5176 Commits (680f744abf7da75018f98127616dd0c995e3b34c)
 

Author SHA1 Message Date
  Martin Kroeker 5f60a32cac
Add -mssse3 if supported by the hardware 5 years ago
  Martin Kroeker fecedc9c69
Add -mssse3 5 years ago
  Martin Kroeker 0eacbca85f
Add Haswell and Zen to temporary sse3 whitelist 5 years ago
  Martin Kroeker 6999086a2b
whitelist SANDYBRIDGE for SSE3 5 years ago
  Martin Kroeker 9dca578c79
Cleanup 5 years ago
  Martin Kroeker 1e7eb7b7a9
Fix typos in currently unused sections 5 years ago
  Martin Kroeker 84949754a0
Fix bfloat16 conditional 5 years ago
  Martin Kroeker 2ae8785603
Add a POWER9 build with BFLOAT16 enabled 5 years ago
  Martin Kroeker e05af6575e
Fix some overlooked "SHBLAS" entries 5 years ago
  Martin Kroeker c1643006ae
Merge pull request #97 from xianyi/develop 5 years ago
  Martin Kroeker 8d2df7d066
Revert special handling of Windows xNRM2 and enable C+intrinsics kernel for SSUM/DSUM 5 years ago
  Martin Kroeker 08929430cd
Merge pull request #2886 from martin-frbg/issue_2767 5 years ago
  Martin Kroeker 0c84ffe05f
Merge pull request #2881 from mattip/fninit 5 years ago
  Martin Kroeker cb4274e3ad
Merge pull request #2888 from Qiyu8/usimd-sum 5 years ago
  Matti Picus 403eb513a0 use emms instead, add WIN guards 5 years ago
  Martin Kroeker cb839575ed
Convert the prototypes of the unimplemented BFLOAT16 functions to the new naming scheme 5 years ago
  Qiyu8 0ed1f07660 Optimize the performance of sum by using universal intrinsics 5 years ago
  Martin Kroeker bb74dd29db
Restore -msse3 5 years ago
  Martin Kroeker 629c497b6c
common_sh.h renamed to common_sb.h 5 years ago
  Martin Kroeker 2c552f1074
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 7ae9e8960e
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker e3a29f6b58
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 006c7f6671
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 85154c2e18
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker ae1ab5bfdf
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 052f31bc3c
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 3aecafad80
Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 756062afa5
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 2061f7fdff
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker dc8a1afa63
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 32733ded04
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 3bc8e8c334
Rename "HALF" and "sh" to "BFLOAT16"and "sb" 5 years ago
  Martin Kroeker 573508f0ee
Rename common_sh.h to common_sb.h 5 years ago
  Martin Kroeker ca31c32693
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 5800758b43
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 924fd806d0
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 4db09c6cec
Rename compare_sgemm_shgemm.c to compare_sgemm_sbgemm.c 5 years ago
  Martin Kroeker fd94236042
Rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker 68ce719fac
Rename shdot_microk_cooperlake.c to sbdot_microk_cooperlake.c 5 years ago
  Martin Kroeker d7dd9b396c
Rename shdot.c to sbdot.c 5 years ago
  Martin Kroeker 9ae80490e0
rename "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
  Martin Kroeker d314d1f49f
Rename shgemm_kernel_power10.c to sbgemm_kernel_power10.c 5 years ago
  Martin Kroeker f0883740e4
Merge pull request #96 from xianyi/develop 5 years ago
  Martin Kroeker 1c0b03efb4
Merge branch 'develop' into develop 5 years ago
  Martin Kroeker c589c3e2a1
Merge pull request #2882 from martin-frbg/issue2709 5 years ago
  Martin Kroeker ec638a82bf
Merge pull request #2852 from martin-frbg/issue2588-cmake 5 years ago
  Martin Kroeker caa0d757ca
repair TABs 5 years ago
  Martin Kroeker 6154f72d6d
Copy BUILD_ settings to the LAPACK make.inc 5 years ago
  Martin Kroeker ae8b0d257a
Set BUILD_ options to 1 instead of just defining them 5 years ago
  Martin Kroeker 1da32cc1fc
Add cblas_xerbla interface 5 years ago