Optimize SGEMM step by step

This project is a step-by-step guide to optimize the SGEMM step of the SGEMM algorithm.

Note: CUBLAS 中的矩阵是列主序的，因此为了便于对比，下面的 kernel 对应的宏也是基于列主序的，这样方便与 CUBLAS 计算得到的矩阵进行对比。

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
.vscode		.vscode
include		include
LICENSE		LICENSE
Makefile		Makefile
README.md		README.md
test_main.cu		test_main.cu

Provide feedback