Commit Graph

  • bd2da90e13 Fixed typo in getarch_2nd.c. Zhang Xianyi 2013-07-29 15:42:00 +0800
  • 84bd0aabaa added dtrsm_kernel_LT_8x2_bulldozer.S wernsaar 2013-07-28 16:47:58 +0200
  • 5b504d6c23 Refs #263. Rollback bulldozer and piledriver kernels to barcelona kernels. Zhang Xianyi 2013-07-28 17:39:24 +0800
  • 72b1edaf1b Merge branch 'develop' into bulldozer Zhang Xianyi 2013-07-28 06:38:25 +0200
  • 47607f39bd Merge 9af334873a into 6e0db36373 Sébastien Fabbro 2013-07-27 09:10:30 -0700
  • a2930664f4 Refs #262. Added executable stack markings. Zhang Xianyi 2013-07-28 00:09:40 +0800
  • 651a8c245f Merge 9f0fb6e662 into 23186d9f21 Sébastien Fabbro 2013-07-27 08:03:12 -0700
  • 6e0db36373 Merge branch 'sfabbro-ldflags' into develop Zhang Xianyi 2013-07-27 23:03:07 +0800
  • 1e1250b703 Fixed #260. Fixed generating 32-bit shared library on previous commit. Zhang Xianyi 2013-07-27 23:01:36 +0800
  • 23186d9f21 Fixed the FMA3 detection bug. Zhang Xianyi 2013-07-27 22:37:57 +0800
  • e6ebbfd314 Merge branch 'ldflags' of https://github.com/sfabbro/OpenBLAS into sfabbro-ldflags Zhang Xianyi 2013-07-27 22:19:54 +0800
  • 4471c77905 Fixed #261. Use strncmp instead of a comparing trick. Zhang Xianyi 2013-07-26 23:43:54 +0800
  • fa2cc65a0b Merge 4e1eba58aa into 63f14189e3 Sébastien Fabbro 2013-07-25 14:17:31 -0700
  • 9af334873a Add stack markings for GNU as arch-independent for assembler files Sebastien Fabbro 2013-07-24 10:04:57 -0700
  • 5118ead930 Add my contributions Sebastien Fabbro 2013-07-24 10:03:57 -0700
  • 4e1eba58aa Fixed aliasing Sebastien Fabbro 2013-07-24 09:45:26 -0700
  • 9f0fb6e662 Respect user's LDFLAGS Sebastien Fabbro 2013-07-24 09:37:16 -0700
  • f26b7a08aa Merge branch 'develop' v0.2.7 Zhang Xianyi 2013-07-26 01:34:45 +0800
  • 63f14189e3 Refs #259. Fixed missing LAPACK functions in shared library. Zhang Xianyi 2013-07-26 01:32:32 +0800
  • e39384432b Merge branch 'develop' Zhang Xianyi 2013-07-23 13:40:08 +0800
  • c5437149c0 Merge pull request #257 from staticfloat/develop Zhang Xianyi 2013-07-22 22:35:29 -0700
  • 13e88b936e Merge 6f5b395009 into d4f9571818 Elliot Saba 2013-07-22 17:12:54 -0700
  • 6f5b395009 Fix xianyi/OpenBLAS#256 Elliot Saba 2013-07-22 17:02:06 -0700
  • d4f9571818 Refs #255. Didn't use f77 compiler. Zhang Xianyi 2013-07-22 11:34:43 +0800
  • 937d838619 Update CONTRIBUTORS.md Zhang Xianyi 2013-07-20 23:32:23 +0800
  • a8f9b6a665 Merge branch 'develop' Zhang Xianyi 2013-07-20 23:05:36 +0800
  • 6209c8fc44 Fixed #253. Update doc for v0.2.7 version. Zhang Xianyi 2013-07-20 23:05:12 +0800
  • 238ceb4ac0 Merge branch 'loongson3b' into develop Zhang Xianyi 2013-07-20 22:33:35 +0800
  • 77b572fa0b Merge branch 'loongson3a' into develop Zhang Xianyi 2013-07-20 22:32:38 +0800
  • f69f89b846 Fixed #254. Added the date of changes in contributors file. Zhang Xianyi 2013-07-20 11:35:27 +0800
  • c77032b0cc create contributor file. Zhang Xianyi 2013-07-19 08:38:03 +0800
  • 1b3b9e841d Fixed a computational error in zgemm_kernel_4x4_sandy.S file. wangqian 2013-07-18 20:23:21 +0800
  • b67252c2e4 Ensure the correct stack alignment on Win32. Zhang Xianyi 2013-07-17 15:19:07 +0800
  • c69e73b868 Fixed typo in generating shared library on x86_64. Zhang Xianyi 2013-07-16 23:18:18 +0800
  • b51e2ba1ee Modified Makefile to avoid redundant echo. Zhang Xianyi 2013-07-16 22:44:27 +0800
  • 9c0a834f98 Modified Makefile.install Zhang Xianyi 2013-07-16 17:45:00 +0800
  • 2a7503e563 Refs #225. Fixed a bug in GEMM OpenMP threading. Zhang Xianyi 2013-07-15 09:56:19 +0800
  • fd0c388681 Refs #191. A walk around for dtrtri_U single thread bug. Zhang Xianyi 2013-07-14 22:16:30 +0800
  • 61a9582987 Changed makefile for lapack. Zhang Xianyi 2013-07-14 10:41:54 +0800
  • b681064c6c Updated travis. Zhang Xianyi 2013-07-12 21:41:12 +0800
  • e80e285928 Update build matrix for Travis CI. Zhang Xianyi 2013-07-11 23:49:29 +0800
  • 2ed0f6ab60 Fixed the typo. Zhang Xianyi 2013-07-11 23:47:07 +0800
  • 5448643557 Fixed generating dll bug in last commit. Zhang Xianyi 2013-07-11 22:24:50 +0800
  • 824c3c4df3 Fixed #251. Merge branch 'grisuthedragon-develop' into develop Zhang Xianyi 2013-07-11 21:41:44 +0800
  • c19a488af2 create openblas_get_parallel to retrieve information which parallelization model is used by OpenBLAS. grisuthedragon 2013-07-11 13:39:27 +0200
  • d2efce783d Merge 773140ee2f into 32d2ca3035 grisuthedragon 2013-07-11 04:51:53 -0700
  • 773140ee2f create openblas_get_parallel to retrieve information which parallelization model is used by OpenBLAS. grisuthedragon 2013-07-11 13:39:27 +0200
  • 32d2ca3035 Refs #214, #221, #246. Fixed the getrf overflow bug on Windows. Zhang Xianyi 2013-07-11 03:20:02 +0800
  • 6df39ad9e7 Refs #248. Support LAPACK and LAPACKE with lsbcc. Zhang Xianyi 2013-07-10 16:02:27 +0800
  • 3a96e4cbcb Merge pull request #249 from wernsaar/develop Zhang Xianyi 2013-07-10 01:01:03 -0700
  • 13b29149b0 Merge 6f008abcef into 3eb5af1955 wernsaar 2013-07-09 09:23:08 -0700
  • 6f008abcef replaced defined(DOUBLE) by !defined(XDOUBLE) wernsaar 2013-07-09 18:17:50 +0200
  • 3eb5af1955 Refs #247. Included lapack source codes. Avoid downloading tar.gz from netlib.org Zhang Xianyi 2013-07-09 17:00:02 +0800
  • fbb75e58b1 Fixed the typo in getarch.c Zhang Xianyi 2013-07-09 16:26:59 +0800
  • f54f5bac9e Refs #248. Fixed the LSB compatiable issue for BLAS only. For example, make CC=lsbcc NO_LAPACK=1. Zhang Xianyi 2013-07-09 15:38:03 +0800
  • 5d3312142a Refs #221 #246. Fixed the overflowing stack bug in mutlithreading BLAS3. Zhang Xianyi 2013-07-08 01:07:05 +0800
  • 886cbaf4e4 Support AMD Piledriver by bulldozer kernels. Zhang Xianyi 2013-07-06 12:06:43 -0300
  • 0c4074e10b Added Travis CI status image. Zhang Xianyi 2013-07-05 15:28:41 +0800
  • cc522aa21d Use quiet make for Travis CI. Zhang Xianyi 2013-07-05 14:52:57 +0800
  • 9c78fad721 Install gfortran in Travis CI. Zhang Xianyi 2013-07-05 11:11:18 +0800
  • 6028232ad1 Added travis.yml file. Zhang Xianyi 2013-07-04 23:30:53 +0800
  • feb9a3889a Improved make clean on Mac OS X. Zhang Xianyi 2013-07-02 14:37:30 +0800
  • 32dbeb636d Refs #221. Set stack limit to 16MB to prevent a SEGFAULT bug on Mac OS X with DYNAMIC_ARCH=1 & NUM_THREADS=256. Zhang Xianyi 2013-07-02 14:17:55 +0800
  • 57944538b6 Use ALIGN_5 instead of .algin 32 in assembly kernel. Added ALIGN_5 for 32-bit OSX. Zhang Xianyi 2013-07-01 16:09:05 +0800
  • 3ce2c62b0b Merge pull request #242 from danluu/readme.haswell Zhang Xianyi 2013-06-30 09:40:32 -0700
  • 2c689ddf9c Merge 50464997a3 into 8e7cad1650 Dan Luu 2013-06-30 09:38:30 -0700
  • 50464997a3 Fix miscellaneous typos Dan Luu 2013-06-30 11:36:13 -0500
  • 8e7cad1650 Fixed #217 openblas_config.h bug on Windows 64. Zhang Xianyi 2013-07-01 00:35:14 +0800
  • 590e6aeafc Add Haswell support Dan Luu 2013-06-30 11:35:00 -0500
  • 88ef307cef Refs #241. Add Haswell support (using sandybridge optimizations) Dan Luu 2013-06-29 17:26:56 -0500
  • bd3d39ff53 Merge e5c574807a into 6e8501c8a1 Dan Luu 2013-06-29 15:40:26 -0700
  • e5c574807a Attempt to add Haswell support (using sandybridge optimizations) Dan Luu 2013-06-29 17:26:56 -0500
  • 6e8501c8a1 Fixed #239 bug in param.h about BARCELONA and BULLDOZER. Zhang Xianyi 2013-06-29 10:36:01 +0800
  • fa916a0fac Fixed #238 bug in lsame on x86. Zhang Xianyi 2013-06-28 22:43:41 +0800
  • fb298b34ae Merge pull request #235 from wernsaar/develop Zhang Xianyi 2013-06-21 17:59:26 -0700
  • b5aecb6dd4 Merge 16012767f4 into 646e168d26 wernsaar 2013-06-21 08:35:33 -0700
  • 16012767f4 added dcopy_bulldozer.S wernsaar 2013-06-21 16:06:51 +0200
  • bcbac31b47 added ddot_bulldozer.S wernsaar 2013-06-20 16:15:09 +0200
  • 8dc0c72583 added daxpy_bulldozer.S wernsaar 2013-06-20 14:07:54 +0200
  • 89405a1a0b cleanup of dgemm_ncopy_8_bulldozer.S wernsaar 2013-06-19 19:31:38 +0200
  • 4f2b12b8a8 added dgemv_t_bulldozer.S wernsaar 2013-06-19 17:32:42 +0200
  • 646e168d26 Merge pull request #233 from wernsaar/develop Zhang Xianyi 2013-06-18 20:02:36 -0700
  • 8b94116a83 Merge 93dbbe1fb8 into cd1d473ba0 wernsaar 2013-06-18 04:52:26 -0700
  • 93dbbe1fb8 added dgemm_ncopy_8_bulldozer.S wernsaar 2013-06-18 13:29:23 +0200
  • a135f5d9ed added gemm_tcopy_2_bulldozer.S wernsaar 2013-06-18 11:01:33 +0200
  • d0b6299b13 added dgemm_tcopy_8_bulldozer.S wernsaar 2013-06-17 14:19:09 +0200
  • 9e58dd509e added gemm_ncopy_2_bulldozer.S wernsaar 2013-06-17 12:55:12 +0200
  • 7c8227101b cleanup of dgemv_n_bulldozer.S and optimization of inner loop wernsaar 2013-06-16 12:50:45 +0200
  • f67fa62851 added dgemv_n_bulldozer.S wernsaar 2013-06-15 16:42:37 +0200
  • cd1d473ba0 Merge pull request #230 from wernsaar/develop Zhang Xianyi 2013-06-13 07:29:27 -0700
  • b2ebf211e0 Merge 0ded1fcc1c into 56f160134d wernsaar 2013-06-13 07:29:02 -0700
  • 56f160134d Refs #231. Change the default C compiler to clang on Mac OSX. Zhang Xianyi 2013-06-13 22:15:19 +0800
  • 0ded1fcc1c performance optimizations in sgemm_kernel_16x2_bulldozer.S wernsaar 2013-06-13 11:35:15 +0200
  • a789b588cd added cgemm_kernel_4x2_bulldozer.S wernsaar 2013-06-12 15:55:27 +0200
  • 8eaa04acbb added zgemm_kernel_2x2_bulldozer.S wernsaar 2013-06-11 12:00:49 +0200
  • d854b30ae6 Added UNROLL values for 3M to getarch_2nd.c, Makefile.system and Makefile.L3 wernsaar 2013-06-09 17:26:42 +0200
  • d65bbec99b added new sgemm kernel for BULLDOZER wernsaar 2013-06-09 15:57:42 +0200
  • e4c39c7c26 changed stack touching wernsaar 2013-06-08 10:43:08 +0200
  • ba800f0883 correct GEMM_THREAD in param.h wernsaar 2013-06-08 10:03:59 +0200
  • 25491e42f9 New dgemm kernel for BULLDOZER: dgemm_kernel_8x2_bulldozer.S wernsaar 2013-06-08 09:40:17 +0200