{"title":"灵活控制并行程序之间的数据传输","authors":"Joe Shang-Chieh Wu, A. Sussman","doi":"10.1109/GRID.2004.31","DOIUrl":null,"url":null,"abstract":"Allowing loose coupling between complex e-science applications has many advantages, such as being able to easily incorporate new applications and to flexibly specify how the applications are connected to transfer data between them. To facilitate efficient, flexible data transfers between applications, in this paper we describe methods for making decisions at runtime about when such transfers occur, and for flexibly specifying when data transfers are desired. We also present preliminary experimental results that measure the overheads incurred by our approach.","PeriodicalId":335281,"journal":{"name":"Fifth IEEE/ACM International Workshop on Grid Computing","volume":"13 29","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"Flexible control of data transfers between parallel programs\",\"authors\":\"Joe Shang-Chieh Wu, A. Sussman\",\"doi\":\"10.1109/GRID.2004.31\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Allowing loose coupling between complex e-science applications has many advantages, such as being able to easily incorporate new applications and to flexibly specify how the applications are connected to transfer data between them. To facilitate efficient, flexible data transfers between applications, in this paper we describe methods for making decisions at runtime about when such transfers occur, and for flexibly specifying when data transfers are desired. We also present preliminary experimental results that measure the overheads incurred by our approach.\",\"PeriodicalId\":335281,\"journal\":{\"name\":\"Fifth IEEE/ACM International Workshop on Grid Computing\",\"volume\":\"13 29\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-11-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fifth IEEE/ACM International Workshop on Grid Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GRID.2004.31\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fifth IEEE/ACM International Workshop on Grid Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GRID.2004.31","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Flexible control of data transfers between parallel programs
Allowing loose coupling between complex e-science applications has many advantages, such as being able to easily incorporate new applications and to flexibly specify how the applications are connected to transfer data between them. To facilitate efficient, flexible data transfers between applications, in this paper we describe methods for making decisions at runtime about when such transfers occur, and for flexibly specifying when data transfers are desired. We also present preliminary experimental results that measure the overheads incurred by our approach.