    Fix pivot offset calculation for negative incx Martin Kroeker 2022-01-17 00:06:41 +0100
  • 1b49ef8dcf
    Fix pivot index for negative increments Martin Kroeker 2022-01-17 00:05:33 +0100
  • b6a445cfd8 adapt Makefile for SVE trsm Bine Brank 2022-01-16 21:40:56 +0100
  • 0fb6cc07bf fix ztrsm lt/ut copy Bine Brank 2022-01-16 21:39:57 +0100
  • f1315288a8 add sve ztrsm Bine Brank 2022-01-15 22:27:25 +0100
  • aaa2b1a861 fix sve dtrsm kernels Bine Brank 2022-01-15 21:02:14 +0100
  • 8071e179f1 add remaining sve trsm copy kernels Bine Brank 2022-01-11 21:16:38 +0100
  • f87468ac91 trsm_lncopy_sve Bine Brank 2022-01-10 21:45:37 +0100
  • e8939b3d30 sve trsmRN and trsmRT Bine Brank 2022-01-10 20:42:20 +0100
  • 5188aede5d
    Merge pull request #3511 from martin-frbg/cmakeutils Martin Kroeker 2022-01-10 09:12:52 +0100
  • a9e297e476
    Fix handling of ifdef/ifndef Martin Kroeker 2022-01-09 23:31:59 +0100
  • 098672b51b add trsm_kernel_LT_sve Bine Brank 2022-01-09 20:11:47 +0100
  • be7e55880c sve trsm_kernel_LN Bine Brank 2022-01-09 19:40:04 +0100
  • 499ae5e8f7
    Merge pull request #3510 from martin-frbg/issue3505 Martin Kroeker 2022-01-09 14:50:51 +0100
  • b6b024232d
    Merge pull request #3508 from snadampal/v1_n2 Martin Kroeker 2022-01-09 14:50:26 +0100
  • 2573ccfb2e
    make DYNAMIC_ARCH option available to getarch_2nd/param.h Martin Kroeker 2022-01-08 23:50:34 +0100
  • f1ac59f200
    Forward DYNAMIC_ARCH option to Makefile.prebuild Martin Kroeker 2022-01-08 23:48:58 +0100
  • 15d4b37913
    SkylakeX: match parameters to dgemm kernels for dyn/non-dyn Martin Kroeker 2022-01-08 23:48:13 +0100
  • 19c8f615dc OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics Sunita Nadampalli 2022-01-07 00:28:17 +0000
  • cbcea149f0 update contributors Bine Brank 2022-01-06 10:29:35 +0100
  • bb33446b40 fix makefile.L3 Bine Brank 2022-01-06 10:26:11 +0100
  • f33543d029 combine zchemm into single file Bine Brank 2022-01-05 14:42:37 +0100
  • 0c91d043ae adapt CMake for SVE Bine Brank 2022-01-05 14:36:39 +0100
  • 39ab219704 sve copy functions for cgemm chemm zsymm Bine Brank 2022-01-05 09:12:22 +0100
  • 18102ae8c3 add cgemm ctrmm sve kernels Bine Brank 2022-01-05 09:09:18 +0100
  • 87537b8c55 modify sve zgemmcopy kernels Bine Brank 2022-01-05 09:07:28 +0100
  • d30157d891 update configuration of kernels for A64FX and ARMV8SVE Bine Brank 2022-01-05 09:00:54 +0100
  • 07fa6fa3b1 configure Makefile for sve Bine Brank 2022-01-05 08:57:51 +0100
  • 2e2c02b762 fix sve ztrmm kernel Bine Brank 2022-01-04 14:42:07 +0100
  • 68c414d3a6 ztrmm sve copy functions Bine Brank 2022-01-04 14:40:59 +0100
  • ce329ab686 add sve zhemm copy routines Bine Brank 2022-01-03 15:56:05 +0100
  • 0140373802 add sve ztrmm Bine Brank 2022-01-02 19:15:33 +0100
  • ca2637af70
    Update azure-pipelines.yml Martin Kroeker 2022-01-02 13:24:26 +0100
  • 0ea61108e3
    Update azure-pipelines.yml Martin Kroeker 2022-01-02 12:11:26 +0100
  • b9e9431821
    Update azure-pipelines.yml Martin Kroeker 2022-01-01 23:17:12 +0100
  • ffb10f1872
    Update azure-pipelines.yml Martin Kroeker 2022-01-01 22:43:43 +0100
  • 4f7e6f01dd
    Add SDE job that builds on Sandybridge, tests on SkylakeX Martin Kroeker 2022-01-01 20:14:27 +0100
  • ecf034b250
    Merge pull request #3502 from jgillis/develop Martin Kroeker 2022-01-01 12:12:32 +0100
  • f8b1ca5039
    Merge pull request #3504 from martin-frbg/issue3503 Martin Kroeker 2022-01-01 11:43:17 +0100
  • b329e45288
    Guard against omp_get_num_places returning zero Martin Kroeker 2022-01-01 00:46:23 +0100
  • fa2c9de621
    Update azure-pipelines.yml Martin Kroeker 2021-12-31 18:37:50 +0100
  • f7b6912868 ztrmm sve copy kernels Bine Brank 2021-12-30 21:00:16 +0100
  • ea3db69faa
    Fix cmake crosscompilation for core2 target jgillis 2021-12-29 22:50:20 +0100
  • 40b14e4957 fix zgemm kernel Bine Brank 2021-12-29 11:42:04 +0100
  • ee823b6ed9
    Merge pull request #3500 from martin-frbg/osx_dyn_xerbla Martin Kroeker 2021-12-28 22:54:27 +0100
  • 6cae44d4f7
    Ensure that the right xerbla gets included in OSX DYNAMIC_ARCH builds Martin Kroeker 2021-12-28 19:06:55 +0100
  • a06b4aff52
    Merge pull request #3496 from yuanhec/develop Martin Kroeker 2021-12-28 18:51:56 +0100
  • 9d455b1b09 Merge remote-tracking branch 'upstream/develop' into develop yuanhecai 2021-12-27 09:50:57 +0800
  • 6ec4aab875 zgemm sve copy routines Bine Brank 2021-12-26 17:05:46 +0100
  • 878064f394 sve zgemm kernel Bine Brank 2021-12-26 08:44:05 +0100
  • d97a3e5a5f
    Update KERNEL.SKYLAKEX Martin Kroeker 2021-12-25 13:27:49 +0100
  • 892ed1e53b
    Update param.h Martin Kroeker 2021-12-25 13:26:35 +0100
  • 683a7548bf added macros for sve zgemm kernels Bine Brank 2021-12-25 11:46:41 +0100
  • e62e797d3a
    Update KERNEL.SKYLAKEX Martin Kroeker 2021-12-24 22:54:40 +0100
  • b54b3bbdcc
    Update param.h Martin Kroeker 2021-12-24 22:53:39 +0100
  • 7b146e590c
    fix function typecast Martin Kroeker 2021-12-24 20:01:52 +0100
  • e9a0e52201
    fix function typecast Martin Kroeker 2021-12-24 20:00:50 +0100
  • 2db0b2e445 Fixed MSA enabled optimization on Loongson-3A4000 yuanhecai 2021-12-23 20:04:27 +0800
  • 253670383f
    Merge pull request #3491 from gxw-loongson/develop Martin Kroeker 2021-12-22 08:34:12 +0100
  • 9809931eb4
    clean up unused variables and unreachable statements Martin Kroeker 2021-12-21 18:53:55 +0100
  • 6b407a16cb
    fix function typecasts Martin Kroeker 2021-12-21 18:51:28 +0100
  • aecb4a5e8d
    fix function typecasts Martin Kroeker 2021-12-21 18:50:22 +0100
  • c49d46f25f
    fix function typecast Martin Kroeker 2021-12-21 18:49:18 +0100
  • 64365c919e
    fix function typecasts Martin Kroeker 2021-12-21 18:47:35 +0100
  • d1ee6ff73f
    fix function typecasts Martin Kroeker 2021-12-21 18:45:28 +0100
  • 07fe5b19a4
    typecast function pointers Martin Kroeker 2021-12-21 12:31:54 +0100
  • e3c9947c0f prepare kernel for sve zgemm Bine Brank 2021-12-21 11:19:27 +0100
  • 8d9b9c6b2a loongarch64: Optimize dgemm_kernel gxw 2021-12-21 09:22:59 +0800
  • 8cec83bdfb
    Update version to 0.3.19.dev Martin Kroeker 2021-12-19 21:22:19 +0100
  • 894fde9bfe
    Update version to 0.3.19.dev Martin Kroeker 2021-12-19 21:21:47 +0100
  • d1c6270c52
    Merge pull request #3489 from xianyi/release-0.3.0 Martin Kroeker 2021-12-19 21:21:13 +0100
  • 2480e5046e
    Update version to 0.3.19 v0.3.19 Martin Kroeker 2021-12-19 20:55:57 +0100
  • 488911486a
    Merge pull request #3488 from xianyi/develop Martin Kroeker 2021-12-19 20:54:49 +0100
  • 54a0c0bce3
    Merge branch 'release-0.3.0' into develop Martin Kroeker 2021-12-19 16:35:07 +0100
  • 6025daca63
    Update version to 0.3.19 Martin Kroeker 2021-12-19 16:32:04 +0100
  • e545614cd0
    Merge pull request #3487 from martin-frbg/0319changes Martin Kroeker 2021-12-19 16:30:47 +0100
  • b6001a2ee3
    Update with 0.3.19 changes Martin Kroeker 2021-12-19 14:34:14 +0100
  • 9c8d1e013f
    Merge pull request #3486 from martin-frbg/nvhpc Martin Kroeker 2021-12-18 23:09:30 +0100
  • ed430cd963
    Update -tp option for recent nvfortran on x86_64 Martin Kroeker 2021-12-18 21:56:26 +0100
  • b3f4b8c95a
    Merge pull request #3485 from martin-frbg/issue3453 Martin Kroeker 2021-12-17 11:08:36 +0100
  • 6ed52576f8
    Add feature-based fallback for unknown x86_64 cpus Martin Kroeker 2021-12-16 22:02:49 +0100
  • 126ad48991
    Merge pull request #3484 from martin-frbg/issue3481 Martin Kroeker 2021-12-16 21:50:28 +0100
  • f67a0620a3
    Merge pull request #3480 from wzgpeter/develop Martin Kroeker 2021-12-16 21:50:06 +0100
  • 449fb7d849
    Merge pull request #3478 from ffontaine/develop Martin Kroeker 2021-12-16 21:49:19 +0100
  • 7a7fbb11c3
    define "unlikely" on non-cygwin too Martin Kroeker 2021-12-16 17:28:28 +0100
  • b31349c22a
    Open up delayed (re)init to non-Cygwin OS as well Martin Kroeker 2021-12-16 16:58:12 +0100
  • 4d61e453cc
    Merge pull request #3483 from martin-frbg/issue3482 Martin Kroeker 2021-12-16 11:54:20 +0100
  • f3b51ec608
    move brace inside the ifdef block Martin Kroeker 2021-12-16 09:37:58 +0100
  • 92b7b949dd fix bug in zscal function Wu Zhigang 2021-12-15 00:22:19 -0800