37aee1f9b
Merge branch 'develop' by
2014-12-03 23:01:33 +0800
f5424fc9d
Update the doc for 0.2.13 version. by
2014-12-03 23:00:29 +0800
0cf29ba6d
Fixed a bug of sgemm sandy bridge kernel. by
2014-12-03 17:38:41 +0800
50e18033e
Merge pull request #471 from nolta/patch-4 by
2014-12-03 12:53:20 +0800
551b55d1c
Merge pull request #470 from nolta/patch-3 by
2014-12-03 12:50:46 +0800
271ceb8ba
(refs/pull/471/head)
c_check: set $hostarch to x86_64 instead of amd64 by
2014-12-02 21:23:23 -0500
5f846be2e
(refs/pull/470/head)
fix fortran compiler detection on FreeBSD by
2014-12-02 20:47:40 -0500
fe7dcf98f
Refs #461. Provide OpenBLASConfig.cmake to support CMake. by
2014-11-29 02:16:40 +0800
2fb02626d
Update organization info. by
2014-11-25 15:28:58 +0800
a85c2785a
Refs #467. Added generic kernel file for x86_64. by
2014-11-24 15:34:48 +0800
73750ce9b
(refs/pull/465/merge)
Merge cb07a181e6 into 4806715c97 by
2014-11-11 14:23:10 +0000
4806715c9
Fixed #456. Merged the optimizations for APM's xgene-1 (aarch64). Merge branch 'benedikt-huber-dave-patch' into develop by
2014-11-11 22:21:04 +0800
58c90d593
# The first commit's message is: Optimizations for APM's xgene-1 (aarch64). by
2014-10-09 06:52:10 -0700
cb07a181e
(refs/pull/465/head)
Added Dave Nuechterlein to the contributors list. by
2014-11-11 14:04:22 +0100
7e4e195e8
(tag: v0.2.12)
Merge branch 'develop' by
2014-10-13 17:10:41 +0800
7d8f51b16
Removed unnecessary file references. by
2014-10-09 18:49:34 -0700
aba0751d4
Optimizations for APM's xgene-1 (aarch64). by
2014-10-09 06:52:10 -0700
2987bc7b4
refs #464. Fixed the bug of detecting L2 associative on x86. by
2014-11-10 17:15:34 +0800
695e0fa64
#463 fixed a compiling bug on AIX. by
2014-11-10 14:39:56 +0800
cbb23c46c
Merge pull request #459 from tkelman/symbol-rename by
2014-10-25 19:49:03 +0800
0b4602b75
(refs/pull/459/head)
add SYMBOLPREFIX and SYMBOLSUFFIX makefile options by
2014-10-24 22:27:00 -0700
ac5a7e1c1
Update dot to 0.2.12 version. by
2014-10-13 17:10:12 +0800
f1b9a4a1c
Ref #454: fixed bug in common_param.h by
2014-09-23 11:34:29 +0200
ae6b7caf3
Merge pull request #453 from wernsaar/develop by
2014-09-22 16:47:54 +0800
f446d2368
(refs/pull/453/head)
updated cblas.h and cblas_noconst.h by
2014-09-21 13:39:15 +0200
dab4edd06
added benchmark for gemm3m functions by
2014-09-21 12:00:41 +0200
9d7057366
bugfix for GEMM3M functions by
2014-09-21 11:41:43 +0200
7f234f8ed
added GEMM3M tests by
2014-09-21 10:55:08 +0200
9e829ce98
enabled cblas gemm3m functions by
2014-09-20 17:20:02 +0200
d49fd3388
disabled SYMM3M and HEMM3M functions because segment violations by
2014-09-20 15:27:40 +0200
f0f9b25bb
added test for CGEMM3M function by
2014-09-20 14:53:30 +0200
7aae4a62e
enabled use of GEMM3M functions by
2014-09-20 14:27:10 +0200
7a911569b
added test for GEMM3M functions by
2014-09-20 14:21:42 +0200
466bfb8b8
updated README.md by
2014-09-17 16:01:07 +0200
70d1ba09b
Update the doc for target list. by
2014-09-17 14:29:21 +0800
d293b78b6
Merge pull request #451 from eshelman/patch-1 by
2014-09-17 14:20:06 +0800
9912dbbcf
(refs/pull/451/head)
Add HASWELL to TargetList.txt by
2014-09-16 18:26:45 -0400
01bc462e8
Merge pull request #449 from wernsaar/develop by
2014-09-16 14:33:48 +0800
3300f5ebf
(refs/pull/449/head)
optimized multithreading lower limits by
2014-09-15 11:38:25 +0200
59e2c2055
Merge pull request #448 from wernsaar/develop by
2014-09-15 13:12:14 +0800
b7c9566ee
(refs/pull/448/head)
removed obsolete gemv kernel files by
2014-09-14 11:00:53 +0200
6df1b0be8
optimized zgemv_n_microk_sandy-4.c by
2014-09-14 10:21:22 +0200
2ac1e076c
added optimized zgemv_n kernel for sandybridge by
2014-09-14 09:02:05 +0200
9908b6031
bugfix in KERNEL.PILEDRIVER by
2014-09-13 16:26:53 +0200
8f100a14f
optimized cgemv_t kernel for haswell by
2014-09-13 16:13:27 +0200
53b5726b0
added optimized cgemv_t kernel for haswell by
2014-09-13 15:14:12 +0200
1a352b24e
updated KERNEL.HASWELL by
2014-09-13 12:23:27 +0200
5194818d4
updated zgemv_t_4.c by
2014-09-13 09:48:34 +0200
8a39cdb1c
added optimized zgemv_t kernel for haswell by
2014-09-13 09:47:07 +0200
fd2478c9e
optimized interface/zgemv.c for multithreading by
2014-09-12 19:18:23 +0200
0a1390f2d
enabled optimized zgemv_t kernel for bulldozer by
2014-09-12 17:43:47 +0200
a8b0812fe
optimized zgemv_t for bulldozer by
2014-09-12 17:42:25 +0200
a0fb68ab4
added optimized zgemv_t kernel for bulldozer by
2014-09-12 17:04:22 +0200
6544d30e4
(refs/pull/447/head)
Fix segfault when gemm is called immediately after set_num_threads. by
2014-09-12 08:55:23 -0500
44c11165d
bugfix in cgemv_t_4.c by
2014-09-12 14:12:24 +0200
564be4eb7
added optimized cgemv_t kernel by
2014-09-12 13:38:01 +0200
107c3ea7d
added optimized zgemv_t routine by
2014-09-12 12:35:20 +0200
bb8d69833
optimized zgemv_n_microk_haswell-4.c for small size by
2014-09-11 13:44:55 +0200
e0192a691
bugfix in zgemv_n_4.c by
2014-09-11 13:18:00 +0200
bced4594b
added optimized zgemv_n kernel by
2014-09-11 12:34:57 +0200
cafba99b6
bufix in cgemv_n_microk_haswell-4.c by
2014-09-11 11:12:44 +0200
ac8f232b2
more optimizations by
2014-09-11 10:25:48 +0200
f98e1244c
optimized cgemv_n_4.c by
2014-09-10 19:26:14 +0200
be95700b3
added optimized cgemv_kernel for haswell by
2014-09-10 14:11:24 +0200
4aa534ae9
added cgemv_n kernel, optimized for small sizes by
2014-09-10 13:45:13 +0200
1cba8e7b1
Merge pull request #446 from grisuthedragon/cblas_matcopy by
2014-09-10 16:31:31 +0800
d13e92f07
Merge pull request #445 from wernsaar/develop by
2014-09-10 16:28:14 +0800
baa46e4fb
(refs/pull/445/head)
added and tested optimized dgemv_n kernel for haswell by
2014-09-09 16:17:45 +0200
faab7a181
added optimized dgemv_n kernel for haswell by
2014-09-09 15:32:32 +0200
8109d8232
optimized dgemv_t kernel for haswell by
2014-09-09 14:38:08 +0200
debc6d1a0
bugfix in KERNEL.HASWELL by
2014-09-09 14:04:44 +0200
e73a0113e
added optimized gemv kernels by
2014-09-09 13:54:55 +0200
44f2bf9ba
added optimized dgemv_t kernel for haswell by
2014-09-09 13:34:22 +0200
a057e5434
(refs/pull/446/head)
add CBLAS interface for s/d/c/zimatcopy by
2014-09-09 09:52:13 +0200
cd34e9701
removed obsolete files by
2014-09-08 19:15:31 +0200
7794766d3
Add cblas_(s/d/c/z)omatcopy in order to have cblas interface for them. by
2014-09-08 17:57:44 +0200
658939faa
optimized dgemv_n kernel for small sizes by
2014-09-08 15:22:35 +0200
f511807fc
modified multithreading threshold by
2014-09-08 12:27:32 +0200
c4d9d4e5f
added haswell optimized kernel by
2014-09-08 12:25:16 +0200
7c0a94ff4
bugfix in sgemv_n_microk_haswell-4.c by
2014-09-08 10:54:33 +0200
cbbc80aad
added optimized sgemv_t kernel for haswell by
2014-09-08 10:13:39 +0200
2be5c7a64
bugfix for windows by
2014-09-07 21:48:42 +0200
80f778687
enabled optimized sgemv kernels for piledriver by
2014-09-07 21:13:57 +0200
553e27540
optimized sgemv_n kernel for sandybridge by
2014-09-07 20:53:30 +0200
7b3932b3f
optimized sgemv_n kernel for nehalem by
2014-09-07 19:20:08 +0200
75207b114
optimized sgemv_n for very small size of m by
2014-09-07 18:23:48 +0200
274828fa5
optimizations for very small sizes by
2014-09-07 13:45:03 +0200
5ae1731fe
better optimzations for sgemv_t kernel by
2014-09-06 21:28:57 +0200
c8eaf3ae2
optimized sgemv_t_4 kernel for very small sizes by
2014-09-06 19:41:57 +0200
3a7ab47ee
optimized sgemv_t by
2014-09-06 18:34:25 +0200
cf5544b41
optimization for small size by
2014-09-06 13:17:56 +0200
d143f84dd
added optimized sgemv_n kernel for haswell by
2014-09-06 12:08:48 +0200
779423747
undef WHEREAMI by
2014-09-06 11:01:42 +0200
a64fe9bcc
added optimized sgemv_n kernel for sandybridge by
2014-09-06 08:41:53 +0200
2021d0f9d
experimentally removed expensive function calls by
2014-09-05 15:05:53 +0200
6df7a8893
optimized sgemv_t for sandybridge by
2014-09-05 10:22:50 +0200
53de94369
bugfix for sgemv_n_4.c by
2014-09-04 18:55:52 +0200
7f910010a
optimized sgemv_n kernel for small sizes by
2014-09-04 13:09:27 +0200
3a5d8dbff
optimized sgemv_n_4.c by
2014-09-03 15:34:30 +0200
2a60c6d4b
optimized sgemv_n for small sizes by
2014-09-03 14:48:45 +0200