Commit Graph

  • 5cc0301fc3 Enable utest for appveyor. Zhang Xianyi 2016-02-12 01:50:20 -0500
  • 19a6dedfd6 Add utest for CMake. Zhang Xianyi 2016-02-12 05:38:13 +0800
  • 0e2b92e216 Added mising lapacke files for CMake. Zhang Xianyi 2016-02-12 05:28:16 +0800
  • d06b92906a Add gemm3m building for CMake. Zhang Xianyi 2016-02-12 05:02:51 +0800
  • 8e98478ff3 Update ctest.h from github.com:xianyi/ctest.git. Zhang Xianyi 2016-02-12 05:01:57 +0800
  • fb8968fb83 Refs #707. Bugfix for previous commit. Zhang Xianyi 2016-02-11 05:14:53 +0800
  • dae6b82a71 Refs #707. Add BUILD_LAPACK_DEPRECATED flag in Makefile.rule. Zhang Xianyi 2016-02-11 04:22:53 +0800
  • d73244b825 Refs #727. Align stack buffer address on 32-bytes. Zhang Xianyi 2016-02-11 03:51:26 +0800
  • 233c6b959f Merge pull request #780 from jeromerobert/bug727 Zhang Xianyi 2016-02-08 13:24:40 -0500
  • 16ec5323c9 Fix zgemv.c compilation when stack allocation is disabled Jerome Robert 2016-02-08 12:05:02 +0100
  • 0ad02ef2d6 update CONTRIBUTORS.md Jerome Robert 2016-01-18 18:54:51 +0100
  • 73397faf68 Add benchmark/smallscaling.c Jerome Robert 2016-01-03 14:04:33 +0100
  • 5fc2203d8a zgemv: Add a workaround for #746 Jerome Robert 2016-01-24 10:14:41 +0100
  • 78dcf5c3d5 Improve performances of ztrmv on small matrices Jerome Robert 2016-01-14 22:12:57 +0100
  • 32f793195f Use stack allocation in zgemv and zger Jerome Robert 2016-01-03 14:01:12 +0100
  • d87db1d245 Merge 48599f0a3b into 52eba814ce Martin Kroeker 2016-02-02 18:44:17 +0000
  • 48599f0a3b Update dynamic.c Martin Kroeker 2016-02-02 12:33:14 +0100
  • 1a1f3245d6 Update dynamic.c Martin Kroeker 2016-02-02 11:59:00 +0100
  • edae5b9300 Update dynamic.c Martin Kroeker 2016-02-02 09:00:18 +0100
  • d4adc71406 Update cpuid_x86.c Martin Kroeker 2016-01-31 15:33:56 +0100
  • 92058a75e2 For gemm multi-threading, simply split M. optimized_for_deeplearning Zhang Xianyi 2015-11-25 05:14:56 +0800
  • 1367a64d09 Merge branch 'develop' of github.com:xianyi/OpenBLAS into arm_soft_fp_abi Zhang Xianyi 2015-11-11 19:25:07 +0000
  • 3673c77ff4 Merge 93718dcc67 into d00ada378f ashwinyes 2015-11-10 14:07:54 +0000
  • 93718dcc67 Fix bug in benchmark/gemm.c Ashwin Sekhar T K 2015-11-06 20:15:05 +0530
  • 924f4b00bd Optimized trmm kernels for CORTEXA57 Ashwin Sekhar T K 2015-11-02 19:30:28 +0530
  • bc4e96311b Optimized zgemm kernel for CORTEXA57 Ashwin Sekhar T K 2015-11-02 18:58:28 +0530
  • 82b791bf1a Optimized cgemm kernel for CORTEXA57 Ashwin Sekhar T K 2015-11-02 18:40:27 +0530
  • 262c1479a7 Optimized dgemm kernel for CORTEXA57 Ashwin Sekhar T K 2015-11-02 17:53:28 +0530
  • 3d8be7b6ad Improve the sgemm kernel for CORTEXA57 Ashwin Sekhar T K 2015-11-02 17:45:24 +0530
  • 8055add702 Optimized gemv kernels for CORTEXA57 Ashwin Sekhar T K 2015-11-02 17:17:47 +0530
  • f801abd58b Optimized swap kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 14:39:02 +0530
  • 5ee916d1fd Optimized scal kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 14:36:31 +0530
  • f4cadff039 Optimized rot kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 14:33:00 +0530
  • c29ea30dcd Optimized nrm2 kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 14:29:27 +0530
  • d1b2ec5eba Optimized dot kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 14:16:04 +0530
  • 183b2e6cdc Optimized copy kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 12:19:05 +0530
  • b5143de005 Optimized axpy kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 12:12:08 +0530
  • 9af52f1af8 Optimized asum kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 11:52:15 +0530
  • 25a9a1da48 Optimized iamax kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-06 11:41:15 +0530
  • 64df449fe7 Optimized amax kernels for CORTEXA57 Ashwin Sekhar T K 2015-10-05 19:49:44 +0530
  • 45b2757613 Fix compiler errors in common.h Ashwin Sekhar T K 2015-10-05 17:46:11 +0530
  • c425f99e36 Adding arm64 target CORTEXA57 Ashwin Sekhar T K 2015-09-04 13:26:52 +0530
  • 86333efdb0 Minor C code fixes in interface/ Ralph Campbell 2015-09-03 18:00:12 +0530
  • 03faa3c066 Minor C code fixes in driver/ Ralph Campbell 2015-09-03 17:57:06 +0530
  • 3e8d6ea74f Init POWER8 kernels by POWER6. Zhang Xianyi 2015-11-03 12:25:05 +0800
  • be4e5fcd20 Fixed #778. Merge branch 'buffer51-develop' into develop Zhang Xianyi 2016-02-05 08:39:08 +0800
  • 855e0cb700 Restored LAPACK_COMPLEX_STRUCTURE for Android prior to 21. Refs #682. buffer51 2016-02-04 17:20:07 -0500
  • 7f7d04dcd2 Fixed linking error when compiling ARMv7 for Android (disabled -lpthread and added -Wl,--no-warn-mismatch). buffer51 2016-02-04 17:05:31 -0500
  • 4e1b521e27 Fix lapack complex implementation of lauu2 and potf2 for Android (use FLOAT instead of FLOAT[2] as imaginary part is not used). buffer51 2015-11-07 19:31:13 -0500
  • a1a96589aa Fixed #773 blas_quickdivide bug on CMake and Visual Studio x86 32-bit. Zhang Xianyi 2016-02-04 15:23:32 -0500
  • 0e68beb89f Fixed #711, #698. Merge branch 'byzhang-develop' into develop Zhang Xianyi 2016-02-03 02:56:27 +0800
  • 926ba8b7ca Merge branch 'develop' of https://github.com/byzhang/OpenBLAS into byzhang-develop Zhang Xianyi 2016-02-03 02:48:32 +0800
  • 9f080c47e1 Merge pull request #743 from tkelman/patch-1 Zhang Xianyi 2016-02-02 13:46:12 -0500
  • 52eba814ce Fixed #769. Merge branch 'martin-frbg-develop' into develop Zhang Xianyi 2016-02-02 13:43:51 -0500
  • 935356c34f Update dynamic.c and cpuid_x86.c for Intel Avoton. Martin Kroeker 2016-02-02 09:00:18 +0100
  • ff9388d625 Refs #768. Swap the result of zdot x87 fp kernel. Zhang Xianyi 2016-02-02 09:15:02 +0800
  • 4f05c23673 Update cpuid_x86.c Martin Kroeker 2016-01-31 15:33:56 +0100
  • 4a1263f609 Fix the source paths Benyu Zhang 2016-02-01 18:32:42 -0800
  • 962376664d Refs #768. Swap the result of zdot x87 fp kernel. Zhang Xianyi 2016-02-02 09:15:02 +0800
  • 5fef0d1b75 re enable Fortran optimization flag on windows Tony Kelman 2016-01-18 08:44:46 -0800
  • 578f471808 Fix utest bug when INTERFACE64=1. Zhang Xianyi 2016-01-28 22:18:38 -0600
  • 5a8447e97e Use ctest.h for unit test. Enable unit test on travis CI. Zhang Xianyi 2016-01-29 11:35:31 +0800
  • be95bdaf47 Detect ARMV8 on 32-bit mode by using ARMV7 kernels. Zhang Xianyi 2016-01-28 17:30:26 +0000
  • c44ff4d648 Refs #714. avoid compiling warnings. Zhang Xianyi 2016-01-28 04:38:07 +0800
  • e003a1294c Merge pull request #764 from martin-frbg/develop Zhang Xianyi 2016-01-26 14:03:27 -0600
  • 44062517eb Update Makefile.system Martin Kroeker 2016-01-26 20:35:25 +0100
  • 13f0f8c10e Refs #723. Avoid out of boundary for getf2. Zhang Xianyi 2016-01-26 09:14:57 -0600
  • f5df444ceb Merge pull request #762 from jeromerobert/bug760 Zhang Xianyi 2016-01-26 08:45:16 -0600
  • e382713423 Merge pull request #759 from jeromerobert/bug742 Zhang Xianyi 2016-01-26 08:43:32 -0600
  • aaa8551c57 Merge pull request #749 from lotheac/illumos_fixes Zhang Xianyi 2016-01-26 08:42:20 -0600
  • 0d87c1ffb6 Let openblas_get_num_threads return the number of active threads Jerome Robert 2016-01-26 13:04:16 +0100
  • 0b194426f8 Merge pull request #761 from wernsaar/develop wernsaar 2016-01-26 09:19:14 +0100
  • 63a7d7fb24 updated gemv_n_vfpv3.S for armv7 Werner Saar 2016-01-25 15:00:13 +0100
  • b4ede558a5 updated nrm2 kernel for armv7 Werner Saar 2016-01-25 11:55:25 +0100
  • de3e2d4349 updated trmm kernels for armv7 Werner Saar 2016-01-25 11:08:56 +0100
  • a0e51e96f1 updated gemm kernels for armv7 Werner Saar 2016-01-25 10:46:10 +0100
  • d6afac9624 don't pass -Y at all to the linker on illumos Lauri Tirkkonen 2016-01-22 18:46:27 +0200
  • c2891330bc updated KERNEL.ARMV6 Werner Saar 2016-01-24 17:12:07 +0100
  • ceaa931e48 updated gemv kernel for armv6 Werner Saar 2016-01-24 16:31:19 +0100
  • eaa63165df updated cgemv and zgemv kernels for armv6 Werner Saar 2016-01-24 14:42:38 +0100
  • c65357c566 updated trmm_kernels for armv6 Werner Saar 2016-01-24 13:03:33 +0100
  • e63e9f9f26 updated gemm_kernels for armv6 Werner Saar 2016-01-24 11:55:50 +0100
  • 1fe3aab047 Use GEMM_MULTITHREAD_THRESHOLD as a number of ops Jerome Robert 2016-01-24 10:30:50 +0100
  • aafd3ab60e updated cdot and zdot on arm Werner Saar 2016-01-24 10:56:49 +0100
  • 1a1935507b [z]ger: increase multithread threshold Jerome Robert 2016-01-15 18:40:13 +0100
  • d2f84c9c8a Ref #740: updated nrm2_vfp.S Werner Saar 2016-01-23 17:47:58 +0100
  • ca32253f32 Ref #740: updated asum_vfp.S and iamax_vfp.S Werner Saar 2016-01-23 14:44:34 +0100
  • 9066d1f982 Ref #750 and Ref #740 : bugfix for sdot, dsdot and ddot on arm Werner Saar 2016-01-23 11:59:51 +0100
  • 8d85be770d actually install the shared lib on illumos Lauri Tirkkonen 2016-01-22 18:50:05 +0200
  • 7ba1d9b9ca actually build the shared lib on illumos Lauri Tirkkonen 2016-01-22 18:50:29 +0200
  • 31aff441ce use $(AWK) in Makefile.install and switch it to nawk Lauri Tirkkonen 2016-01-22 18:50:53 +0200
  • e737e32fd1 RLIMIT_NPROC doesn't exist on illumos Lauri Tirkkonen 2016-01-22 18:49:17 +0200
  • 8635d425c1 make parallel make work on illumos Lauri Tirkkonen 2016-01-22 18:48:50 +0200
  • 97cd4b8aee illumos fixes to memory.c Lauri Tirkkonen 2016-01-22 18:48:25 +0200
  • 72390e3ffb Merge pull request #747 from wernsaar/develop wernsaar 2016-01-21 14:21:59 +0100
  • b07d733a71 added updates for syrk and syr2k Werner Saar 2016-01-21 13:16:44 +0100
  • fa3018c30e Merge pull request #745 from jakirkham/minor_fix_scipy_prof Zhang Xianyi 2016-01-20 11:24:22 -0600
  • 6caa40302e Merge pull request #744 from jeromerobert/bug731 Zhang Xianyi 2016-01-20 11:18:21 -0600
  • a48b247e9e benchmark/scripts/SCIPY/dsyrk.py: Overwrite will work on a Fortran array of the correct type. John Kirkham 2016-01-19 15:32:28 -0500
  • b1b115ecd6 benchmark/scripts/SCIPY/ssyrk.py: Overwrite will work on a Fortran array of the correct type. John Kirkham 2016-01-19 15:31:37 -0500