{"title":"对Myrinet/GM2双端口网络的评估","authors":"R. Zamani, Y. Qian, A. Afsahi","doi":"10.1109/LCN.2004.20","DOIUrl":null,"url":null,"abstract":"It is important to systematically assess the features and performance of the new interconnects for high performance clusters. This work presents the performance of the two-port Myrinet networks at the GM2 and MPI layers using a complete set of microbenchmarks. We also present the communication characteristics and the performance of the NAS multi-zone benchmarks and SMG2000 application under the MPI and MPI-OpenMP programming paradigms. We found that the host overhead is very small in our cluster, and the Myrinet is sensitive to the buffer reuse patterns. Our applications achieved a better performance for MPI than the mixed-mode. All the applications studied use only nonblocking communications, thus are able to overlap their communications with the computations. Our experiments show that the two-port communication at the GM and MPI levels (except for the RDMA read, and overlap) outperforms the one-port communication for the bandwidth. However, this did not translate into a considerable improvement at least for our applications.","PeriodicalId":366183,"journal":{"name":"29th Annual IEEE International Conference on Local Computer Networks","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"An evaluation of the Myrinet/GM2 two-port networks\",\"authors\":\"R. Zamani, Y. Qian, A. Afsahi\",\"doi\":\"10.1109/LCN.2004.20\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"It is important to systematically assess the features and performance of the new interconnects for high performance clusters. This work presents the performance of the two-port Myrinet networks at the GM2 and MPI layers using a complete set of microbenchmarks. We also present the communication characteristics and the performance of the NAS multi-zone benchmarks and SMG2000 application under the MPI and MPI-OpenMP programming paradigms. We found that the host overhead is very small in our cluster, and the Myrinet is sensitive to the buffer reuse patterns. Our applications achieved a better performance for MPI than the mixed-mode. All the applications studied use only nonblocking communications, thus are able to overlap their communications with the computations. Our experiments show that the two-port communication at the GM and MPI levels (except for the RDMA read, and overlap) outperforms the one-port communication for the bandwidth. However, this did not translate into a considerable improvement at least for our applications.\",\"PeriodicalId\":366183,\"journal\":{\"name\":\"29th Annual IEEE International Conference on Local Computer Networks\",\"volume\":\"50 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-11-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"29th Annual IEEE International Conference on Local Computer Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/LCN.2004.20\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"29th Annual IEEE International Conference on Local Computer Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/LCN.2004.20","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An evaluation of the Myrinet/GM2 two-port networks
It is important to systematically assess the features and performance of the new interconnects for high performance clusters. This work presents the performance of the two-port Myrinet networks at the GM2 and MPI layers using a complete set of microbenchmarks. We also present the communication characteristics and the performance of the NAS multi-zone benchmarks and SMG2000 application under the MPI and MPI-OpenMP programming paradigms. We found that the host overhead is very small in our cluster, and the Myrinet is sensitive to the buffer reuse patterns. Our applications achieved a better performance for MPI than the mixed-mode. All the applications studied use only nonblocking communications, thus are able to overlap their communications with the computations. Our experiments show that the two-port communication at the GM and MPI levels (except for the RDMA read, and overlap) outperforms the one-port communication for the bandwidth. However, this did not translate into a considerable improvement at least for our applications.