8533aca964
Avoid penalizing tall skinny matrices
2019-01-23 10:03:00 +01:00
cda81cfae0
Shift transition to multithreading towards larger matrix sizes
...
See #1886 and JuliaRobotics issue 500. trsm benchmarks on Haswell and Zen showed that with these values performance is roughly doubled for matrix sizes between 8x8 and 14x14, and still 10 to 20 percent better near the new cutoff at 32x32.
2019-01-19 00:10:01 +01:00
256eb588bb
Merge pull request #1963 from quickwritereader/develop
...
Blas1 single missing kernels implemented with vector builtins
2019-01-16 18:41:03 +01:00
a034e65512
Merge branch 'develop' into develop
2019-01-16 19:25:13 +04:00
8c3386be87
Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin},
...
Fixed idamin,icamin choosing the first occurance index of equal minimals
2019-01-16 15:16:21 +00:00
1e3ada6db4
Merge pull request #1960 from cnjsdfcy/Hygon
...
Add support for Hygon Dhyana
2019-01-16 10:27:14 +01:00
29dc72889f
Add support for Hygon Dhyana
2019-01-16 14:25:19 +08:00
dbc9a060ef
Fix missing braces in support_av() call
2019-01-14 22:41:31 +01:00
00401489c2
Fix missing braces in support_avx()
2019-01-14 22:38:32 +01:00
21c0f2af7b
Merge pull request #1957 from martin-frbg/issue1954
...
Move TLS key deletion to openblas_quit
2019-01-10 12:04:08 +01:00
ad2c386d6a
Move TLS key deletion to openblas_quit
...
fixes #1954 (as suggested by thrasibule in that issue)
2019-01-10 00:32:50 +01:00
8d99dba86b
Merge pull request #1949 from martin-frbg/issue1947
...
Query AVX2 and AVX512VL support when selecting x86 kernels
2019-01-08 20:44:08 +01:00
1650311246
Bump xcode to 8.3
2019-01-08 14:43:45 +01:00
cf5d48e833
Update OSX environment to Sierra
...
as homebrew seems to have dropped support for El Capitan in their gcc packages
2019-01-08 14:41:48 +01:00
191677b902
Add travis_wait to the OSX brew install phase
2019-01-08 10:46:47 +01:00
31ed19e8b9
Add message for SkylakeX and KNL fallbacks to Haswell
2019-01-05 19:41:13 +01:00
e1574fa2b4
Add xcr0 (os support) check
2019-01-05 18:08:02 +01:00
68eb3146ce
Add xcr0 (os support) check
2019-01-05 18:07:14 +01:00
0afaae4b23
Query AVX2 and AVX512VL capability in x86 cpu detection
2019-01-05 16:58:56 +01:00
ae1d1f74f7
Query AVX2 and AVX512 capability for runtime cpu selection
2019-01-05 16:55:33 +01:00
ed01f4932a
Merge pull request #1946 from martin-frbg/issue1908
...
More fixes for cross-compiling ARM64 targets
2019-01-04 01:37:37 +01:00
802f0dbde1
More fixes for cross-compiling ARM64 targets
...
Fixed core naming for DYNAMIC_ARCH. Corrected GEMM_DEFAULT entries and added SYMV_P. Replaced outdated VULCAN define for ThunderX2T99 with ARMV8 to get basic definitions back. For issue #1908
2019-01-03 22:17:31 +01:00
20d1aad13f
Fix missing quotes around thunderx targets
2019-01-02 20:15:35 +01:00
d11554c88f
Validate user supplied TARGET ( #1941 )
...
the build will now abort with an error message when an undefined build TARGET is named
Fixes #1938
2018-12-31 23:19:44 +01:00
ed704185ab
Increment version to 0.3.6.dev
2018-12-31 23:11:37 +01:00
2940798ea7
Increment version to 0.3.6.dev
2018-12-31 23:10:59 +01:00
1c75b65d53
Merge branch 'release-0.3.0' into develop
2018-12-31 23:07:53 +01:00
13d006339b
Update ChangeLog.txt with changes from 0.3.5
2018-12-31 23:00:46 +01:00
bf76162635
Merge pull request #1944 from hartzell/patch-1
...
Typo: Skyalke -> Skylake
2018-12-31 18:36:18 +01:00
0d52aefc6b
Typo: Skyalke -> Skylake
...
Worth fixing, it gets in the way of searching....
2018-12-30 14:55:34 -08:00
a6787b0f81
Merge pull request #1939 from TiborGY/patch-2
...
Fix typo in UNKNOWN core name
2018-12-30 20:10:05 +01:00
8643521127
Merge pull request #1943 from martin-frbg/issue1748
...
Re-enable loop unrolling in trmv and remove the scary warning
2018-12-30 20:07:01 +01:00
5a720cf9ca
Re-enable loop unrolling in trmv and remove the scary warning
...
fixes #1748 as that half of the fix for #1332 appears to have been an overreaction on my part.
2018-12-30 15:22:37 +01:00
ccd5945d38
Merge pull request #1942 from martin-frbg/issue1720
...
Delete the pthread key on cleanup in TLS mode
2018-12-30 14:47:05 +01:00
9f80e0f5fc
Remove stray include of complex.h
...
already provided conditionally by common.h via openblas_utest.h
Unconditional inclusion breaks older Android and similar platforms that use OPENBLAS_COMPLEX_STRUCT
2018-12-30 14:39:18 +01:00
bba1e67269
Delete the pthread key on cleanup in TLS mode
...
to avoid a crash when OpenBLAS was loaded via dlopen and libc tries to clean up the leaked TLS after dlclose
Fixes #1720
2018-12-29 21:59:31 +01:00
93240f489e
Fix wrong case in TARGET setting for Alpine
2018-12-29 18:12:54 +01:00
7cbc2c37d6
Update cpuid_mips64.c
2018-12-28 14:36:39 +01:00
c329de2931
Update Makefile
2018-12-28 14:35:41 +01:00
187233953c
Update cpuid_mips.c
2018-12-28 14:34:38 +01:00
09170268a3
Update cpuid_arm.c
2018-12-28 14:33:18 +01:00
211120c508
Fix typo in UNKNOWN core name
...
Should be of no consequence, right?
2018-12-27 23:09:21 +01:00
9e4d190f4f
Merge pull request #1932 from martin-frbg/issue1915
...
Add -fPIC to provided CFLAGS/FFLAGS if required
2018-12-24 23:48:33 +01:00
fe02ba86a4
Remove unnecessary change again
2018-12-24 20:46:04 +01:00
284fb00971
Merge pull request #1934 from fenrus75/betagoof
...
Fix thinko in skylake beta handling
2018-12-24 19:53:50 +01:00
795285c587
Fix thinko in skylake beta handling
...
casting ints is cheaper but it has a rounding, not memory casing effect, resulting in
invalid outcome
2018-12-24 18:49:50 +00:00
d6818777d1
Make sure that -fPIC is present if needed
2018-12-23 23:47:37 +01:00
5bd21ab6e1
Make sure that -fPIC is present when needed
...
override user-provided FFLAGS if necessary
2018-12-23 23:46:48 +01:00
e1eab96502
Merge pull request #1931 from martin-frbg/pr1921
...
Add -mavx2 to TARGET=HASWELL builds
2018-12-23 23:15:54 +01:00
76b4b8980f
Use -dumpversion with gcc only
2018-12-23 19:08:19 +01:00
Martin Kroeker
Abdelrauf
Ubuntu
caiyu
TiborGY
George Hartzell
Arjan van de Ven