I-WAY上的共享内存NUMA编程

Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing Pub Date : 1996-08-06 DOI:10.1109/HPDC.1996.546214

J. Nieplocha, R. Harrison

{"title":"I-WAY上的共享内存NUMA编程","authors":"J. Nieplocha, R. Harrison","doi":"10.1109/HPDC.1996.546214","DOIUrl":null,"url":null,"abstract":"The performance of the Global Array shared-memory non-uniform memory-access programming model is explored on the I-WAY, wide-area network distributed supercomputer environment. The Global Array model is extended by introducing a concept of mirrored arrays. Latencies and bandwidths for remote memory access are studied, and the performance of a large application from computational chemistry is evaluated using both fully distributed and also mirrored arrays. Excellent performance can be obtained with mirroring if even modest (0.5 MB/s) network bandwidth is available.","PeriodicalId":267002,"journal":{"name":"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1996-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"23","resultStr":"{\"title\":\"Shared memory NUMA programming on I-WAY\",\"authors\":\"J. Nieplocha, R. Harrison\",\"doi\":\"10.1109/HPDC.1996.546214\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The performance of the Global Array shared-memory non-uniform memory-access programming model is explored on the I-WAY, wide-area network distributed supercomputer environment. The Global Array model is extended by introducing a concept of mirrored arrays. Latencies and bandwidths for remote memory access are studied, and the performance of a large application from computational chemistry is evaluated using both fully distributed and also mirrored arrays. Excellent performance can be obtained with mirroring if even modest (0.5 MB/s) network bandwidth is available.\",\"PeriodicalId\":267002,\"journal\":{\"name\":\"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1996-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"23\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of 5th IEEE International Symposium on High Performance Distributed Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HPDC.1996.546214\",\"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 5th IEEE International Symposium on High Performance Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPDC.1996.546214","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 23

摘要

在I-WAY广域网分布式超级计算机环境下，研究了全局阵列共享存储器非均匀存储器访问编程模型的性能。通过引入镜像数组的概念扩展了全局数组模型。研究了远程存储器访问的延迟和带宽，并使用完全分布式和镜像阵列对计算化学中的大型应用程序的性能进行了评估。即使是适度的(0.5 MB/s)网络带宽可用，也可以通过镜像获得出色的性能。

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

Shared memory NUMA programming on I-WAY

The performance of the Global Array shared-memory non-uniform memory-access programming model is explored on the I-WAY, wide-area network distributed supercomputer environment. The Global Array model is extended by introducing a concept of mirrored arrays. Latencies and bandwidths for remote memory access are studied, and the performance of a large application from computational chemistry is evaluated using both fully distributed and also mirrored arrays. Excellent performance can be obtained with mirroring if even modest (0.5 MB/s) network bandwidth is available.

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 5th IEEE International Symposium on High Performance Distributed Computing

自引率

0.00%

发文量