OSchip
/
OpenBLAS
Not watched
1
0
Fork 0
Code
Releases 66 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
8075 Commits
51 Branches
78 MB
387 Download
Tree: c1f7a81663
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'c1f7a81663'
${ noResults }
Commit Graph

778 Commits (c1f7a81663ae9e172d82b91c7ffbd482d71ceeac)

Author SHA1 Message Date
  Chen, Guobing 5d86becdae Add all SBGEMM kernels for IA AVX512-BF16 based platforms 4 years ago
  Wangyang Guo fa777f5517 Small Matrix: skylakex: add DGEMM_SMALL_M_PERMIT and tune for TN kernel 5 years ago
  Wangyang Guo 8592c21af4 Small Matrix: skylakex: dgemm nn: fix typo in idx load 5 years ago
  Wangyang Guo 3e79f6d89a Small Matrix: skylakex: add dgemm tn kernel 5 years ago
  Wangyang Guo 323d7da4f7 Small Matrix: skylakex: add dgemm tt kernel 5 years ago
  Wangyang Guo f57fc932ac Small Matrix: skylakex: add dgemm nt kernel 5 years ago
  Wangyang Guo 91ec21202b Small Matrix: skylakex: add dgemm nn kernel 5 years ago
  Wangyang Guo 72e070539c Small Matrix: skylakex: add sgemm tt kernel 5 years ago
  Wangyang Guo 02c6e764f2 Small Matrix: skylakex: add SGEMM_SMALL_M_PERMIT and tune for TN kernel 5 years ago
  Wangyang Guo 642c393879 Small Matrix: skylakex: add sgemm tn kernel 5 years ago
  Wangyang Guo ae3f5c737c Small Matrix: skylakex: sgemm nt: optimize for M < 12 5 years ago
  Wangyang Guo 0d72d75bf9 Small Matrix: skylakex: add sgemm nt kernel 5 years ago
  Wangyang Guo ca7682e3a3 Small Matrix: skylakex: sgemm nn: fix n6 conflicts with n4 5 years ago
  Wangyang Guo 9967e61abb Small Matrix: skylakex: sgemm nn: fix error when beta not zero 5 years ago
  Wangyang Guo a87736346f Small Matrix: skylakex: sgemm nn: add n6 to improve performance 5 years ago
  Wangyang Guo 4c9d9940fd Small Matrix: skylakex: sgemm nn: reduce store 4 N at a time 5 years ago
  Wangyang Guo 13b32f69b7 Small Matrix: skylakex: sgemm nn: reduce store 4 M at a time 5 years ago
  Wangyang Guo 3d8c6d9607 Small Matrix: skylakex: sgemm nn: clean up unused code 5 years ago
  Wangyang Guo 49b61a3f30 Small Matrix: skylakex: sgemm_nn: optimize for M <= 8 5 years ago
  Wangyang Guo f88470323b Optimize M < 16 using AVX512 mask 5 years ago
  Wangyang Guo 9186456a12 small matrix: SkylakeX: add SGEMM NN kernel 5 years ago
  Martin Kroeker 5b4b385ecf
Temporarily disable the SkylakeX sgemv_t microkernel due to LAPACK testsuite failures 4 years ago
  Ma, Yu 706a08d4a0 Optimized sgemv_t for small N based on AVX512 5 years ago
  Martin Kroeker 5f677e782e
Merge pull request #3196 from guowangy/skylakex-gemm-batch-k 5 years ago
  Martin Kroeker 02087a62e7
Merge pull request #3205 from intelmy/sgemv_n_opt 5 years ago
  Martin Kroeker 8b90e5f202
Drop redundant inclusion of complex.h 5 years ago
  Martin Kroeker c0ca63ea46
Fix missing conditionals for non-SKX kernels 5 years ago
  pnp 3d4ccd2a13 fix for build error 5 years ago
  pnp c59652f0ce optimize on sgemv_n for small n 5 years ago
  Wangyang Guo aa7b3dc3db GEMM: skylake: improve the performance when m is small 5 years ago
  Martin Kroeker 3d511f0e66
replace spurious avx512 requirement with fma check 5 years ago
  Martin Kroeker 2dfb24730d
Use "old" compute(24) function with clang due to register limitations 5 years ago
  Martin Kroeker 7b8f580941
Merge pull request #3156 from martin-frbg/omatcopy_d 5 years ago
  Martin Kroeker 0f5e86a0d9
Remove premature entry for DOMATCOPY_RT 5 years ago
  Martin Kroeker 7b294a99fd
Move common.h back to the top of the file so that SKYLAKEX (from config.h) is defined in time 5 years ago
  Martin Kroeker 0934568d9c
Move includes under the ifdef for compilers w/o intrinsics support 5 years ago
  Martin Kroeker a9f6f7ad39
Remove spurious AVX512 requirement and add AVX2/FMA3 guard 5 years ago
  Martin Kroeker 292d1af1a0
Update omatcopy_rt.c 5 years ago
  Martin Kroeker 325b398e3c
Update omatcopy_rt.c 5 years ago
  Martin Kroeker 6f5667b4d4
Enable optimized S/D OMATCOPY_RT 5 years ago
  Martin Kroeker cceeee7806
Add optimized omatcopy_rt 5 years ago
  Martin Kroeker 47691c031f
Use Haswell optimizations for Zen as well 5 years ago
  Martin Kroeker ce7ddd8921
Use Haswell optimizations for Zen as well 5 years ago
  Martin Kroeker 950c047b49
Use Haswell optimizations for Zen as well 5 years ago
  Martin Kroeker 46509953a9
Use Haswell optimizations for Zen as well 5 years ago
  Martin Kroeker db348dcff2
Enable optimized srot/drot kernels from Haswell 5 years ago
  Martin Kroeker 69a5558203
Merge pull request #3059 from Guobing-Chen/BF16_gemm 5 years ago
  Alex Henrie 202fc9e8ed Fix uninitialized argument value in dasum_k 5 years ago
  Chen, Guobing b0beb0b1ca Initial code for Cooperlake BF16 GEMM kernel 5 years ago
  Martin Kroeker 114eb159a4
Disable FMA intrinsics in the srot kernel when the compiler is PGI/NVIDIA 5 years ago