Beast code in Giters

wjc404's repositories

GEMM_AVX512F

SGEMM and DGEMM subroutines using AVX512F instructions.

Language:CGPL-3.014 1 1

GEMM_AVX2

Fast avx2/fma3 dgemm and sgemm subroutines for medium to large matrices(>2000*2000) on haswell/skylake/zen processors, with performances comparable to MKL.

Language:CGPL-3.07 20

Simple_CUDA_GEMM

Sgemm kernel function on Nvidia Pascal GPU, able to achieve 60% theoretical performance.

Language:CudaGPL-3.05 10

GEMM_AVX2_FMA3

sgemm and dgemm subroutine for large matrices, slightly outperform Intel MKL

Language:CGPL-3.0100

bitonic_fp32_avx_top16

Topk with K = 16 or 32, based on bitonic sort algorithm, using Intel AVX instructions.

Language:C++MIT010

COMPLEX_GEMM_AVX2_FMA3

cgemm and zgemm subroutines for large matrices, using avx2 and fma3 instructions, with performance comparable to MKL2018

Language:CGPL-3.0000

cpu_gemm_opt

how to design cpu gemm on x86 with avx256, that can beat openblas.

Language:C++MIT000

GEMM3M_AVX2_FMA3

cgemm3m and zgemm3m subroutines for large matrices, using AVX2 and FMA3 instructions.

Language:CGPL-3.0000

OpenBLAS

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

Language:FortranBSD-3-Clause000

OpenBLAS_L3_kernel_tester

GPL-3.0000