phynexis-deps/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3,840 Commits 60 Branches 70 Tags
Travisppc
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Martin Kroeker 5fdf9ad24f Merge pull request #2228 from martin-frbg/issue2227 
Add Intel Goldmont Plus CPUID
 2019-08-19 18:26:51 +02:00
Martin Kroeker 2fe967c542 Merge branch 'develop' into issue2227 2019-08-19 14:20:39 +02:00
Martin Kroeker 6d8595351c Add Intel Goldmont Plus CPUID 
fixes #2227
 2019-08-19 14:19:21 +02:00
Martin Kroeker f40200f559 Merge pull request #2223 from martin-frbg/getarch-pgi 
Make getarch compile with PGI
 2019-08-16 12:21:30 +02:00
Martin Kroeker a95a5e52b8 Fix PGI compiler detection for getarch 2019-08-16 09:00:11 +02:00
Martin Kroeker e3d846ab57 Do not use -march=native with the PGI compiler 2019-08-16 08:58:10 +02:00
Martin Kroeker 8506386d82 Merge pull request #1 from xianyi/develop 
rebase
 2019-08-16 08:56:15 +02:00
Martin Kroeker 9ef96b32a6 Add multithreading support to the x86_64 zdot kernel (#2222) 
* Add multithreading support

copied from the ThunderX2T99 kernel. For #2221
 2019-08-15 22:09:12 +02:00
Martin Kroeker b48c025974 Merge pull request #2218 from martin-frbg/issue2215 
Make the new DGEMM regression test properly depend on CBLAS and LAPACKE
 2019-08-14 07:32:31 +02:00
Martin Kroeker a1fce67743 Make the new DGEMM regression test properly depend on CBLAS and LAPACKE 
fixes #2215
 2019-08-13 22:29:48 +02:00
Martin Kroeker 103b32fdb7 Merge pull request #2216 from martin-frbg/issue2214 
Remove case-sensitivity in x86 LSAME on (AMD) cpus without CMOV
 2019-08-13 13:59:33 +02:00
Martin Kroeker aef9804089 Fix unwanted case-sensitivity in x86 LSAME for (AMD) processors without CMOV 
Problem was already noticed some years ago in #238, but back then the problem was only corrected in one of the #ifdef branches.
Fixes #2214
 2019-08-13 10:19:10 +02:00
Martin Kroeker 303869f572 Update with changes from 0.3.7 2019-08-11 23:31:36 +02:00
Martin Kroeker 02d9203981 Increment version to 0.3.8.dev 2019-08-11 23:28:47 +02:00
Martin Kroeker 7b6808b69c Increment version to 0.3.8.dev 2019-08-11 23:28:13 +02:00
Martin Kroeker 321288597c Merge pull request #2212 from martin-frbg/nofort-nolib 
Avoid spurious dependency on the fortran runtime despite NOFORTRAN=1
 2019-08-11 20:26:34 +02:00
Martin Kroeker be147a9f28 Avoid adding a spurious dependency on the fortran runtime despite NOFORTRAN=1 
for cases where a fortran compiler is present but not wanted (e.g. not fully functional)
 2019-08-11 16:24:39 +02:00
Martin Kroeker c275290ea6 Merge pull request #2211 from martin-frbg/arm64_gcc_trivial 
Silence two nuisance warnings from gcc
 2019-08-11 16:08:05 +02:00
Martin Kroeker b7bbb02447 Silence two nuisance warnings from gcc 2019-08-11 12:46:05 +02:00
Martin Kroeker bf1430f7d7 Merge pull request #2208 from martin-frbg/munmap-debug 
Provide more information on mmap/munmap failure
 2019-08-09 07:55:35 +02:00
Martin Kroeker dccff2e785 Merge pull request #2206 from martin-frbg/zen-dtrmm 
Replace vpermpd with vpermilpd in the Haswell DTRMM kernel
 2019-08-09 07:55:20 +02:00
Martin Kroeker 5c3458a6e7 Merge pull request #2199 from martin-frbg/zen-dtrsm 
Replace most vpermpd calls in the Haswell DTRSM_RN kernel
 2019-08-09 07:55:02 +02:00
Martin Kroeker 1776ad82c0 Add files via upload 2019-08-09 00:08:11 +02:00
Martin Kroeker 4e2f81cfa1 Provide more information on mmap/munmap failure 
for #2207
 2019-08-08 23:15:35 +02:00
Martin Kroeker acf6002ab2 Replace most vpermpd calls in the Haswell DTRSM_RN kernel 2019-08-03 12:40:13 +02:00
Martin Kroeker 96a794e9fd Merge pull request #2198 from martin-frbg/icelake 
Update CPUID recognition for Intel Ice Lake
 2019-08-02 08:36:14 +02:00
Martin Kroeker 3d36c45116 Add CPUID identification of Intel Ice Lake 2019-08-01 22:52:35 +02:00
Martin Kroeker 648491e1aa Autodetect Intel Ice Lake (as SKYLAKEX target) 2019-08-01 22:51:09 +02:00
Martin Kroeker 2dfb804cb9 Replace vpermpd with vpermilpd in the Haswell DTRMM kernel 
to improve performance on AMD Zen (#2180) applying wjc404's improvement of the DGEMM kernel from #2186
 2019-07-28 23:17:28 +02:00
Martin Kroeker 4c153ec9da Merge pull request #2196 from wjc404/develop 
Add vbroadcastsd kernel to dgemm_kernel_4x8_haswell.S
 2019-07-28 23:11:40 +02:00
Martin Kroeker f0406a7708 Merge pull request #2112 from ffontaine/develop 
Makefile.arm: remove -march flags
 2019-07-27 13:00:13 +02:00
Martin Kroeker 561f3fd995 Merge pull request #2193 from martin-frbg/makeutest 
Override special make variables
 2019-07-24 20:19:21 +02:00
Martin Kroeker 30efed14d1 Unset special make variables in ctest Makefile as well 2019-07-24 15:26:09 +02:00
Martin Kroeker af2e7f28fc Override special make variables 
as seen in https://github.com/xianyi/OpenBLAS/issues/1912#issuecomment-514183900 , any external setting of TARGET_ARCH (which could result from building OpenBLAS as part of a larger project that actually uses this variable) would cause the utest build to fail. 
(Other subtargets appear to be unaffected as they do not use implicit make rules)
 2019-07-23 16:56:40 +02:00
Martin Kroeker 4250e6ed64 Merge pull request #2191 from tylerjereddy/conditional_updates 
MAINT: remove legacy CMake endif()
 2019-07-23 16:20:39 +02:00
Martin Kroeker 7b0b7c11d2 Merge pull request #2190 from martin-frbg/zdot-zen 
Replace vpermpd with vpermilpd in the Haswell/Zen zdot microkernel
 2019-07-23 16:15:08 +02:00
Martin Kroeker d14cf1ccf4 Merge pull request #2189 from wjc404/develop 
Update dgemm_kernel_4x8_haswell.S for reducing cache misses
 2019-07-23 08:32:56 +02:00
Martin Kroeker 28e96458e5 Replace vpermpd with vpermilpd 
to improve performance on Zen/Zen2 (as demonstrated by wjc404 in #2180)
 2019-07-22 08:28:16 +02:00
Martin Kroeker b0b7600bef Merge pull request #2186 from wjc404/develop 
Update "dgemm_kernel_4x8_haswell.S" for improving performance on zen2 chips
 2019-07-18 16:04:44 +02:00
Martin Kroeker bafa021ed6 Merge pull request #2181 from isuruf/install_name 
Change install_name on osx to match linux
 2019-07-09 20:08:52 +02:00
Martin Kroeker 08dedf4c5e Merge pull request #2177 from martin-frbg/noaff 
Fix surprising behaviour of NO_AFFINITY=0
 2019-07-07 18:28:21 +02:00
Martin Kroeker b89c781637 Fix surprising behaviour of NO_AFFINITY=0 2019-07-07 16:04:45 +02:00
Martin Kroeker dd7ff77f4b Merge pull request #2175 from martin-frbg/cmake-mingw-fixes 
Fix CMAKE compilation with MinGW32 and add it to Appveyor
 2019-07-06 18:07:19 +02:00
Martin Kroeker 8fb76134bc Mingw32 needs leading underscore on object names 
(also copy BUNDERSCORE settings for FORTRAN from the corresponding Makefile)
 2019-07-06 15:07:15 +02:00
Martin Kroeker 04d671aae2 Make disabling DYNAMIC_ARCH on unsupported systems work 
needs to be unset in the cache for the change to have any effect
 2019-07-06 15:05:04 +02:00
Martin Kroeker f69a0be712 Add getarch flags to disable AVX on x86 
(and other small fixes to match Makefile behaviour)
 2019-07-06 15:02:39 +02:00
Martin Kroeker ae9e8b131e Add mingw builds to Appveyor config 2019-07-06 14:30:33 +02:00
Martin Kroeker 9086543f50 Utest needs CBLAS but not necessarily FORTRAN 2019-07-06 14:29:47 +02:00
Martin Kroeker abea977ded Merge pull request #2162 from martin-frbg/pgi 
Fixes for PGI compiler
 2019-07-03 19:16:30 +02:00
Martin Kroeker 6b6c9b1441 Merge pull request #2172 from quickwritereader/develop 
power9 cgemm/ctrmm. new sgemm 8x16
 2019-07-01 21:06:02 +02:00
Martin Kroeker 2f13f04224 Merge pull request #2170 from pkubaj/patch-1 
Fix build on PPC970 for FreeBSD
 2019-06-30 23:29:02 +02:00
Martin Kroeker 3b761892df Merge pull request #2169 from pkubaj/develop 
Fix build on FreeBSD/powerpc64.
 2019-06-25 12:56:33 +02:00
Martin Kroeker 7684c4f8f8 PGI compiler does not like -march=native 2019-06-20 19:56:01 +02:00
Martin Kroeker 7faf42b7bb Merge pull request #2167 from kavanabhat/dtrmm_power8_segfault 
Fix DTRMMKERNEL register save for power8 64-bit mode (Fix for #2166)
 2019-06-19 14:38:01 +02:00
Martin Kroeker 280552b988 Fix mov syntax 2019-06-16 18:35:43 +02:00
Martin Kroeker bbd4bb0154 Zero ecx with a mov instruction 
PGI assembler does not like the initialization in the constraints.
 2019-06-16 15:04:10 +02:00
Martin Kroeker 6d3efb2b58 Update Makefile.x86_64 2019-06-14 08:08:11 +02:00
Martin Kroeker d9ff2cd90d Do not force gcc options on non-gcc compilers 
fixes compile failure with pgi 18.10 as reported on OpenBLAS-users
 2019-06-13 23:01:35 +02:00
Martin Kroeker 2a43062de7 Merge pull request #2159 from martin-frbg/issue2149 
Avoid unintentional activation of TLS codepath via USE_TLS=0
 2019-06-10 19:12:45 +02:00
Martin Kroeker 4ea794a522 Avoid unintentional activation of TLS code via USE_TLS=0 
fixes #2149
 2019-06-10 17:24:15 +02:00
Martin Kroeker ece0bfb881 Merge pull request #2158 from martin-frbg/issue2143 
Remove any inadvertent use of -march=native from DYNAMIC_ARCH builds
 2019-06-10 14:08:11 +02:00
Martin Kroeker 1f4b6a5d5d Remove any inadvertent use of -march=native from DYNAMIC_ARCH builds 
from #2143, -march=native precludes use of more specific options like -march=skylake-avx512 in individual kernels, and defeats the purpose of dynamic arch anyway.
 2019-06-10 09:50:13 +02:00
Martin Kroeker be8f70d269 Merge pull request #2157 from martin-frbg/2154-2 
Add gfortran workaround for potential ABI violation
 2019-06-09 12:19:08 +02:00
Martin Kroeker e674e1c735 Update fc.cmake 2019-06-09 09:31:13 +02:00
Martin Kroeker 6ca898b63b Add gfortran workaround for potential ABI violation 
for #2154
 2019-06-08 23:17:03 +02:00
Martin Kroeker 26411acd56 Merge pull request #2148 from TiborGY/cpp_thread_test_2 
Thread safety tester using C++11 threading (cleaned history)
 2019-06-07 13:23:07 +02:00
Martin Kroeker 0ab4076dd8 Merge pull request #2156 from martin-frbg/issue2154 
Add gfortran workaround for C->FORTRAN ABI violation
 2019-06-06 13:43:12 +02:00
Martin Kroeker a0caa762b3 Add gfortran workaround for ABI violations 
for #2154 (see gcc bug 90329)
 2019-06-06 10:24:16 +02:00
Martin Kroeker 900d5a3205 Add gfortran workaround for ABI violations in LAPACKE 
for #2154 (see gcc bug 90329)
 2019-06-06 10:18:40 +02:00
Martin Kroeker a17cf36225 Merge pull request #2153 from quickwritereader/develop 
improved power9 zgemm,sgemm
 2019-06-06 07:42:56 +02:00
Martin Kroeker 909ad04aef Merge pull request #2145 from martin-frbg/1912-3 
Separate implementations of AMAX and IAMAX on arm
 2019-06-05 20:27:45 +02:00
Martin Kroeker 417efd41c6 Merge pull request #2110 from pc2/cpu-detection 
Fix detection of Skylake processors when using GCC
 2019-06-05 20:27:05 +02:00
Martin Kroeker 27649b9543 Document NO_AVX512 
for #2151
 2019-06-03 11:01:33 +02:00
Martin Kroeker 74c10b57c6 Use generic kernels for complex (I)AMAX to support softfp 2019-05-30 11:38:11 +02:00
Martin Kroeker c5495d2056 Ensure correct output for DAMAX with softfp 2019-05-30 11:25:43 +02:00
Martin Kroeker c70496b108 Separate implementations of AMAX and IAMAX on arm 
As noted in #1912 and comment on #1942, the combined implementation happens to "do the right thing" on hardfp, but cannot return both value and index on softfp where they would have to share the return register
 2019-05-29 15:02:51 +02:00
Martin Kroeker ca8d8835f5 Merge pull request #2144 from xianyi/revert-2142-issue1912-2 
Revert "Add softfp support in min/max kernels"
 2019-05-29 14:09:10 +02:00
Martin Kroeker d76b20b4d2 Revert "Add softfp support in min/max kernels" 2019-05-29 14:07:17 +02:00
Martin Kroeker 85af04da3c Merge pull request #2142 from martin-frbg/issue1912-2 
Add softfp support in min/max kernels
 2019-05-28 22:56:08 +02:00
Martin Kroeker 11e0dcbffb Merge pull request #2141 from martin-frbg/issue1912 
Build and run utests independently of fortran
 2019-05-28 20:50:40 +02:00
Martin Kroeker 79366ff7a9 Add softfp support in min/max kernels 
fix for #1912
 2019-05-28 20:34:22 +02:00
Martin Kroeker 21d05a4835 Merge pull request #2140 from martin-frbg/pgi19 
Do not try ancient PGI hacks with recent versions of that compiler
 2019-05-26 12:39:20 +02:00
Martin Kroeker 940f38f6dd Build and run utests in any case, they do their own checks for fortran availability 2019-05-24 13:02:23 +02:00
Martin Kroeker 1778fd4219 Do not try ancient PGI hacks with recent versions of that compiler 
should fix #2139
 2019-05-22 13:48:27 +02:00
Martin Kroeker 969dd6175e Merge pull request #2136 from martin-frbg/issue2126 
Add option to allow combining USE_THREAD=0 with thread locking support
 2019-05-16 12:08:16 +02:00
Martin Kroeker d8d5682481 Merge pull request #2134 from tylerjereddy/skylake_regress_guard_may14 
TST: add SkylakeX AVX512 CI test
 2019-05-15 23:40:06 +02:00
Martin Kroeker f66c11fc22 Remove unrelated change 2019-05-15 23:38:12 +02:00
Martin Kroeker 5ecffc28f2 Add option USE_LOCKING but keep default settings intact 2019-05-15 23:36:17 +02:00
Martin Kroeker 86dda5c2fa Add option USE_LOCKING for SMP-like locking in USE_THREAD=0 builds 2019-05-15 23:21:20 +02:00
Martin Kroeker 1e52572be3 Add option USE_LOCKING for single-threaded build with locking support 2019-05-15 23:19:30 +02:00
Martin Kroeker d2cb610272 Add option USE_LOCKING for single-threaded build with locking support 
for calling from concurrent threads
 2019-05-15 23:18:43 +02:00
Martin Kroeker 9208ab8603 Merge pull request #2130 from isuruf/drone 
Drone CI for arm64 native builds
 2019-05-14 09:37:00 +02:00
Martin Kroeker 63554d5dec Merge pull request #2129 from martin-frbg/armv8azure 
Move ARMv8/gcc CI job from Travis to Azure
 2019-05-12 09:55:57 +02:00
Martin Kroeker 43068288e9 Update .travis.yml 2019-05-11 22:37:06 +02:00
Martin Kroeker 999a04f101 Move ARMv8 gcc build from Travis to Azure 2019-05-11 16:08:23 +02:00
Martin Kroeker 3cb1c8d210 Move ARMv8 gcc build from Travis to Azure 2019-05-11 16:07:30 +02:00
Martin Kroeker ff1bfe7b16 Merge pull request #2127 from martin-frbg/issue2114_2 
Add NO_AFFINITY to available CMAKE options on Linux, and set it to ON
 2019-05-09 15:25:09 +02:00
Martin Kroeker 9ea30f3788 Replace ISMIN and ISAMIN kernels on all x86_64 platforms (#2125) 
* Mark iamax_sse.S as unsuitable for MIN due to issue #2116
* Use iamax.S rather than iamax_sse.S for ISMIN/ISAMIN on all x86_64 as workaround for #2116
 2019-05-09 14:42:36 +02:00
Martin Kroeker a3d4c65d62 Add NO_AFFINITY to available options on Linux, and set it to ON 
to match the gmake default. Fixes second part of #2114
 2019-05-09 11:52:02 +02:00
Martin Kroeker e1fc02095c Merge pull request #2124 from tylerjereddy/manylinux1_azure 
TST: Azure manylinux1 & clean-up
 2019-05-09 08:57:37 +02:00