【张先轶】BLISlab学习优化矩阵乘。第一课

1789 3 2022-06-24 14:14:32 未经作者授权,禁止转载
5495
BLISlab是一个开源教学项目, 教你一步一步优化矩阵乘。 本视频主讲人: 张先轶(中科院博士,OpenBLAS开源项目发起人,PerfXLab创始人&CEO) BLISlab: A Sandbox for Optimizing GEMM  Matrix-matrix multiplication is a fundamental operation of great importance to scientific computing and, increasingly, machine learning. It is a simple enough concept to be introduced in a typical high school algebra course yet in practice important enough that its implementation on computers continues to be an active research topic. This note describes a set of exercises that use this operation to illustrate how high performance can be attained on modern CPUs with hierarchical memories (multiple caches). It does so by building on the insights that underly the BLAS-like Library Instantiation Software (BLIS) framework by exposing a simplified “sandbox” that mimics the implementation in BLIS. As such, it also becomes a vehicle for the “crowd sourcing” of the optimization of BLIS. We call this set of exercises “ BLISlab”.  拓展资料: blislab的github站点 https://github.com/ybNo1/blislab OpenBLAS gemm从零入门 https://zhuanlan.zhihu.com/p/65436463
这个频道有趣、有益、有知识!强烈推荐您关注。分享计算机公益课、大咖演讲、科技视频和一些有趣的内容。

传奇没意思了?那是因为你没玩过这款

1.2万播放icon简介
张先轶博士毕业于北京理工,中科院博士, UT Austin和MIT博后研究。 CCF高性能计算专委会委员。 OpenBLAS开源项目发起人。 PerfXLab(澎峰科技)创始人兼CEO。 曾荣获中国计算机学会科技进步二等奖,中国科学院杰出科技成就奖。
【张先轶】BLISlab学习优化矩阵乘。第一课
43:48
【张先轶】BLISlab学习优化矩阵乘。第二课
35:35
【张先轶】BLISlab学习优化矩阵乘。第三课
44:07
BLISlab学习矩阵乘。第四课
21:17
【张先轶】SIMD向量化编程入门(百校万人计划·高性能计算专才培养公开课系列)
32:46
【张先轶】性能优化之计算机体系结构概略
32:48
【张先轶】RISC-V Vector向量编程(百校万人计划·高性能计算专才培养公开课系列)
52:54
顶部
赛事库 课堂 2021拜年纪