1568 Commits (60e1fddca7634917a56bcc4cb43bbbee08eb136a)

Author SHA1 Message Date
  Martin Kroeker f1bf040b25
Merge pull request #2988 from xiegengxin/smp-asum 6 years ago
  Xianyi Zhang 7037849498 Merge branch 'develop' into risc-v 6 years ago
  Martin Kroeker 7e9cb39a25
Merge pull request #2981 from Qiyu8/fix-sum 6 years ago
  Gengxin Xie d6e7e05bb3 Improve the performance of dasum and sasum when SMP is defined 6 years ago
  Qiyu8 ae0b1dea19 modify system.cmake to enable fma flag 6 years ago
  Qiyu8 e0dac6b53b fix the CI failure of target specific option mismatch 6 years ago
  Qiyu8 e5c2ceb675 fix the CI failure of lack the head 6 years ago
  Qiyu8 a87e537b8c modify macro 6 years ago
  Qiyu8 5bc0a7583f only FMA3 and vector larger than 128 have positive effects. 6 years ago
  Qiyu8 8c0b206d4c Optimize the performance of rot by using universal intrinsics 6 years ago
  Qiyu8 c4c591ac5a fix sum optimize issues 6 years ago
  Xianyi Zhang fc35b72ae1 Refs #2899 6 years ago
  Xianyi Zhang 913cc9a4ca Merge branch 'develop' into risc-v 6 years ago
  Martin Kroeker ff16329cb7
Merge pull request #2972 from xiegengxin/rot-intrinsic 6 years ago
  Martin Kroeker 110c7a6de0
Merge pull request #2979 from RajalakshmiSR/dot_power10 6 years ago
  Rajalakshmi Srinivasaraghavan 6e364981a8 Optimize sdot/ddot for POWER10 6 years ago
  Martin Kroeker b976a0bf40
Remove previous workaround for compiler flags related to cpu capabilities in x86_64 DYNAMIC_ARCH builds 6 years ago
  Martin Kroeker ff74319ea5
Merge pull request #2977 from martin-frbg/issue2976 6 years ago
  Martin Kroeker 28d2dfe2b3
Fix macro name used in ifdef 6 years ago
  Gengxin Xie 725ffbf041 fix typo 6 years ago
  Gengxin Xie d9ba49165a Improve the performance of rot by using AVX512 and AVX2 intrinsic 6 years ago
  Rajalakshmi Srinivasaraghavan dd7a9cc5bf POWER10: Change dgemm unroll factors 6 years ago
  Rajalakshmi Srinivasaraghavan b435491885 Optimize caxpy for POWER10 6 years ago
  Chen, Guobing a7b1f9b1bb Implementation of BF16 based gemv 6 years ago
  Martin Kroeker 67f39ad813
Merge pull request #2939 from thrasibule/Makefile_cleanup 6 years ago
  Rajalakshmi Srinivasaraghavan c24ba8b1dd Optimize saxpy for POWER10 6 years ago
  Martin Kroeker 6f9460f0f6
Merge pull request #2937 from martin-frbg/pwr-buffersz 6 years ago
  Guillaume Horel 1917a4e7b8 reuse variables defined in Makefile.system 6 years ago
  Martin Kroeker 34c3c407ef
label always_inline function as inline to silence a gcc warning 6 years ago
  Martin Kroeker 2e48d560ba
Fix compiler version check 6 years ago
  Rajalakshmi Srinivasaraghavan ad745c0bae Optimize scopy/ccopy for POWER10 6 years ago
  İsmail Dönmez 4a1d00f589
Fix build with -Werror=return-type 6 years ago
  Bart Oldeman b073d759d0 x86_64: clobber all xmm registers after vzeroupper 6 years ago
  Martin Kroeker dc6e44c3f8
Merge pull request #2916 from martin-frbg/issue2911 6 years ago
  Martin Kroeker a61c086408
Fix spurious trailing whitespace in comment 6 years ago
  Bart Oldeman 03e781b766 sgemm_direct_skylakex: fix 75eeb26 regression. 6 years ago
  Martin Kroeker f1a4071d8c
Clean up STACKSIZE redefinition 6 years ago
  Martin Kroeker 97cf10062f
Clean up STACKSIZE redefinition 6 years ago
  Martin Kroeker 17e288e18d
Clean up STACKSIZE redefinition 6 years ago
  Martin Kroeker c1422f3e46
Clean up STACKSIZE redefinition 6 years ago
  Martin Kroeker d85b24e103
Clean up STACKSIZE redefinition 6 years ago
  Zhang Xianyi d7ba7679b6 Merge branch 'develop' into risc-v 6 years ago
  Martin Kroeker df70667043
fix core list for sse/sse2 6 years ago
  Martin Kroeker f071d1207a
add sse2 6 years ago
  Martin Kroeker dc6cefd2f5
Expressly enable -msse for 32bit DYNAMIC_ARCH kernels 6 years ago
  Martin Kroeker c339c40c01
Silence a redefinition warning 6 years ago
  Martin Kroeker 10379fc83b
Use ifdef instead of if 6 years ago
  Martin Kroeker 4c25910da0
Merge pull request #2896 from martin-frbg/intrin-double 6 years ago
  damonyu ef8e7d0279 Add the support for RISC-V Vector. 6 years ago
  Martin Kroeker ae6ac83991
Revert "add double precision SSE" 6 years ago