Optimizing Communication for Massively Parallel Processing大规模并行处理的优化通信.pptVIP

下载本文档

4
0
约4.51千字
约 30页
2017-03-08 发布于上海
举报
版权申诉

Optimizing Communication for Massively Parallel Processing大规模并行处理的优化通信.ppt

1、本文档共30页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Optimizing Communication for Massively Parallel Processing大规模并行处理的优化通信

Opportunities and Challenges of Modern Communication Architectures: Case Study with QsNet CAC WorkshopSanta Fe, NM, 2004 Sameer Kumar* and Laxmikant V. KaleParallel Programming LaboratoryUniversity of Illinois at Urbana Champaign Outline Processor virtualization QsNet Opportunities Performance Evaluation of QsNet Challenges of QsNet Summary Processor Virtualization Basic idea of processor virtualization User specifies interaction between objects (VPs) RTS maps VPs onto physical processors Typically, # virtual processors # processors Embodied in Charm++ and AMPI QsNet Popular interconnect from Quadrics Several parallel systems in top500 use QsNet Pittsburgh’s Lemieux (6TF) ASCI-Q (20TF) Elite network Elan adaptor Elite Network 320 MB/s each way after protocol Reliable fat-tree network Multiple routes provides fault tolerance Adaptive worm hole routing 35 ns per hop Elan Network Adaptor Features Low latency (4.5 μs for MPI) High bandwidth (320MB/s/node) Components Sparc processor DMA Engine 64 MB RAM On chip cache Low CPU Overhead Traditional Message Passing Adaptive Overlap Benefit of Adaptive Overlap Charm++ Message Driven Execution NAMD: A Production MD System Scaling NAMD Several QsNet challenges had to be overcome to scale NAMD QsNet Challange: Latency Latency Bottlenecks Latency Slow NIC processor with a 100Mhz clock Cache size only 8KB Traversing a large loop flushes it Managing Latency: Message Combining NAMD PME Performance QsNet Challenge: Bandwidth Improving Bandwidth QsNet Challenge: Stretched Handlers Stretched Sends Green superscripts Similar stretches observed in the middle of entry methods Stretching Solution Stretched Sends Elan Isend blocked when the rendezvous for the previous Isend to any destination had not been acknowledged Solved the problem by closely working with Quadrics and obtaining a patch Isend only blocks on the rendezvous of the previous message to the same destination Stretching Solution Contd. Stretches in the middle of en