2480e5046
(tag: v0.3.19, refs/pull/3489/head)
Update version to 0.3.19 by
2021-12-19 20:55:57 +0100
488911486
Merge pull request #3488 from xianyi/develop by
2021-12-19 20:54:49 +0100
54a0c0bce
(refs/pull/3488/head)
Merge branch 'release-0.3.0' into develop by
2021-12-19 16:35:07 +0100
6025daca6
Update version to 0.3.19 by
2021-12-19 16:32:04 +0100
e545614cd
Merge pull request #3487 from martin-frbg/0319changes by
2021-12-19 16:30:47 +0100
b6001a2ee
(refs/pull/3487/head)
Update with 0.3.19 changes by
2021-12-19 14:34:14 +0100
9c8d1e013
Merge pull request #3486 from martin-frbg/nvhpc by
2021-12-18 23:09:30 +0100
ed430cd96
(refs/pull/3486/head)
Update -tp option for recent nvfortran on x86_64 by
2021-12-18 21:56:26 +0100
b3f4b8c95
Merge pull request #3485 from martin-frbg/issue3453 by
2021-12-17 11:08:36 +0100
6ed52576f
(refs/pull/3485/head)
Add feature-based fallback for unknown x86_64 cpus by
2021-12-16 22:02:49 +0100
126ad4899
Merge pull request #3484 from martin-frbg/issue3481 by
2021-12-16 21:50:28 +0100
f67a0620a
Merge pull request #3480 from wzgpeter/develop by
2021-12-16 21:50:06 +0100
449fb7d84
Merge pull request #3478 from ffontaine/develop by
2021-12-16 21:49:19 +0100
7a7fbb11c
(refs/pull/3484/head)
define "unlikely" on non-cygwin too by
2021-12-16 17:28:28 +0100
b31349c22
Open up delayed (re)init to non-Cygwin OS as well by
2021-12-16 16:58:12 +0100
4d61e453c
Merge pull request #3483 from martin-frbg/issue3482 by
2021-12-16 11:54:20 +0100
f3b51ec60
(refs/pull/3483/head)
move brace inside the ifdef block by
2021-12-16 09:37:58 +0100
92b7b949d
(refs/pull/3480/head)
fix bug in zscal function by
2021-12-15 00:22:19 -0800
c270c7b01
(refs/pull/3479/head)
fix bug in zscal function by
2021-12-15 00:22:19 -0800
a0cc119f2
(refs/pull/3478/head)
Makefile: also consider -O, -Og and -Os when stripping flags by
2021-12-14 23:36:16 +0100
c8d05aa7a
Move the threads overflow flag under the protection of the local blas lock (#3476) by
2021-12-13 08:34:52 +0100
2f220fdcf
(refs/pull/3476/head)
Add files via upload by
2021-12-12 21:39:02 +0100
89e1a67da
Update .travis.yml by
2021-12-12 20:06:28 +0100
23290003f
Update .travis.yml by
2021-12-12 19:11:54 +0100
b0a590f4f
Merge pull request #3475 from wjc404/optimize-A53-dgemm by
2021-12-12 19:09:08 +0100
f4d1f0333
Merge pull request #3474 from rafaelcfsousa/rafael/cmake_power by
2021-12-12 19:08:27 +0100
6a0497c3e
Move accesses to the overflow flag into the scope of the blas lock by
2021-12-12 14:24:01 +0100
b610d2de3
(refs/pull/3475/head)
optimize cgemm on ARM cortex A53 & cortex A55 by
2021-12-12 17:22:52 +0800
697e2752d
Merge pull request #3464 from binebrank/arm_sve_sgemm by
2021-12-11 20:35:22 +0100
60684d636
(refs/pull/3433/head)
Update .travis.yml by
2021-12-11 19:11:17 +0100
ffb389326
Update .travis.yml by
2021-12-11 18:26:35 +0100
a8f62a347
(refs/pull/3464/head)
fix UNROLL_MN and add to targets for SVE by
2021-12-11 16:37:23 +0100
774267fda
adjust Makefile.L3 for SVE by
2021-12-11 16:35:08 +0100
d38110a5c
(refs/pull/3474/head)
Use CMake variables instead of as by
2021-12-10 17:35:28 -0600
23a756135
Fix error cmake (small kernels) by
2021-12-09 09:57:39 -0600
214fbcee1
Fix cmake for power by
2021-12-09 08:28:17 -0600
f7f7fea0d
Merge pull request #3472 from kavanabhat/p10_aixas_p8 by
2021-12-09 07:28:57 +0100
2241068c2
Merge pull request #3469 from martin-frbg/issue2986 by
2021-12-08 22:19:32 +0100
3e9a52869
Fix ar path in ARMV7 Darwin NDK build on Azure (#3473) by
2021-12-08 22:18:44 +0100
847e335aa
(refs/pull/3473/head)
Update azure-pipelines.yml by
2021-12-08 18:13:26 +0100
c0cb437bd
Update azure-pipelines.yml by
2021-12-08 16:33:27 +0100
f21501149
Fix ar path in ARMV7 Darwin NDK build by
2021-12-08 15:46:05 +0100
eee3381cb
(refs/pull/3472/head)
Fallback for Power kernels by
2021-12-08 03:52:23 -0600
02c7390af
(refs/pull/3471/head)
Update .travis.yml by
2021-12-07 13:50:41 +0100
5378046ab
(refs/pull/3469/head)
roll back DGEMM kernels to 4x8 when compiling for DYNAMIC_ARCH by
2021-12-06 19:43:54 +0100
dd1f64537
switch DGEMM unroll parameters for SkylakeX if DYNAMIC_ARCH by
2021-12-06 19:42:51 +0100
a1fea1fe2
sgemm v2x8 SVE kernel by
2021-12-05 18:47:29 +0100
2ae73a2b3
Merge pull request #3468 from martin-frbg/issue3467 by
2021-12-05 15:52:44 +0100
8d11278e2
(refs/pull/3468/head)
Fix hardcoded library name by
2021-12-05 14:38:41 +0100
abe1ce343
strmm sve v1x8 kernel by
2021-12-05 14:03:08 +0100
ea09355ea
Fix DYNAMIC_ARCH builds with CMAKE on OSX and add corresponding test to Azure CI (#3409) by
2021-12-04 22:24:02 +0100
d62dc3e85
(refs/pull/3409/head)
Update azure-pipelines.yml by
2021-12-04 19:28:47 +0100
7986da09d
Update CMakeLists.txt by
2021-12-04 14:45:45 +0100
8fe42d719
Update CMakeLists.txt by
2021-12-04 10:21:38 +0100
54d321d74
Merge pull request #3466 from rafaelcfsousa/rafael/small_matrix_p10 by
2021-12-03 12:12:20 +0100
c248442df
Merge pull request #3465 from kavanabhat/develop by
2021-12-03 12:11:43 +0100
1470b7e4d
Delete test_zhemv.c by
2021-12-03 11:41:53 +0100
0882db30a
Merge pull request #3455 from cenewcombe/develop by
2021-12-03 10:01:20 +0100
db7f6e1b4
Update CMakeLists.txt by
2021-12-03 10:00:27 +0100
9a45b5123
(refs/pull/3465/head)
Update Makefile.system by
2021-12-02 13:29:38 +0530
4e4297f5e
Update CMakeLists.txt by
2021-12-01 21:57:31 +0100
e2a78c083
Update CMakeLists.txt by
2021-12-01 19:29:48 +0100
84125e403
Merge pull request #1 from kavanabhat/as_check_fix by
2021-12-01 20:30:43 +0530
af4ec2653
Update CMakeLists.txt by
2021-12-01 15:06:18 +0100
7b5b93037
Fix truncated assembler checks by
2021-12-01 19:30:40 +0530
ff3f78d2e
Update CMakeLists.txt by
2021-12-01 11:22:02 +0100
0628233cc
Update CMakeLists.txt by
2021-11-30 22:25:49 +0100
a140f1801
Update CMakeLists.txt by
2021-11-30 17:33:52 +0100
c21bf6890
Update CMakeLists.txt by
2021-11-30 13:20:09 +0100
f52ff4060
Update CMakeLists.txt by
2021-11-30 10:29:14 +0100
0de36f7b5
trmm sve copy fucntions for single precision by
2021-11-29 21:25:05 +0100
9d855c0ab
Update CMakeLists.txt by
2021-11-29 20:41:52 +0100
21501f7bc
Update CMakeLists.txt by
2021-11-28 23:55:25 +0100
fa7dc9ecf
Update CMakeLists.txt by
2021-11-28 23:37:07 +0100
c78fdcc80
(refs/pull/3466/head)
[POWER] Add support for SMALL_MATRIX_OPT by
2021-11-16 14:47:41 -0600
86ae89bf3
add sgemm kernel and copy functions for sgemm and ssymm by
2021-11-28 18:12:47 +0100
454edd741
Merge pull request #3425 from binebrank/arm_sve_dgemm by
2021-11-26 16:14:55 +0100
bcfbdc81b
Merge pull request #3459 from rafaelcfsousa/fix_cmake by
2021-11-26 15:19:24 +0100
7c6370cbf
Merge pull request #3462 from martin-frbg/azure-alpine2 by
2021-11-26 13:40:23 +0100
fbfc8b1b8
(refs/pull/3462/head)
Update alpine-chroot-install again by
2021-11-26 13:39:49 +0100
ca65a4e91
(refs/pull/3425/head)
update CONTRIBUTORS.md by
2021-11-26 13:11:19 +0100
1af73ce38
Adapt CMake for SVE by
2021-11-26 10:35:01 +0100
e7fca060d
Merge pull request #3457 from wjc404/optimize-A53-dgemm by
2021-11-26 10:30:47 +0100
bc4c98de2
Merge pull request #3456 from martin-frbg/issue3444 by
2021-11-26 10:29:28 +0100
c3b1e55bd
AzureCI: Fetch alpine-chroot-install from master to get key updates (#3460) by
2021-11-26 09:38:41 +0100
fcddd32cb
(refs/pull/3460/head)
Update azure-pipelines.yml by
2021-11-25 23:03:33 +0100
359dc11cf
Update azure-pipelines.yml by
2021-11-25 22:04:47 +0100
d6af505bd
Update azure-pipelines.yml by
2021-11-25 20:33:28 +0100
ed688a1e4
Fetch alpine-chroot-install from master to get key updates by
2021-11-25 20:01:21 +0100
5c1cd5e0c
(refs/pull/3457/head)
MOD: add comments to a53 zgemm kernel by
2021-11-25 22:48:48 +0800
d5c9353f1
(refs/pull/3459/head)
Modify the order that cmake set the KERNEL variables (generic now is fallback) by
2021-11-24 20:07:20 -0600
fb891f33d
Fix the cmake parser to identify more patterns by
2021-11-24 14:07:28 -0600
9f59b19fc
MOD: optimize zgemm on cortex-A53/cortex-A55 by
2021-11-24 21:51:45 +0800
f4da23dcb
reduced dgemm_unroll_m to work with 128-bit sve by
2021-11-23 21:18:08 +0100
531a28b6a
removed unused code (compiler warnings) by
2021-11-22 10:12:34 +0100
9b9cb90bb
modify Makefile for SVE copy by
2021-11-22 09:54:20 +0100
9388f05a3
configure SVE Makefile by
2021-11-21 18:33:43 +0100
b58d4f31a
some clean-up & commentary by
2021-11-21 14:56:27 +0100
52a3f004a
(refs/pull/3456/head)
Fix unintended reversion of recent CortexA53 changes by
2021-11-20 23:54:48 +0100
a3cd36acf
Add CMAKE support for cross-compiling to MIPS32 by
2021-11-20 17:34:28 +0100