-
GEMM_AVX512F Public
SGEMM and DGEMM subroutines using AVX512F instructions.
-
bitonic_fp32_avx_top16 Public
Topk with K = 16 or 32, based on bitonic sort algorithm, using Intel AVX instructions.
C++ MIT License UpdatedJan 12, 2022 -
OpenBLAS Public
Forked from OpenMathLib/OpenBLASOpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
Fortran BSD 3-Clause "New" or "Revised" License UpdatedDec 12, 2021 -
Simple_CUDA_GEMM Public
Sgemm kernel function on Nvidia Pascal GPU, able to achieve 60% theoretical performance.
-
-
GEMM_AVX2 Public
Fast avx2/fma3 dgemm and sgemm subroutines for medium to large matrices(>2000*2000) on haswell/skylake/zen processors, with performances comparable to MKL.
-
COMPLEX_GEMM_AVX2_FMA3 Public
cgemm and zgemm subroutines for large matrices, using avx2 and fma3 instructions, with performance comparable to MKL2018
C GNU General Public License v3.0 UpdatedFeb 27, 2020 -
GEMM3M_AVX2_FMA3 Public
cgemm3m and zgemm3m subroutines for large matrices, using AVX2 and FMA3 instructions.
C GNU General Public License v3.0 UpdatedSep 8, 2019 -
GEMM_AVX2_FMA3 Public archive
sgemm and dgemm subroutine for large matrices, slightly outperform Intel MKL
-
cpu_gemm_opt Public
Forked from carlushuang/cpu_gemm_opthow to design cpu gemm on x86 with avx256, that can beat openblas.
C++ MIT License UpdatedApr 15, 2019