0fc560ba2
bugfix for buffer overflow by
2014-09-03 10:13:47 +0200
d1800397f
optimized interface/gemv.c for multithreading by
2014-09-02 17:36:07 +0200
f4ff88949
updated interface/gemv.c for multithreading by
2014-09-02 16:30:04 +0200
210bec911
added plot-header to compare multithreading by
2014-09-02 14:11:42 +0200
f3b50dcf5
removed obsolete instructions from sgemv_t_4.c by
2014-09-02 13:35:41 +0200
93eaba959
optimized sgemv_t for bulldozer by
2014-09-02 12:42:36 +0200
9570e5696
optimized sgemv_t_4.c for small sizes by
2014-09-01 15:11:37 +0200
d7f91f8b4
extended gemv.c benchmark by
2014-09-01 15:07:36 +0200
53f1277b6
modified benchmark/gemv.c by
2014-08-31 15:38:18 +0200
bc99faef1
optimized sgemv_t_4.c for uneven sizes by
2014-08-31 14:33:15 +0200
848c0f16f
optimized sgemv_t_4.c for small size by
2014-08-31 13:23:44 +0200
e2fc8c8c2
changed 1 test value (bug in lapack-testing?) by
2014-08-30 13:58:02 +0200
53e6dbf6c
optimized sgemv_t kernel for small sizes by
2014-08-30 13:36:27 +0200
868f8a875
Merge pull request #443 from idunham/fix by
2014-08-29 13:31:06 +0800
db7e6366c
(refs/pull/443/head)
Workaround PIC limitations in cpuid. by
2014-08-28 13:05:07 -0700
2702323f7
Merge pull request #440 from wernsaar/develop by
2014-08-28 12:43:54 +0800
20cd85012
(refs/pull/440/head)
modification for clang compiler by
2014-08-27 09:00:20 +0200
5fa615873
renoved flag no-integrated-as, because not working on macosx by
2014-08-26 18:29:40 +0200
84badf808
EXPERIMENTAL: added the flag -no-integrated-as for clang compiler in Makefile.system by
2014-08-26 17:36:32 +0200
c8cc4a0d2
Fixed the typo in Changelog.txt by
2014-08-26 16:14:34 +0800
3885eebdb
added optimized zaxpy bulldozer kernel by
2014-08-25 15:52:35 +0200
ee7444515
added optimized caxpy kernel for bulldozer by
2014-08-25 14:53:28 +0200
9d2ace8ba
added optimized daxpy kernel for bulldozer by
2014-08-24 10:57:12 +0200
b55f99730
added optimized daxpy kernel for nehalem by
2014-08-23 17:53:07 +0200
29125864b
updated gemm.c by
2014-08-23 17:28:01 +0200
e45c960c2
added optimized saxpy kernel for nehalem by
2014-08-23 17:15:21 +0200
55e81da37
added axpy benchmark-test by
2014-08-23 13:12:44 +0200
ac76b6267
added optimized dgemv_n kernel for nehalem by
2014-08-23 10:40:57 +0200
f1b96c484
added optimized ddot kernel for bulldozer by
2014-08-22 21:19:29 +0200
16d6be852
added optimized ddot kernel for nehalem by
2014-08-22 20:34:41 +0200
53ec5789e
bugfix for Makefile by
2014-08-22 17:02:55 +0200
95a707ced
update of KERNEL.BULLDOZER by
2014-08-22 17:01:27 +0200
5d97b0754
added optimized sdot kernel for nehalem by
2014-08-22 17:00:26 +0200
8a9e86891
added optimized sdot for bulldozer by
2014-08-22 14:29:17 +0200
7e404de3d
bugfix in Makefile by
2014-08-22 11:51:30 +0200
e4472ad85
added sdot and ddot benchmarks by
2014-08-22 11:42:07 +0200
fb0b4552a
added hemv benchmark by
2014-08-22 10:00:09 +0200
6f73ffc11
added benchmarks for csymv and zsymv by
2014-08-21 19:33:57 +0200
c8b064526
added optimized symv_L kernels for nehalem by
2014-08-21 14:27:00 +0200
ec05ff3f6
added optimized ssymv_L kernel for bulldozer by
2014-08-21 13:32:06 +0200
f6f912266
added optimized dsymv_L kernel for bulldozer by
2014-08-21 13:02:53 +0200
8247f38dc
added optimized dsymv_U kernel for nehalem by
2014-08-20 09:58:04 +0200
ef6374196
updated optimized dsymv_U kernel for bulldozer by
2014-08-20 09:00:56 +0200
f824c2b75
updated optimized ssymv_U for bulldozer by
2014-08-19 19:25:03 +0200
4ba4ab623
added optimized ssymv_U kernel for nehalem by
2014-08-19 17:09:45 +0200
4f39447c0
added optimized ssymv_U kernel for bulldozer by
2014-08-18 13:52:24 +0200
74c946567
added optimized dsymv_U kernel for bulldozer by
2014-08-18 12:18:10 +0200
a7126c2ce
(tag: v0.2.11)
Merge branch 'develop' by
2014-08-18 11:16:14 +0800
a69dd3fbc
OpenBLAS 0.2.11 version. by
2014-08-18 11:15:42 +0800
101dd0817
add reference in C for symv_U by
2014-08-16 13:52:50 +0200
493d4fe7e
added reference in C for symv_L by
2014-08-16 11:36:48 +0200
0a22816e7
Ref #433: removed obsolete lapack entries from common_interface.h by
2014-08-15 12:40:10 +0200
c3cd6e7e3
Merge pull request #434 from wernsaar/develop by
2014-08-15 08:07:27 +0800
11eab4c01
(refs/pull/434/head)
added optimized cgemv_n for haswell by
2014-08-14 19:00:30 +0200
4568d32b6
added optimized cgemv_t kernel for haswell by
2014-08-14 14:10:29 +0200
c1a6374c6
optimized zgemv_n kernel for sandybridge by
2014-08-13 16:10:03 +0200
dc0593731
added additional test values by
2014-08-13 14:54:50 +0200
247012913
added fast return, if m or n < 1 by
2014-08-13 13:54:19 +0200
8c582d362
optimized zgemv_t_microk_haswell-2.c by
2014-08-13 13:42:22 +0200
11e34ddd1
bugfix for zgemv_n_microk_haswell-2.c by
2014-08-13 12:54:18 +0200
9528f0d9e
bugfix in zgemv_n_microk_sandy-2.c by
2014-08-13 12:18:03 +0200
b06550519
added optimized cgemv_t c-kernel by
2014-08-12 12:15:41 +0200
6093ee536
bugfix in zgemv_n_microk_haswell-2.c by
2014-08-12 10:02:25 +0200
07c66b196
modified algorithm for better numerical stability by
2014-08-12 08:35:42 +0200
58b075dae
added optimized zgemv_t kernel for haswell by
2014-08-11 16:57:52 +0200
09fcd3a34
add optimized zgemv_t kernel for bulldozer by
2014-08-11 14:19:25 +0200
726ad085c
added optimized zgemv_t for haswell by
2014-08-11 13:10:12 +0200
6fe416976
added optimimized zgemv_t c-kernel by
2014-08-11 09:13:18 +0200
dbc2eff02
disabled optimized haswell zgemv_n kernel for windows ( bad rounding ) by
2014-08-10 11:57:24 +0200
462b4885f
added optimized zgemv_n kernel for haswell by
2014-08-10 08:39:17 +0200
aa54fe064
added zgemv_n c-function by
2014-08-07 22:30:20 +0200
006ef3ea0
added optimized dgemv_t kernel for haswell by
2014-08-07 10:08:54 +0200
60f17628c
added optimized dgemv_n kernel for haswell by
2014-08-07 09:18:02 +0200
c9bad1403
added optimized sgemv_t kernel for sandybridge by
2014-08-07 07:49:33 +0200
2f8927376
enabled optimized nehalem sgemv_t kernel for windows by
2014-08-06 16:58:21 +0200
d945a2b06
added optimized sgemv_t kernel for nehalem by
2014-08-06 16:21:48 +0200
ca6c8d06c
enabled optimized sgemv kernels for windows by
2014-08-06 14:24:36 +0200
7aa43c892
enabled optimized sgemv kernels for windows by
2014-08-06 14:06:30 +0200
891b96085
added optimized sgemv_t kernel for haswell by
2014-08-06 13:42:41 +0200
95a8caa2f
added optimized sgemv_t kernel by
2014-08-06 12:12:17 +0200
5c0d0ecbd
Merge pull request #430 from wernsaar/develop by
2014-08-06 02:52:30 +0800
8c05b8105
(refs/pull/430/head)
bugfix in sgemv_n.c by
2014-08-05 20:14:29 +0200
c80084a98
changed default x86_64 sgemv_n kernel to sgemv_n.c by
2014-08-05 19:42:56 +0200
2bab92961
enabled optimized sgemv_n kernels for windows by
2014-08-05 14:52:54 +0200
9175b8bd5
changed long to blaslong for windows compatibility by
2014-08-05 13:28:39 +0200
793f2d43b
added optimized sgemv_n kernel for nehalem by
2014-08-05 10:50:08 +0200
a4dde45f8
optimized sgemv_n kernel for sandybridge by
2014-08-05 08:53:09 +0200
7fa7ea3e1
updated haswell optimized sgmv_n kernel by
2014-08-05 08:04:47 +0200
3fbc13eb6
modified sgemv_n for haswell by
2014-08-04 16:22:11 +0200
db6917303
added a better optimized sgemv_n kernel for bulldozer and piledriver by
2014-08-04 14:29:01 +0200
c2fdeb6c2
Merge pull request #429 from idunham/numprocs by
2014-08-04 08:12:23 +0800
f7eb81a84
(refs/pull/429/head)
Fix link error on Linux/musl. by
2014-08-03 15:06:30 -0700
edc329883
Merge pull request #427 from wernsaar/develop by
2014-08-03 00:57:44 +0800
793175be3
(refs/pull/427/head)
added experimental support for big numa machines by
2014-08-02 13:40:16 +0200
83c4ba8d3
Merge pull request #426 from wernsaar/develop by
2014-08-02 15:34:41 +0800
271af406f
(refs/pull/426/head)
bugfix for linux affinity code by
2014-08-01 23:10:08 +0200
f5f50b356
added benchmarks for lapack potrf, potrs and potri functions by
2014-08-01 21:08:37 +0200
651dd22d7
added benchmark program for lapack ?getri functions by
2014-08-01 08:55:20 +0200
f329f77bd
Merge pull request #425 from wernsaar/develop by
2014-08-01 08:04:16 +0800
7c611a2f9
(refs/pull/425/head)
bugfix for zgeev by
2014-07-31 12:35:38 +0200