5092 Commits (bfdf4b56dac690cdb03ea06b362cc178f4228d1a)
 

Author SHA1 Message Date
  Qiyu8 bfdf4b56da Add double precision universal intrinsics for X86/ARM 5 years ago
  Martin Kroeker 756802df61
Merge pull request #2890 from martin-frbg/s-d-sum 5 years ago
  Martin Kroeker 01492decf4
Merge pull request #2895 from martin-frbg/sb-tests 5 years ago
  Martin Kroeker bd0752444a
Merge pull request #2894 from RajalakshmiSR/bf16_packing 5 years ago
  Martin Kroeker c1f4f5d4e7
Replace Makefile with simplified version again 5 years ago
  Martin Kroeker 75e3a92df6
Add express -mavx and -msse options (and fix a stray = for cooperlake) 5 years ago
  Martin Kroeker 2a329baa81
Add the BFLOAT16 functions to cmake builds 5 years ago
  Rajalakshmi Srinivasaraghavan 0826d68f93 POWER10: Change the packing format for bfloat16 5 years ago
  Martin Kroeker 4bb73c0171
Rename "HALF" type to "BFLOAT16" 5 years ago
  Martin Kroeker bc5c7f9578
Cleanup 5 years ago
  Martin Kroeker 437b7fe261
sh prefix renamed to sb 5 years ago
  Martin Kroeker a0ada4bcb8
Merge pull request #98 from xianyi/develop 5 years ago
  Martin Kroeker 602a0c7a69
Merge pull request #2892 from RajalakshmiSR/bf16_make 5 years ago
  Rajalakshmi Srinivasaraghavan b5d30b390d Fix build issues with bfloat16 5 years ago
  Martin Kroeker 137ae618db
Fix typo 5 years ago
  Martin Kroeker 9e3cff5cf2
Expressly enable -mavx2 on Zen, SkylakeX and Cooperlake as well 5 years ago
  Martin Kroeker d85b968424
Merge pull request #2891 from martin-frbg/fix-2886 5 years ago
  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