Optimization opportunities created by global data reordering

International Symposium on Code Generation and Optimization, 2003. CGO 2003. Pub Date : 2003-03-23 DOI:10.1109/CGO.2003.1191548

Gadi Haber, M. Klausner, Vadim Eisenberg, Bilha Mendelson, M. Gurevich

{"title":"Optimization opportunities created by global data reordering","authors":"Gadi Haber, M. Klausner, Vadim Eisenberg, Bilha Mendelson, M. Gurevich","doi":"10.1109/CGO.2003.1191548","DOIUrl":null,"url":null,"abstract":"Memory access has proven to be one of the bottlenecks in modern architectures. Improving memory locality and eliminating the amount of memory access can help release this bottleneck. We present a method for link-time profile-based optimization by reordering the global data of the program and modifying its code accordingly. The proposed optimization reorders the entire global data of the program, according to a representative execution rate of each instruction (or basic block) in the code. The data reordering is done in a way that enables the replacement of frequently-executed Load instructions, which reference the global data, with fast Add Immediate instructions. In addition, it tries to improve the global data locality and to reduce the total size of the global data area. The optimization was implemented into FDPR (Feedback Directed Program Restructuring), a post-link optimizer, which is part of the IBM AIX operating system for the IBM pSeries servers. Our results on SPECint2000 show a significant improvement of up to 11% (average 3%) in execution time, along with up to 97.9% (average 83%) reduction in memory references to the global variables via the global data access mechanism of the program.","PeriodicalId":277590,"journal":{"name":"International Symposium on Code Generation and Optimization, 2003. CGO 2003.","volume":"121 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Symposium on Code Generation and Optimization, 2003. CGO 2003.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CGO.2003.1191548","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 15

Abstract

Memory access has proven to be one of the bottlenecks in modern architectures. Improving memory locality and eliminating the amount of memory access can help release this bottleneck. We present a method for link-time profile-based optimization by reordering the global data of the program and modifying its code accordingly. The proposed optimization reorders the entire global data of the program, according to a representative execution rate of each instruction (or basic block) in the code. The data reordering is done in a way that enables the replacement of frequently-executed Load instructions, which reference the global data, with fast Add Immediate instructions. In addition, it tries to improve the global data locality and to reduce the total size of the global data area. The optimization was implemented into FDPR (Feedback Directed Program Restructuring), a post-link optimizer, which is part of the IBM AIX operating system for the IBM pSeries servers. Our results on SPECint2000 show a significant improvement of up to 11% (average 3%) in execution time, along with up to 97.9% (average 83%) reduction in memory references to the global variables via the global data access mechanism of the program.

查看原文本刊更多论文

全局数据重新排序带来的优化机会

内存访问已被证明是现代体系结构中的瓶颈之一。改进内存局部性和消除内存访问量可以帮助缓解这个瓶颈。我们提出了一种基于链接时间概要的优化方法，该方法通过对程序的全局数据重新排序并相应地修改其代码来实现。所提出的优化根据代码中每个指令(或基本块)的代表性执行速率，对程序的整个全局数据进行重新排序。数据重新排序的方式允许用快速的Add Immediate指令替换引用全局数据的频繁执行的Load指令。此外，它还试图提高全局数据的局部性，并减小全局数据区域的总大小。优化是在FDPR(反馈定向程序重组)中实现的，FDPR是一个链接后优化器，它是IBM pSeries服务器的IBM AIX操作系统的一部分。我们在SPECint2000上的结果显示，执行时间显著改善了11%(平均3%)，通过程序的全局数据访问机制对全局变量的内存引用减少了97.9%(平均83%)。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Symposium on Code Generation and Optimization, 2003. CGO 2003.

自引率

0.00%

发文量