a55377e9a
Merge branch 'hpanderson_cmake' into cmake by
2015-07-22 04:07:27 +0800
dcd5ba444
Merge branch 'cmake' of https://github.com/hpanderson/OpenBLAS into hpanderson_cmake by
2015-07-22 04:06:39 +0800
034ffa93f
(integer_datatype)
Provide iaxpy and cblas_iaxpy for integer vectors. make INTEGER_PRECISION=1 by
2015-07-01 03:11:27 +0800
3f1b57668
Fix blas lock bug on AArch64. by
2015-06-26 11:54:41 +0800
d8f18d32c
Merge pull request #595 from tanderson92/fixTests by
2015-06-22 21:54:51 -0500
bdb5c842f
Merge pull request #596 from wernsaar/develop by
2015-06-13 16:44:48 +0200
e7c969e16
(refs/pull/596/head)
added optimized dtrmm_kernel for haswell by
2015-06-13 16:16:29 +0200
9bd962f65
modified haswell parameter dgemm_unroll_n by
2015-06-13 10:28:27 +0200
4f5691e5c
(refs/pull/595/head)
Fix test execution when USE_OPENMP=0 by
2015-06-12 23:52:07 -0700
29293160a
Fix #593. Change MACOSX_DEPLOYMENT_TARGET to 10.6. by
2015-06-08 10:53:50 -0500
3e33afef2
Merge pull request #592 from wernsaar/develop by
2015-06-08 14:22:02 +0200
8614057ea
(refs/pull/592/head)
added benchmark scripts for numpy, octave and R by
2015-06-08 14:06:38 +0200
7f375f9e8
updated geev benchmark by
2015-06-08 12:58:38 +0200
69c5169e7
Merge pull request #589 from wernsaar/develop by
2015-06-03 12:14:09 +0200
e19948baa
(refs/pull/589/head)
small modification of gemm.c by
2015-06-03 09:11:51 +0200
a2eaf234f
Merge pull request #587 from wernsaar/develop by
2015-06-02 15:29:49 +0200
6a13a94e7
(refs/pull/587/head)
added gesv benchmark by
2015-06-02 13:35:49 +0200
eff43d328
Merge pull request #585 from wernsaar/develop by
2015-05-31 15:01:54 +0200
9c4817d07
(refs/pull/585/head)
bugfix for Makefile on mac by
2015-05-31 14:16:51 +0200
319f3a045
Merge pull request #584 from wernsaar/develop by
2015-05-29 13:27:20 +0200
02c7766f6
(refs/pull/584/head)
bugfixes, to build benchmarks with mingw on Windows OS by
2015-05-29 12:56:22 +0200
f38cb67ca
Merge pull request #581 from wernsaar/develop by
2015-05-23 12:58:15 +0200
eea2e30b7
(refs/pull/581/head)
bugfix for arm locking by
2015-05-23 11:40:40 +0200
19b8fd2ae
smp lock bugfix by
2015-05-23 10:58:38 +0200
0cc521274
Merge pull request #580 from wernsaar/develop by
2015-05-23 09:46:39 +0200
c47c8e8cf
(refs/pull/580/head)
added blas level1 swap benchmark by
2015-05-21 08:51:42 +0200
a11555c71
Support Android NDK armeabi-v7a-hard ABI. (-mfloat-abi=hard) by
2015-05-20 21:57:27 -0500
897d03518
Merge pull request #578 from wernsaar/develop by
2015-05-20 11:56:02 +0200
23fbc5728
(refs/pull/578/head)
added blas level1 copy benchmark by
2015-05-20 11:05:00 +0200
6d40fa587
Fix f_check bug. by
2015-05-19 12:04:45 -0500
22dcd7995
Merge pull request #577 from wernsaar/develop by
2015-05-19 10:59:24 +0200
ea4df0aad
(refs/pull/577/head)
Ref #574: Bugfix for armv6 memory barrier by
2015-05-19 10:43:12 +0200
e127fb8fd
1) Refs #575. Remove g77 from compiler list. 2) If OpenBLAS cannot find Fortran compiler, it will only build BLAS (without LAPACK). by
2015-05-19 00:01:04 -0500
8c0597076
(refs/pull/576/merge)
Merge 4a20fec92d into 7fb718a7d8 by
2015-05-18 20:41:27 +0000
4a20fec92
(refs/pull/576/head)
Make gfortran the first to look for by
2015-05-18 16:39:15 -0400
7fb718a7d
Merge pull request #572 from wernsaar/develop by
2015-05-18 13:47:38 +0200
24f58c8bb
(refs/pull/572/head)
added optimized cscal and zscal kernels for steamroller by
2015-05-18 12:40:07 +0200
95b1faf66
added optimized cscal and zscal kernels for steamroller and piledriver by
2015-05-18 10:50:57 +0200
2d9e40605
added optimized cscal kernel for sandybridge by
2015-05-18 08:46:06 +0200
59083e3ce
added optimized cscal kernel for bulldozer by
2015-05-18 07:33:52 +0200
685be4033
Merge pull request #571 from wernsaar/develop by
2015-05-17 14:09:14 +0200
31c9e399e
(refs/pull/571/head)
added optimized cscal kernel for haswell by
2015-05-17 13:44:09 +0200
7de6bb988
added optimized zscal kernel for bulldozer by
2015-05-17 11:45:19 +0200
d63034303
added optimized zscal kernel for haswell by
2015-05-16 16:41:45 +0200
51ff17d46
Add AMD Excavator target. by
2015-05-13 16:16:30 -0500
905534942
Merge pull request #568 from wernsaar/develop by
2015-05-13 13:48:08 +0200
18e90ee2e
(refs/pull/568/head)
bugfix: added static to functions by
2015-05-13 13:31:26 +0200
e00cccc41
added optimized dscal kernel for piledriver by
2015-05-13 13:05:35 +0200
73f09bf64
optimized dscal kernel for increment != 1 by
2015-05-13 12:14:39 +0200
02e772c7e
added optimized dscal kernel for haswell by
2015-05-12 17:19:58 +0200
7aee91399
added optimized dscal kernel for sandybridge by
2015-05-12 16:27:43 +0200
e50a93303
added optimized dscal kernel for bulldozer by
2015-05-12 12:28:44 +0200
5f9011d6e
Merge pull request #566 from powderluv/develop by
2015-05-11 20:59:12 -0500
ebb9eba98
(refs/pull/566/head)
Fix build with ALLOC_SHM=0 (Android NDK) by
2015-05-10 00:10:26 -0700
8e5a1083b
Refs #532. Improve gemv paralel with small m and large n case. by
2015-05-08 05:33:17 +0800
6743beb74
Refs #565. Fix the bug of generate FEXTRALIB. by
2015-05-07 13:06:53 +0800
bcabf72c0
Refs #565. Merge branch 'andreasnoack-anj/bench' into develop by
2015-05-07 12:52:14 +0800
cda29f183
(refs/pull/565/head)
Add vecLib benchmarks by
2015-05-06 21:52:34 -0400
e52d36450
Merge pull request #564 from wernsaar/develop by
2015-05-06 11:10:31 +0200
f8f2e261f
(refs/pull/564/head)
use only 1 thread if m or n < 2*GEMM_MULTITHREAD_THRESHOLD by
2015-05-06 10:41:53 +0200
be3c84370
added loops to trsm.c by
2015-05-06 09:21:19 +0200
e6f57db84
Merge pull request #563 from wernsaar/develop by
2015-05-05 12:13:35 +0200
9bfd267d5
(refs/pull/563/head)
bugfix for gemm3m tests by
2015-05-05 11:58:59 +0200
924bc5372
removed gemm3m functions from normal checks by
2015-05-05 11:39:43 +0200
2b83a6965
Merge pull request #561 from wernsaar/develop by
2015-05-04 11:11:13 +0200
133c11a15
(refs/pull/561/head)
updated dgemv_n kernel for nehalem by
2015-04-30 14:38:06 +0200
30f52d53d
optimized dgemv_n kernel for haswell by
2015-04-30 12:11:39 +0200
a12463732
Merge pull request #560 from sebastien-villemot/develop by
2015-04-29 11:36:47 -0500
642aaba2e
(refs/pull/560/head)
Fix detection of ARM architectures in c_check. by
2015-04-29 18:14:21 +0200
4c616173e
Merge pull request #558 from wernsaar/develop by
2015-04-28 17:30:16 +0200
5e83d8072
(refs/pull/558/head)
optimized dger kernel for sandybridge by
2015-04-28 16:58:11 +0200
b2e1797dc
added optimized sger kernel for sandybridge by
2015-04-28 15:33:38 +0200
e216f686c
optimized saxpy and daxpy for sandybridge by
2015-04-28 10:18:32 +0200
e42652f77
Merge pull request #554 from wernsaar/develop by
2015-04-25 08:11:36 -0500
e77db2af3
(refs/pull/554/head)
add benchmarks for zgeru and cgeru by
2015-04-25 14:53:07 +0200
37b00841a
Merge pull request #552 from jeromerobert/develop by
2015-04-24 14:12:12 -0500
fc0e0391f
bugfixes: replaced int with BLASLONG by
2015-04-24 14:30:44 +0200
da0f27b9a
Merge pull request #553 from wernsaar/develop by
2015-04-24 13:57:48 +0200
c22068c40
(refs/pull/553/head)
optimized sdot.c for increments != 1 by
2015-04-24 13:13:20 +0200
dee100d0e
optimized saxpy.c for increments != 1 by
2015-04-24 11:52:59 +0200
0273966ab
optimized daxpy kernel for increments != 1 by
2015-04-24 11:39:17 +0200
3a67daa95
optimized ddot.c for increments != 1 by
2015-04-24 10:56:55 +0200
ab567d844
(refs/pull/552/head)
gemv: Ensure stack buffer is large enough to handle memory alignment by
2015-04-21 10:12:01 +0200
3c09cea4b
Merge pull request #550 from wernsaar/develop by
2015-04-23 13:27:38 +0200
b4f2153dc
(refs/pull/550/head)
added optimized ssymv kernels for sandybridge by
2015-04-23 12:19:24 +0200
1c4b0eeae
added optimized ssymv kernels for haswell by
2015-04-23 10:23:13 +0200
406d9d64e
Merge pull request #549 from wernsaar/develop by
2015-04-22 12:36:13 +0200
1bec9abb9
(refs/pull/549/head)
added optimized dsymv kernels for sandybridge by
2015-04-22 12:09:43 +0200
3814bf60d
added optimized dsymv kernels for haswell by
2015-04-22 10:42:50 +0200
847e19c04
Refs #478,#482, Enable stack alloc for s/dgemv_t.(revert 9798491) by
2015-04-20 23:22:40 -0500
46c7b4d5c
added asum benchmark by
2015-04-19 11:24:07 +0200
8e05d291b
added scal benchmark by
2015-04-18 08:41:41 +0200
9da555e5f
Merge pull request #546 from wernsaar/develop by
2015-04-16 11:36:51 +0200
6d0db0151
(refs/pull/546/head)
added optimized zaxpy-kernels by
2015-04-16 11:19:37 +0200
37b9033c9
Merge pull request #543 from jeromerobert/develop by
2015-04-15 11:18:14 -0500
59e7a518c
Merge pull request #544 from wernsaar/develop by
2015-04-15 17:04:02 +0200
13889515b
(refs/pull/544/head)
added optimized caxpy-kernel for sandybridge by
2015-04-15 16:29:25 +0200
248c9340c
added optimized caxpy-kernel for haswell by
2015-04-15 15:16:31 +0200
e9f33b4ca
added optimized caxpy-kernel for steamroller by
2015-04-15 13:49:23 +0200
f5d847122
updated caxpy_microk_bulldozer-2.c and caxpy.c by
2015-04-15 11:59:38 +0200