a fast sgemm lib with fix 16 enable on arm 32

maxas Scott Grey's maxas assembler sgemm explaining the (for me) missing parts https://github.com/NervanaSystems/maxas

The repository targets the OpenCL gemm function performance optimization. It compares several libraries clBLAS, clBLAST, MIOpenGemm, Intel MKL(CPU) and cuBLAS(CUDA) on different matrix sizes/vendor's hardwares/OS. Out-of-the-box easy as MSVC, MinGW, Linux(CentOS) x86_64 binary provided. 在不同矩阵大小/硬件/操作系统下比较几个BLAS库的sgemm函数性能，提供binary，开盒即用。

CuPy first example computing GEMM with cuBlas, with handwritten cuda kernel and with NumPy-blas

An alternative SGEMM implementation on AMD Vega Series

A benchmark framework for POWER and x86_64

Step-by-step optimization of CUDA SGEMM

CUDA Kernels on V100

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

GEMM

Fast, Multi-threaded Matrix Multiplication in C

General Matrix Multiplication using NVIDIA Tensor Cores