Commit Graph

  • d92bd5be24
    Update KERNEL.POWER8 Martin Kroeker 2020-02-15 23:07:50 +0100
  • 46e4b12946
    Update KERNEL.POWER8 Martin Kroeker 2020-02-15 23:06:51 +0100
  • 5e94aa4877
    Merge pull request #2417 from marxin/make-ctest-verbose-for-drone Martin Kroeker 2020-02-15 21:57:41 +0100
  • 93f3e27574
    Merge pull request #2415 from marxin/add-cmake-to-gitignore Martin Kroeker 2020-02-15 21:57:03 +0100
  • 785c389b0e
    Merge pull request #2420 from martin-frbg/issue2396 Martin Kroeker 2020-02-15 21:56:16 +0100
  • c222b25b81
    Correct generation of GETRF files by the CMAKE build Martin Kroeker 2020-02-15 19:29:14 +0100
  • 221da8bf05
    Merge pull request #2411 from martin-frbg/fix2254-038 Martin Kroeker 2020-02-14 23:07:43 +0100
  • eb285b4d20
    Make ctest verbose for drone builder. Martin Liska 2020-02-14 10:45:31 +0100
  • cafdd999b8
    Update caxpy_power8.S Martin Kroeker 2020-02-13 22:44:09 +0100
  • 92ca92a46c
    Update caxpy_power8.S Martin Kroeker 2020-02-13 21:24:54 +0100
  • 486c35c5dc
    Update icamin_power8.S Martin Kroeker 2020-02-13 18:38:43 +0100
  • 0e05ea9bac
    Add CMake related files to .gitignore. Martin Liska 2020-02-13 14:51:55 +0100
  • 5ba3699f41
    Update isamin_power8.S Martin Kroeker 2020-02-13 00:00:32 +0100
  • 8eefa530cd
    Update isamax_power8.S Martin Kroeker 2020-02-12 23:59:50 +0100
  • de40d47edf
    Update isamin_power8.S Martin Kroeker 2020-02-12 23:57:48 +0100
  • 7c162b8a21
    Update isamax_power8.S Martin Kroeker 2020-02-12 23:56:57 +0100
  • 0544cbc806
    Fix syntax of endianness conditional Martin Kroeker 2020-02-12 20:00:29 +0100
  • 120d20731f
    Fix syntax of endianness conditional Martin Kroeker 2020-02-12 19:58:42 +0100
  • dc345d84df
    Fix syntax of endianness conditional and add gcc version check for workaround Martin Kroeker 2020-02-12 19:56:52 +0100
  • 616921fd91
    Merge pull request #27 from xianyi/develop Martin Kroeker 2020-02-12 19:16:14 +0100
  • 8a9e9a82a1
    Merge pull request #2410 from bartoldeman/fix-dscal-inline-asm Martin Kroeker 2020-02-12 15:38:37 +0100
  • 7ea5e07d1c Fix inline asm in dscal: mark x, x1 as clobbered. Fixes #2408 Bart Oldeman 2020-02-12 14:11:44 +0000
  • cb6ef49857
    Merge pull request #2407 from susilehtola/patch-2 Martin Kroeker 2020-02-11 13:04:44 +0100
  • 63994e1cdb
    Merge pull request #2405 from susilehtola/patch-1 Martin Kroeker 2020-02-11 13:03:35 +0100
  • 496e3019bc
    Merge pull request #2404 from martin-frbg/issue2395 Martin Kroeker 2020-02-11 13:00:36 +0100
  • 169be3f097
    Merge pull request #2403 from martin-frbg/issue2400 Martin Kroeker 2020-02-11 13:00:16 +0100
  • 6ccbb089c2
    Merge pull request #2402 from gxw-loongson/develop Martin Kroeker 2020-02-11 12:59:53 +0100
  • 59ebe3636a
    Merge pull request #2399 from martin-frbg/buffersize Martin Kroeker 2020-02-11 12:56:56 +0100
  • 5a6bba3061
    Patch out instances of Z15 in dynamic_zarch.c Susi Lehtola 2020-02-11 15:07:33 +1300
  • dff173e50e
    Fix typo in dynamic_zarch.c Susi Lehtola 2020-02-11 14:46:30 +1300
  • 7e5cbb6f35
    Fix bad conditional syntax that caused spurious application of USE_TRMM Martin Kroeker 2020-02-10 21:17:39 +0100
  • 303bdb673b
    Fix coretype detection for Intel extended models 6 and 7 Martin Kroeker 2020-02-10 19:17:32 +0100
  • 754433f420 Avoid printing the following information on mips and mips64 when check msa: "unrecognized command line option ‘-mmsa’" gxw 2020-02-10 19:11:45 +0800
  • 137fd21fea Avoid printing the following information on mips and mips64 platform when check msa: "unrecognized command line option ‘-mmsa’" gxw 2020-02-10 18:49:50 +0800
  • 7f0d523b42 Make BUFFER_SIZE configurable Martin Kroeker 2020-02-09 23:32:57 +0100
  • c353d8b106
    Make BUFFER_SIZE configurable Martin Kroeker 2020-02-09 23:30:22 +0100
  • 579be3aa9d Add configuration option for BUFFER_SIZE Martin Kroeker 2020-02-09 23:28:04 +0100
  • 449e8ea443
    Merge pull request #26 from xianyi/develop Martin Kroeker 2020-02-09 23:23:55 +0100
  • 3bec250cf9
    Increment version to 0.3.9.dev Martin Kroeker 2020-02-09 23:18:44 +0100
  • f03dd23e90 Increment version to 0.3.9.dev Martin Kroeker 2020-02-09 23:18:07 +0100
  • fb5eb47558
    Merge pull request #2398 from xianyi/develop v0.3.8 Martin Kroeker 2020-02-09 23:16:28 +0100
  • fa93d63365 Merge branch 'release-0.3.0' into develop Martin Kroeker 2020-02-09 23:16:06 +0100
  • 90e6c66a57
    Merge pull request #2397 from martin-frbg/038changes Martin Kroeker 2020-02-09 23:01:52 +0100
  • 32d97330b3 Update with changes from 0.3.8 Martin Kroeker 2020-02-09 23:00:36 +0100
  • 29eaf4b6d7
    Merge pull request #25 from xianyi/develop Martin Kroeker 2020-02-09 22:48:15 +0100
  • 47c1bf7f4d typo fixes Martin Kroeker 2020-02-09 01:06:40 +0100
  • 2b55f0ad30
    Merge pull request #2393 from martin-frbg/issue2388 Martin Kroeker 2020-02-09 01:00:33 +0100
  • a5b32ab06c
    Merge pull request #2390 from martin-frbg/pgi Martin Kroeker 2020-02-09 00:13:40 +0100
  • 50545b19d0
    Update CPU and OS support and document DYNAMIC_ARCH option in README.md Martin Kroeker 2020-02-09 00:06:07 +0100
  • b3cbd60d7a
    Remove PGI from list again as it is actually still not capable Martin Kroeker 2020-02-08 10:20:13 +0100
  • 70199d1905
    Merge pull request #2389 from Zeyiii/develop Martin Kroeker 2020-02-07 16:05:46 +0100
  • cfe63d8cc2
    Remove OpenMP libraries from link list Martin Kroeker 2020-02-07 16:03:51 +0100
  • d55b10830f
    Remove OpenMP libraries from link list Martin Kroeker 2020-02-07 16:02:17 +0100
  • c1c10cbb21
    Merge pull request #2384 from wjc404/develop Martin Kroeker 2020-02-07 13:47:12 +0100
  • 5989841524
    Add PGI to avx512-supporting compilers Martin Kroeker 2020-02-07 13:01:31 +0100
  • 68a43db358
    Fix utest compilation with PGI Martin Kroeker 2020-02-07 10:15:18 +0100
  • 9694037b23
    Set SUFFIX in tempfile commands, fix bad architecture option for PGI compiler in avx512 test Martin Kroeker 2020-02-07 10:09:25 +0100
  • 71faa1c1a7
    Merge pull request #24 from xianyi/develop Martin Kroeker 2020-02-07 10:03:02 +0100
  • 3447d04eaf
    Update dgemm_kernel_16x2_skylakex.c wjc404 2020-02-06 02:14:10 +0000
  • 8b5cdcc64c
    Update sgemm_kernel_8x4_haswell.c wjc404 2020-02-06 01:47:46 +0000
  • 4e00d96a78
    Update dgemm_kernel_16x2_skylakex.c wjc404 2020-02-06 01:46:36 +0000
  • ce9ea8f826 Fix another branch w00421467 2020-02-05 15:07:18 +0800
  • 0b909203cb Fix bugs in benchmark of gemv w00421467 2020-02-05 14:53:37 +0800
  • 096da2f51a
    Update dgemm_kernel_16x2_skylakex.c wjc404 2020-02-05 13:36:57 +0800
  • 2f96a2c55b
    Update trmm_R.c wjc404 2020-02-05 10:15:02 +0800
  • 833bd0f8ff
    Update trmm_L.c wjc404 2020-02-05 10:09:41 +0800
  • 77b8f49556
    Update level3_thread.c wjc404 2020-02-04 20:33:08 +0800
  • 1c3e20ce48
    Update level3.c wjc404 2020-02-04 20:30:23 +0800
  • 83b6be7976
    Update param.h wjc404 2020-02-04 19:55:26 +0800
  • 081b188529
    Update KERNEL.SKYLAKEX wjc404 2020-02-03 21:38:08 +0800
  • f3f969f681
    Update param.h wjc404 2020-02-03 21:34:12 +0800
  • 8019e70211
    AVX512 16x2 DGEMM kernel wjc404 2020-02-03 21:32:56 +0800
  • 8d2a796f49
    Merge pull request #2378 from martin-frbg/issue2377 Martin Kroeker 2020-01-30 17:07:19 +0100
  • 8dc9fd4dfe
    Add -march option for AVX512 Martin Kroeker 2020-01-30 12:41:18 +0100
  • abc67bdd74
    Merge pull request #2375 from ewanglong/master Martin Kroeker 2020-01-30 10:27:29 +0100
  • 1f62a82789
    Merge pull request #2376 from wjc404/develop Martin Kroeker 2020-01-23 21:50:19 +0100
  • e9fb8f62b1
    Update level3_gemm3m_thread.c wjc404 2020-01-22 17:40:03 +0000
  • fbf4f48f4a fix a few performance drop in some matrix size per data type Wang,Long 2020-01-22 15:07:50 +0000
  • b9ad450295
    Merge pull request #2373 from Qiyu8/optimize#gemmbeta Martin Kroeker 2020-01-21 15:05:38 +0100
  • e011ad820a
    Merge pull request #2372 from martin-frbg/winexit Martin Kroeker 2020-01-21 14:56:45 +0100
  • ff42e68652 Optimize genenal Gemm Beta Qiyu8 2020-01-20 11:49:42 +0800
  • 23f322f997
    Do not run any cleanup if the program is exiting anyway Martin Kroeker 2020-01-19 13:28:27 +0100
  • 093d37de8d
    Merge pull request #2371 from martin-frbg/issue2370 Martin Kroeker 2020-01-18 20:39:34 +0100
  • d65e9a2bbd
    Merge pull request #2253 from thrasibule/xerbla Martin Kroeker 2020-01-18 20:39:04 +0100
  • 78100b8093
    Free Windows thread memory with MEM_RELEASE rather than MEM_DECOMMIT Martin Kroeker 2020-01-18 15:06:39 +0100
  • 70f45749b9
    Merge pull request #2367 from wjc404/develop Martin Kroeker 2020-01-15 21:13:43 +0100
  • e5dcdeb550
    Update sgemm_direct_skylakex.c wjc404 2020-01-13 16:59:23 +0800
  • 952cc2ba38
    Update sgemm_kernel_16x4_skylakex_2.c wjc404 2020-01-13 16:58:54 +0800
  • feaafbedd3
    make skylakex sgemm code more friendly for readers wjc404 2020-01-13 16:28:41 +0800
  • 1c67567008
    improve skylakex paralleled sgemm performance wjc404 2020-01-13 16:26:03 +0800
  • 4e979bf75b
    Merge pull request #2366 from martin-frbg/install390 Martin Kroeker 2020-01-13 09:00:21 +0100
  • daa4310db5
    Install new lapack.h Martin Kroeker 2020-01-12 22:00:50 +0100
  • b8f3605132
    Merge pull request #23 from xianyi/develop Martin Kroeker 2020-01-12 21:57:23 +0100
  • b36018be6d
    Merge pull request #2365 from wjc404/develop Martin Kroeker 2020-01-09 23:23:09 +0100
  • 3a100b2797
    Update KERNEL.SKYLAKEX wjc404 2020-01-09 13:48:41 +0800
  • 38742d5547
    Merge pull request #2361 from wjc404/develop Martin Kroeker 2020-01-08 16:20:28 +0100
  • bb5c9b2157
    Leave all thread cleanup to Windows when DLL_PROCESS_DETACH happens Martin Kroeker 2020-01-07 22:29:20 +0100
  • bd4c032f52
    Update sgemm_kernel_8x4_haswell.c wjc404 2020-01-07 11:22:46 +0800
  • 9dc9b7b95e
    Update sgemm_kernel_8x4_haswell.c wjc404 2020-01-06 20:11:36 +0800
  • 9f5cdc49d4
    Update CONTRIBUTORS.md wjc404 2020-01-06 12:28:43 +0800