以编译为导向的Matrix-DSP程序分析与优化  

Compilation-oriented code analysis and optimization for Matrix DSP

作　　者：荀长庆[1] 陈照云 文梅[1] 孙海燕[1] 马奕民 XUN Chang-qing;CHEN Zhao-yun;WEN Mei;SUN Hai-yan;MA Yi-min(School of Computer,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学计算机学院,湖南长沙410073

出　　处：《计算机工程与科学》2020年第10期1791-1800,共10页Computer Engineering & Science

基　　金：国家重点研发计划(2018YFB0204301)。

摘　　要：数字信号处理器(DSP)在图像处理、自动化控制、信号处理等多个领域具有广泛应用。自主研发的Matrix DSP采用了典型的单指令多数据SIMD+超长指令字VLIW的向量化架构,因此面向该架构如何实现高效的向量化编程与优化是一项重要挑战。基于Matrix DSP的体系结构特点,以编译器性能为导向,对内核级代码常用的分析优化手段进行梳理和总结,并结合一个通用矩阵乘的例子进行展示,其执行性能可最高提升1个数量级。最后,从编译器优化和程序员高效编程的角度提出了一些后续的思考与讨论。Digital Signal Processor(DSP)are widely used in numerous fields such as image proces-sing,automation control,and signal processing.Matrix DSPs,which are independently developed by ourselves,adopt a typical vectorization architecture of Single Instruction Multiple Data(SIMD)+Very Long Instruction Word(VLIW).Therefore,it is a prominent challenge to implement efficient vecto-rized programming and optimization for such architecture.According to the characteristics of Matrix DSP and the compilation performance,the analysis and optimization methods commonly used in the kernels are summarized.Furthermore,an example of general matrix multiplication(GEMM)is used to show that the execution performance can be improved by up to 1 order of magnitude.Based on the summary of optimization methods,some follow-up thoughts and discussions are proposed from the perspective of compiler optimization and programmers’efficient programming.

关 键 词：Matrix DSP 向量化编程 程序优化 编译器 

分 类 号：TP302.7[自动化与计算机技术—计算机系统结构]