floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,957 Commits 47 Branches 64 Tags
b3ac6ee2227c1c62c6f0b93d8e9985423fabdc9d
Commit Graph

3957 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker
b3ac6ee222 Define alternate kernels for big-endian PPC970 
The altivec versions of SGEMM and CGEMM fail most test in LAPACK-TESTING when compiled for big endian, STRSM/CTRSM even cause segfaults. The rot kernels either fail the corresponding utest or lead to failures in LAPACK-TESTING.
 2019-11-17 15:19:39 +01:00
Martin Kroeker
6082e556cd Use "generic" S/CGEMM unroll M on big-endian PPC970 
as the respective PPC970 "altivec" kernels give wrong results when compiled for big endian
 2019-11-17 15:10:26 +01:00
Martin Kroeker
4e466d739c Merge pull request #15 from xianyi/develop 
rebase
 2019-11-09 18:52:08 +01:00
Martin Kroeker
4c6a457358 Merge pull request #2300 from wjc404/develop 
Optimize SGEMM on SKYLAKEX CPUs
 2019-11-06 07:27:33 +01:00
wjc404
836c414e22 optimizations of software prefetching 2019-11-05 13:36:56 +08:00
Martin Kroeker
d403eb3c2f Merge pull request #2302 from martin-frbg/ppc970 
Disable three-operand DCBT on PPC970 regardless of operating system
 2019-11-04 22:55:05 +01:00
Martin Kroeker
3cd97f1a80 Merge pull request #2301 from martin-frbg/ppc8be 
Disable IDAMIN/MAX and IZAMIN/MAX optimizations on big-endian POWER8
 2019-11-04 22:54:28 +01:00
Martin Kroeker
9955f0996f Merge pull request #2294 from martin-frbg/ios-cleanup 
Remove obsolete workarounds for IOS on ARMV8
 2019-11-04 22:53:58 +01:00
wjc404
430c11e135 Add files via upload 2019-11-04 20:10:12 +08:00
wjc404
fbacd2605d optimizations via software prefetches 2019-11-04 19:37:19 +08:00
Martin Kroeker
6fa89b06a1 Use the two-operand form of DCBT on all PPC970 regardless of OS 
There seems to be no advantage to the three-operand form used in the earliest GotoBLAS kernels, and it causes compilation problems  on other than the previously special-cased platforms as well
 2019-11-03 22:55:31 +01:00
Martin Kroeker
68597002ea The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:42:46 +01:00
Martin Kroeker
d2a6285549 The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:41:19 +01:00
Martin Kroeker
d999688d1a The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:39:06 +01:00
Martin Kroeker
928fe1b28e The assembly microkernel is not safe to use on ELFv1 2019-11-03 22:37:27 +01:00
Martin Kroeker
ccc28c6d60 Merge pull request #13 from xianyi/develop 
resync with upstream
 2019-11-03 22:33:31 +01:00
wjc404
ae43b75a6a Add files via upload 2019-11-02 10:09:19 +08:00
wjc404
54fc06fd70 Add files via upload 2019-11-02 10:06:13 +08:00
wjc404
1df9a2013d new sgemm kernel for skylakex 2019-11-02 00:00:48 +08:00
wjc404
274ff5cdb8 update sgemm_q on skylakex cpus 2019-11-01 23:59:18 +08:00
Martin Kroeker
eb2eddf241 Merge pull request #2296 from kdunee/develop 
Fixed a minor cmake problem, occuring when DYNAMIC_ARCH=ON and CMAKE_C_FLAGS was empty
 2019-10-28 13:24:18 +01:00
k.dunikowski
8691825944 Fixed a minor cmake problem, occuring when DYNAMIC_CORE=ON and CMAKE_C_FLAGS was empty 2019-10-28 08:51:05 +01:00
Martin Kroeker
7dc8a76f60 Merge pull request #2293 from martin-frbg/pr2288 
Add support for NetBSD by adding it to the existing xBSD conditionals
 2019-10-25 23:46:39 +02:00
Martin Kroeker
df857551c0 Remove special parameter set for obsolete IOS/ARMV8 workaround 2019-10-25 23:07:00 +02:00
Martin Kroeker
85ccdce8c4 Remove the IOS fallbacks to generic C kernels 2019-10-25 23:02:37 +02:00
Martin Kroeker
aeabe0a83f Fix regex to parse -R options with and without whitespace 
Both forms are seen on NetBSD (#2288)
 2019-10-25 22:52:30 +02:00
Martin Kroeker
1b90989662 Add NetBSD to the xBSD conditionals 2019-10-25 12:52:49 +02:00
Martin Kroeker
e3e8b5cdca Add NetBSD 2019-10-25 12:51:06 +02:00
Martin Kroeker
69b16a894d Merge pull request #2292 from martin-frbg/g95fixes 
Improve support for g95 and non-GNU ld
 2019-10-25 10:35:17 +02:00
Martin Kroeker
6782e5767d Merge pull request #2291 from martin-frbg/gensymbol 
Fix netlib 3.7/3.8 function enumeration for linktest
 2019-10-25 10:34:50 +02:00
Martin Kroeker
48f5a89f92 Merge pull request #2282 from martin-frbg/issue2281 
Optimize RPCC function on ARM64
 2019-10-25 09:56:30 +02:00
Martin Kroeker
4ae1610f37 Merge pull request #2290 from martin-frbg/cpuidfixes 
Fixup x86 cpuid changes from #2283
 2019-10-24 22:52:15 +02:00
Martin Kroeker
911c3e2f4b Improve support for g95 and non-GNU ld 
Auto-add "-fno-second-underscore" option to make LAPACKE compile (as it calls LAPACK functions that may have gotten a second underscore added otherwise). Also support -R for rpath when parsing compiler directives in f_check
 2019-10-24 22:43:27 +02:00
Martin Kroeker
fab49e49e5 Move most lapack 3.7/3.8 additions to the embedded_underscores list 
to allow linktest to pass with a compiler that adds a second underscore to such names
 2019-10-24 21:26:20 +02:00
Martin Kroeker
b687fba5bc Disable direct clock register access on IOS and Android 
as I find conflicting information on accessibility from non-priviledged processes
 2019-10-24 21:18:17 +02:00
luzpaz
46a8c2519a Remove prototype of unused, unimplemented function (#2274) 
* Fix source typo

Found via `codespell -q 3 -L amin,als,ba,dum,mone,nd,nto,orign -S Changelog.txt,./lapack*`

* Remove beta-thread function per request
 2019-10-24 18:56:53 +02:00
Martin Kroeker
e9437eebd2 Restore Goldmont ID and improve QEMU support 
#2283 had inadvertently removed Goldmont+, and cpuid was reporting a mix of Core2 and Pentium2 for some QEMU configurations
 2019-10-24 18:45:27 +02:00
Martin Kroeker
3a39062cfc Merge pull request #12 from xianyi/develop 
resync with upstream
 2019-10-24 18:40:13 +02:00
Martin Kroeker
eaa0be1313 Merge pull request #2286 from wjc404/develop 
AVX512 DGEMM kernel
 2019-10-20 12:44:19 +02:00
wjc404
6ff013bae0 native support for icopy_4 
90% MKL 1-thread performance.
 2019-10-19 03:54:44 +08:00
wjc404
0d669e04bb Update dgemm_kernel_8x8_skylakex.c 2019-10-18 15:00:17 +08:00
wjc404
17cdd9f9e1 some correction 2019-10-18 14:58:07 +08:00
wjc404
6bcb06fcb1 make further changes to icopy_8 easier 2019-10-18 10:47:31 +08:00
wjc404
b7315f8401 Add files via upload 2019-10-16 19:23:36 +08:00
wjc404
9b19e9e1b0 Update dgemm_kernel_8x8_skylakex.c 2019-10-16 10:14:51 +08:00
wjc404
6bd67ddbab Update dgemm_kernel_8x8_skylakex.c 2019-10-16 03:20:08 +08:00
wjc404
5da9484d93 Add files via upload 2019-10-16 02:01:13 +08:00
wjc404
844629af57 Add files via upload 2019-10-16 02:00:34 +08:00
Martin Kroeker
2beaa82c05 Merge pull request #2283 from martin-frbg/issue2176 
Support QEMU virtual cpu in 64bit mode as CORE2 or BARCELONA
 2019-10-09 22:06:09 +02:00
Martin Kroeker
e8a2aed2b9 Support QEMU cpu calling itself 64bit AMD Athlon as well 
Some QEMU instances pretend to be "AuthenticAMD" with the same family 6/model 6 even when running on an Intel host
(could be related to qemu or libvirt version and/or kvm availability). Also fix the define to depend on __x86_64__ set by the
compiler, the defines using __64BIT__ will only work for getarch_2nd.
 2019-10-09 18:24:13 +02:00