Files
blis/.gitignore
Arnav Sharma 25e59fcbb9 DGEMV Optimizations for NO_TRANSPOSE Cases
- AVX512 specific DGEMV native kernels are added for Zen4/5
  architectures to handle the NO_TRANSPOSE cases and are independent of
  the AXPYF fused kernels.
- The following set of kernels biased towards the n-dimension perform
  beta scaling of y vector within the kernel itself and handle cases
  where n is less than 5:
    - bli_dgemv_n_zen_int_32x8n_avx512( ... )
    - bli_dgemv_n_zen_int_32x4n_avx512( ... )
    - bli_dgemv_n_zen_int_32x2n_avx512( ... )
    - bli_dgemv_n_zen_int_32x1n_avx512( ... )
- The bli_dgemv_n_zen_int_16mx8_avx512( ... ) is biased towards the
  m-dimension and for this kernel beta scaling is handled beforehand
  within the framework.
- Added unit-tests for the new kernels.
- AVX2 path for Zen/2/3 architectures still follows the old approach of
  using fused kernel, namely AXPYF, to perform the GEMV operation.

AMD-Internal: [CPUPL-5560]
Change-Id: I22bc2a865cd28b9cdcb383e17d1ff38bdd28de79
2024-12-12 10:26:50 -05:00

71 lines
888 B
Plaintext

# -- generic files to ignore --
# emacs backup files
*~
# vim backup files
*.swp
# NFS file
.nfs*
# -- compiler-related --
# object files
# NOTE: This will result in git also exluding the top-level obj directory
# since its only contents are .o files.
*.o
# static library archives
# NOTE: This will result in git also exluding the top-level lib directory
# since its only contents are .a files.
*.a
*.so
*.so.*
# test executables
*.x
*.pexe
*.nexe
*.js
# link map files
*.map
# -- build system files --
config.mk
bli_config.h
bli_addon.h
# -- monolithic headers --
include/*/*.h
# -- makefile fragments --
.fragment.mk
# -- misc. --
# BLIS testsuite output file
output.testsuite*
# BLAS test output files
out.*
# GTAGS database
GPATH
GRTAGS
GTAGS
# cmake builds
build_*/*
# Windows build
bin/*
*.dll
*.lib
*.pdb
*.exe
.vscode
# Gtestsuite build files
gtestsuite/build/*