Wei Huang, G. Santhanaraman, Hyun-Wook Jin, Qi Gao, D. Panda
{"title":"Design of High Performance MVAPICH2: MPI2 over InfiniBand","authors":"Wei Huang, G. Santhanaraman, Hyun-Wook Jin, Qi Gao, D. Panda","doi":"10.1109/CCGRID.2006.32","DOIUrl":null,"url":null,"abstract":"MPICH2 provides a layered architecture for implementing MPI-2. In this paper, we provide a new design for implementing MPI-2 over InfiniBand by extending the MPICH2 ADI3 layer. Our new design aims to achieve high performance by providing a multi-communication method framework that can utilize appropriate communication channels/devices to attain optimal performance without compromising on scalability and portability. We also present the performance comparison of the new design with our previous design based on the MPICH2 RDMA channel. We show significant performance improvements in micro-benchmarks and NAS Parallel Benchmarks.","PeriodicalId":419226,"journal":{"name":"Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"79","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCGRID.2006.32","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 79
Abstract
MPICH2 provides a layered architecture for implementing MPI-2. In this paper, we provide a new design for implementing MPI-2 over InfiniBand by extending the MPICH2 ADI3 layer. Our new design aims to achieve high performance by providing a multi-communication method framework that can utilize appropriate communication channels/devices to attain optimal performance without compromising on scalability and portability. We also present the performance comparison of the new design with our previous design based on the MPICH2 RDMA channel. We show significant performance improvements in micro-benchmarks and NAS Parallel Benchmarks.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
