Commit Graph

  • d122242a1c
    Revert "specify TRMMKERNELS" Martin Kroeker 2018-04-25 22:43:33 +0200
  • a8ed428bab
    Disable multithreading in ztrmv Martin Kroeker 2018-04-25 22:35:46 +0200
  • 1da365312a
    Merge pull request #1538 from martin-frbg/arm7utest Martin Kroeker 2018-04-25 08:38:58 +0200
  • 85944c4134
    restore P5600 options Martin Kroeker 2018-04-24 23:09:12 +0200
  • 2d0929fa7c
    Move the test for zero incx,incy in ARMV7 ROT Martin Kroeker 2018-04-24 22:43:00 +0200
  • 125343cc88
    Drop test for zero incx,incy in armv7 AXPY Martin Kroeker 2018-04-24 22:39:50 +0200
  • 8a3b6fa108
    Use generic zrot.c on ppc64/POWER6 to work around utest failure from … (#1535) Martin Kroeker 2018-04-23 19:05:49 +0200
  • ae8e985935
    Update KERNEL.POWER6 Martin Kroeker 2018-04-23 18:46:19 +0200
  • 467996dce1
    Use generic zrot.c on ppc64/POWER6 to work around utest failure from #1469 Martin Kroeker 2018-04-23 16:14:52 +0200
  • 78694f1b7e
    Merge pull request #1534 from xianyi/revert-1333-haswell32 Martin Kroeker 2018-04-22 23:34:17 +0200
  • 9c5518319a
    Revert "Fix 32bit HASWELL builds" revert-1333-haswell32 Martin Kroeker 2018-04-22 20:20:04 +0200
  • 86f49c529d
    Merge pull request #1532 from martin-frbg/utest-cblas Martin Kroeker 2018-04-20 23:44:15 +0200
  • 625c74a38f
    fork utest depends on CBLAS Martin Kroeker 2018-04-20 15:43:59 +0200
  • 5fcaca6438
    fork utest depends on CBLAS Martin Kroeker 2018-04-20 15:42:13 +0200
  • 4fcdd24459
    Merge pull request #1530 from ashwinyes/develop_20180419_Tx2AutoDetect Martin Kroeker 2018-04-19 14:10:57 +0200
  • 68a3c4fca6 ARM64: Enable Auto Detection of ThunderX2T99 Ashwin Sekhar T K 2018-04-19 09:05:25 +0000
  • 0ee395db35 Fixed TRMM and SYMM for RISCV Jerry Zhao 2018-04-18 18:03:32 -0700
  • 307592d8aa
    Specify trmm kernels as the generic gemm kernel is unsuitable for trmm Martin Kroeker 2018-04-19 00:00:32 +0200
  • a93066e348
    Correct choice of c/z asum kernel on mips32 Martin Kroeker 2018-04-18 23:06:14 +0200
  • 9520bba7fa
    Add KERNEL file for 1004K Martin Kroeker 2018-04-17 22:14:11 +0200
  • 9a47daa532
    Fix mips32 identification and add MIPS 1004K (MT7621 SoC) Martin Kroeker 2018-04-17 22:11:59 +0200
  • c167a3d6f4 Added RISCV build Jerry Zhao 2018-04-16 12:34:43 -0700
  • 0c4718c57a
    Merge pull request #1523 from martin-frbg/utest_waith Martin Kroeker 2018-04-15 13:09:30 +0200
  • f29389c7ac
    Merge pull request #1520 from martin-frbg/cpucounts Martin Kroeker 2018-04-14 22:24:34 +0200
  • 734d7c6a93
    Include sys/types.h for proper typedefs related to wait() Martin Kroeker 2018-04-14 18:59:46 +0200
  • 7c861605b2
    Catch invalid cpu count returned by CPU_COUNT_S Martin Kroeker 2018-04-14 18:29:10 +0200
  • 2ca0faf495
    Merge pull request #1515 from martin-frbg/mipsdot Martin Kroeker 2018-04-11 08:21:25 +0200
  • 0fe434598b
    Fix precision of mips dsdot Martin Kroeker 2018-04-10 23:30:59 +0200
  • 15c437e092
    Merge pull request #1512 from ararslan/aa/travis-macos-2 Martin Kroeker 2018-04-07 23:31:26 +0200
  • b966bd79d5
    Add a BINARY=32 build to macOS Alex Arslan 2018-04-07 12:29:57 -0700
  • 2e988dbf35
    Add macOS to the Travis testing matrix Alex Arslan 2018-04-07 10:56:34 -0700
  • be6090d396
    Merge pull request #1511 from xianyi/revert-1510-aa/travis-macos Martin Kroeker 2018-04-07 13:29:31 +0200
  • daae8fd197
    Revert "Add macOS to the Travis testing matrix" revert-1510-aa/travis-macos Martin Kroeker 2018-04-07 13:27:24 +0200
  • 20c6c38e51
    Merge branch 'develop' into atomic Martin Kroeker 2018-04-07 12:09:39 +0200
  • a1fb7670f7
    Merge pull request #1510 from ararslan/aa/travis-macos Martin Kroeker 2018-04-07 12:07:12 +0200
  • 6c99c97489
    Merge pull request #1509 from ararslan/aa/dragonfly Martin Kroeker 2018-04-07 12:06:57 +0200
  • 6a0930560e
    Add macOS to the Travis testing matrix Alex Arslan 2018-04-06 17:53:58 -0700
  • 24f8d5b624
    Add DragonFly to exports/Makefile Alex Arslan 2018-04-06 17:30:10 -0700
  • 77b4dbd53b
    Merge pull request #1506 from martin-frbg/issue1497 Martin Kroeker 2018-04-05 23:46:36 +0200
  • bc4c3bca01
    Merge pull request #1507 from martin-frbg/threads_usage Martin Kroeker 2018-04-05 08:54:07 +0200
  • 6b0a9d135c
    Merge pull request #1508 from ararslan/aa/wording Martin Kroeker 2018-04-05 08:53:38 +0200
  • 137ccd9dd9
    Minor changes to wording and formatting in the README Alex Arslan 2018-04-04 14:30:32 -0700
  • 84923dedb7
    Merge pull request #1505 from ararslan/aa/compiler Martin Kroeker 2018-04-04 22:45:33 +0200
  • 8ec28ff461
    Remove unguarded use of _Atomic and fix tabbing Martin Kroeker 2018-04-04 22:40:30 +0200
  • ca8ca796d3
    Underline importance of NUM_THREADS setting for BUFFER allocation Martin Kroeker 2018-04-04 22:26:51 +0200
  • 8f811a9312
    Reinstate macOS logic Alex Arslan 2018-04-04 11:41:45 -0700
  • 36a17536ca
    Compile with cc rather than gcc whenever possible Alex Arslan 2018-04-03 15:09:25 -0700
  • bb9876db33
    Fix thread races and infinite looping on systems with many cpus Martin Kroeker 2018-04-04 18:16:52 +0200
  • d636b418af
    Merge pull request #1504 from ararslan/aa/openbsd Martin Kroeker 2018-04-04 15:26:46 +0200
  • a460c92577
    Merge pull request #1501 from martin-frbg/issue875 Martin Kroeker 2018-04-04 15:26:21 +0200
  • 33f838393c
    Add OpenBSD and DragonFly to community supported platforms Alex Arslan 2018-04-03 16:42:01 -0700
  • a41d241a0e
    Add support for DragonFly BSD Alex Arslan 2018-04-03 16:39:29 -0700
  • 8da6b6ae52
    Allow building on OpenBSD Alex Arslan 2018-04-02 10:48:22 -0700
  • 01c4b82f04
    Update memory.c Martin Kroeker 2018-03-31 22:32:06 +0200
  • 93db123f7e
    Update memory.c Martin Kroeker 2018-03-29 13:13:49 +0200
  • 752fdb5dd8
    Add workaround for old gcc and clang versions Martin Kroeker 2018-03-29 11:56:56 +0200
  • 07ed01e97f
    Merge pull request #1500 from martin-frbg/issue1474 Martin Kroeker 2018-03-28 09:15:34 +0200
  • 35c5a32309
    Correct index variables used in MFlops calculation Martin Kroeker 2018-03-27 21:52:29 +0200
  • c7b55b6082
    Merge pull request #1499 from quickwritereader/develop Martin Kroeker 2018-03-27 21:43:23 +0200
  • 840e01061f
    Merge pull request #1491 from martin-frbg/ddot_mt Martin Kroeker 2018-03-27 21:43:05 +0200
  • 28ca97015d power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot z13: improved zgemv_(t|n)_4,zscal,zaxpy QWR QWR 2018-03-07 10:01:03 -0500
  • 73c5ca74fa
    Merge pull request #1495 from martin-frbg/aff Martin Kroeker 2018-03-19 18:03:25 +0100
  • e453555d97
    Disable CPU affinity by default again Martin Kroeker 2018-03-19 18:02:23 +0100
  • 6a6ffaff1e
    Merge pull request #1494 from martin-frbg/x86_dsdot Martin Kroeker 2018-03-17 15:26:47 +0100
  • 28ac9ea5a6
    Use generic/dot.c instead of the inferior arm/dot.c for x86 DSDOT Martin Kroeker 2018-03-17 13:49:15 +0100
  • a55694dd5b
    Declare dot_compute static to avoid conflicts in multiarch builds Martin Kroeker 2018-03-16 22:23:36 +0100
  • 85a41e9cdb
    Add multithreading support for Haswell DDOT Martin Kroeker 2018-03-16 16:58:47 +0100
  • 40160ff3c1
    Use _Atomic instead of volatile for thread safety where C11 is supported Martin Kroeker 2018-03-10 00:15:44 +0100
  • 6a99fcce94
    Use _Atomic instead of volatile for thread safety where C11 is supported Martin Kroeker 2018-03-10 00:03:49 +0100
  • 2c7392f07b
    Merge pull request #1482 from martin-frbg/haswell_axpy Martin Kroeker 2018-03-04 22:21:18 +0100
  • 81215711a2
    Re-enable DAXPY microkernels for x86_64 Martin Kroeker 2018-03-04 19:37:03 +0100
  • 809fd0d451
    Rewrite ROTMG to address cases not covered by the netlib algorithm (#1480) Martin Kroeker 2018-03-04 17:39:56 +0100
  • f29c74f80d
    More spelling fixes in comments Martin Kroeker 2018-03-04 10:51:13 +0100
  • 25f5ca70d7
    Fix spelling errors in comments Martin Kroeker 2018-03-04 10:45:28 +0100
  • f8b52aa41c
    Fix spelling in comment Martin Kroeker 2018-03-04 10:43:19 +0100
  • 72e65157df
    Merge pull request #1481 from martin-frbg/utest-fixup Martin Kroeker 2018-03-03 22:43:56 +0100
  • 471832e39f
    Update rotmg tests in utest_main2.c Martin Kroeker 2018-03-03 18:38:41 +0100
  • 69a8aa6de2
    Fix transposition of expected and computed values in error message Martin Kroeker 2018-03-03 18:01:51 +0100
  • 3fb3a74c05
    Correct ROTMG utest for issue1452 and add another from gonum Martin Kroeker 2018-03-03 14:47:13 +0100
  • 81f81cbc63
    Rewrite ROTMG based on the new implementation in GONUM Martin Kroeker 2018-03-03 14:42:09 +0100
  • 83b0712602
    Merge f1aaf0777a into 0ab5bf1746 Andrew 2018-02-28 17:48:10 +0000
  • 0ab5bf1746
    Merge pull request #1476 from xsacha/patch-1 Martin Kroeker 2018-02-28 18:47:57 +0100
  • 22167170b3
    Merge pull request #1477 from quickwritereader/develop Martin Kroeker 2018-02-28 18:46:54 +0100
  • 69d9f36ff4
    Merge pull request #1468 from martin-frbg/martin-frbg-patch-1 Martin Kroeker 2018-02-28 18:40:31 +0100
  • f81815e48a
    Fix CMake cross-compiling Sacha 2018-02-28 10:25:25 +1000
  • f1aaf0777a Retrigger CI and fix #1474 Andrew 2018-02-27 23:12:24 +0100
  • 87e7cd9e19 take out unreachable branch to re-trigger CI Andrew 2018-02-27 21:13:54 +0100
  • 5f855d965d
    Merge pull request #1475 from ashwinyes/develop_20180227_utest_dsdot_fixes Martin Kroeker 2018-02-27 14:04:16 +0100
  • fa9ca65c0e ARM64: Fix utest dsdot errors Ashwin Sekhar T K 2018-02-27 10:47:55 +0000
  • 719b68f077
    Merge pull request #1473 from martin-frbg/p2align Martin Kroeker 2018-02-27 08:28:20 +0100
  • fe9f15f2d8
    Merge pull request #1472 from martin-frbg/utest-fixes Martin Kroeker 2018-02-26 22:48:07 +0100
  • 497f0c3d8a
    Replace .align with .p2align in the Nehalem microkernels Martin Kroeker 2018-02-26 20:58:33 +0100
  • ea37db828e
    Convert .align to .p2align for OSX compatibility Martin Kroeker 2018-02-26 20:48:03 +0100
  • e6a0a3de73
    Merge pull request #1471 from martin-frbg/p2align Martin Kroeker 2018-02-26 12:28:01 +0100
  • 6e70287776
    Use generic/dot.c for DSDOT on ARMV5 and above Martin Kroeker 2018-02-25 19:57:23 +0100
  • 58f236ad73
    Use generic/dot.c for DSDOT on zarch Martin Kroeker 2018-02-25 19:52:14 +0100
  • e207107150
    Use generic/dot.c for DSDOT on z13 Martin Kroeker 2018-02-25 19:51:25 +0100
  • c9d408064a
    Use dot.S also for DSDOT on CORTEXA57 Martin Kroeker 2018-02-25 19:48:09 +0100
  • 288d1a3f6e
    Use dot.S also for DSDOT on ARMV8 Martin Kroeker 2018-02-25 19:45:16 +0100
  • 7c1925acec
    Use .p2align instead of .align for compatibility on Sandybridge as well Martin Kroeker 2018-02-24 19:43:15 +0100