分组阵列布局减少通信，提高并行程序的局部性

Proceedings of 1994 International Conference on Parallel and Distributed Systems Pub Date : 1994-12-19 DOI:10.1109/ICPADS.1994.590375

Tien-Pao Shih, E. Davidson

{"title":"分组阵列布局减少通信，提高并行程序的局部性","authors":"Tien-Pao Shih, E. Davidson","doi":"10.1109/ICPADS.1994.590375","DOIUrl":null,"url":null,"abstract":"A data layout method, array grouping, is proposed to improve communication efficiency and cache utilization of parallel programs containing indirect array references or nonunit stride indexing. Conditions on where to apply this technique are specified in a series of theorems. The technique is then applied to a real finite element application. The experimental results show that communication is reduced by 15%, and data subcache misses by 40% on 56 processors of the KSR1 parallel computer.","PeriodicalId":154429,"journal":{"name":"Proceedings of 1994 International Conference on Parallel and Distributed Systems","volume":"600 ","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Grouping array layouts to reduce communication and improve locality of parallel programs\",\"authors\":\"Tien-Pao Shih, E. Davidson\",\"doi\":\"10.1109/ICPADS.1994.590375\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A data layout method, array grouping, is proposed to improve communication efficiency and cache utilization of parallel programs containing indirect array references or nonunit stride indexing. Conditions on where to apply this technique are specified in a series of theorems. The technique is then applied to a real finite element application. The experimental results show that communication is reduced by 15%, and data subcache misses by 40% on 56 processors of the KSR1 parallel computer.\",\"PeriodicalId\":154429,\"journal\":{\"name\":\"Proceedings of 1994 International Conference on Parallel and Distributed Systems\",\"volume\":\"600 \",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1994-12-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of 1994 International Conference on Parallel and Distributed Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICPADS.1994.590375\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of 1994 International Conference on Parallel and Distributed Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPADS.1994.590375","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

为了提高包含间接数组引用或非单元步进索引的并行程序的通信效率和缓存利用率，提出了一种数据布局方法——数组分组。在一系列定理中规定了应用这种技术的条件。然后将该技术应用于实际的有限元应用。实验结果表明，在KSR1并行计算机的56个处理器上，通信减少了15%，数据子缓存丢失减少了40%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Grouping array layouts to reduce communication and improve locality of parallel programs

A data layout method, array grouping, is proposed to improve communication efficiency and cache utilization of parallel programs containing indirect array references or nonunit stride indexing. Conditions on where to apply this technique are specified in a series of theorems. The technique is then applied to a real finite element application. The experimental results show that communication is reduced by 15%, and data subcache misses by 40% on 56 processors of the KSR1 parallel computer.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of 1994 International Conference on Parallel and Distributed Systems

自引率

0.00%

发文量