| #!/usr/bin/python3 | |
| import os | |
| import re | |
| import subprocess | |
| import mmap | |
| def patch(filename : str, bytes): | |
| subprocess.run(["cp",filename, filename + '_patched']) | |
| with open(filename + "_patched", "r+b") as f: |
| [CONST_PARAM] | |
| rtsp = 1 ; RTSPЭ�飬0���ر� 1������ |
This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).
Matrix multiplication is a mathematical operation that defines the product of
| #include <immintrin.h> | |
| #include <intrin.h> | |
| #include <stdio.h> | |
| #include <stdlib.h> | |
| #include <string.h> | |
| union Mat44 { | |
| float m[4][4]; | |
| __m128 row[4]; | |
| }; |
