基于局部性分析数据预取在GCC上的实现
被引量:1
Implementation of Data Prefetching Based on Locality Analysis in GCC
摘要
微处理器与DRAM之间速度差异越来越大,系统优化需要更多积极有效的方法来减少或隐藏访存延迟.数据预取是隐藏访存延迟的一种有效方法,本文在GCC编译器上实现了一种基于精确局部性分析的数据预取优化算法.对spec2000和NPB2.3的测试结果显示,实施了该优化的GCC平均性能比原来提高了9%.
出处
《计算机工程与科学》
CSCD
2006年第z2期21-23,44,共4页
Computer Engineering & Science
基金
国家863计划资助项目(2002AA110030)
参考文献4
-
1[1]Stenven P VanderWeil,David J Lilja.Data Prefetch Mechanisms[Z].
-
2[2]Daniel Ortega,Eduard Ayguade,et al.Cost-Effective Compiler Directed Memory Prefetching and Bypassing.
-
3[3]T Mowry,M Lam,A Gupta.Design and Evaluation of a Compiler Algorithm for Prefetching[A].5th Int'l Conf on Architectural Support for Programming Languages and Operating Systems[C].1992.
-
4[4]Chi-Keung Luk,Todd C Mowry.Compiler-Based Prefetching for Recursive Data Structures[Z].
同被引文献20
-
1黄娟娟,李春江,徐颖.GCC中自动向量化代价模型剖析[C]//第17届计算机工程与工艺年会暨第三届微处理器技术论坛论文集.长沙:国防科技大学出版社,2013:259-268.
-
2Hennessy J L,Patterson D A.Computer architecture:a quantitative approach[M].[S.l.]:Elsevier,2012.
-
3Hwang S J,Park M S.Efficient software data prefetching for a loop with large arrays[C]//EURO-PAR’95 Parallel Processing.Berlin Heidelberg:Springer,1995:301-312.
-
4Byna S,Chen Y,Sun X H.A taxonomy of data prefetching mechanisms[C]//International Symposium on Parallel Architectures,Algorithms,and Networks,I-SPAN 2008,2008:19-24.
-
5Free Software Foundation,Inc.GCC,the GNU compiler collection[EB/OL].(2014-12-23).https://gcc.gnu.org/.
-
6Free Software Foundation,Inc.GCC 4.9 release series[EB/OL].(2014-10-30).http://gcc.gnu.org/gcc-4.9/.
-
7Smith A J.Sequential program prefetching in memory hierarchies[J].Computer,1978,11(12):7-21.
-
8Callahan D,Kennedy K,Porterfield A.Software prefetching[J].ACM SIGOPS Operating Systems Review,1991,25:40-52.
-
9Intel.Intel itanium architecture software developer’s manual,vol.3:instruction set reference[Z].Rev 2.3,May 2010.
-
10MIPS Technologies.MIPS32tmarchitecture for programmers;volume II:the MIPS32tminstruction set[Z].Revision 0.95,March 12,2001.
二级引证文献5
-
1贺春林,赖庆宽,朱广林,何先波.基于X86平台的编译器性能优化[J].西南民族大学学报(自然科学版),2020,46(1):33-40.
-
2余龙龙,韩林.基于申威GCC编译器的间接预取算法[J].计算机系统应用,2022,31(8):203-211.
-
3王翠霞,韩林,刘浩浩.基于指令Cache和寄存器压力的循环展开优化[J].计算机工程与科学,2022,44(12):2111-2119. 被引量:2
-
4高秀武,姜军,白书敬,黄亮明.一种加速访存地址计算的编译优化[J].计算机工程,2023,49(1):173-180.
-
5刘大兴,顾乃杰,黄章进,苏俊杰,齐东升.一种用于软件预取的访存轨迹采样算法[J].计算机工程,2024,50(10):362-369.