Hamid Yasinian, Mansour Esmaeilpour, M. Shirmohammadi, Mahshid Jamshidi
{"title":"Messaging techniques (MPI) in grid environment: a survey","authors":"Hamid Yasinian, Mansour Esmaeilpour, M. Shirmohammadi, Mahshid Jamshidi","doi":"10.1504/IJSSS.2018.10013663","DOIUrl":null,"url":null,"abstract":"The newfangled phenomenon of grid, meaning to share the heterogeneous calculative sources and data between the independent organizations which are geographically disjoined. Grid functional programs usually need a great volume of distributed data or calculative sources for applying which does not usually exist in a single organisation. Nevertheless, due to the existence of the heterogeneous sources and the dynamic nature of grid, reaching a high level of functioning in this environment is so difficult. Regarding the grid environment's being heterogeneous and dynamic performing, these acts are not easy at all. Applying a MPI functional program on calculative grids needs fault tolerance and designing a middleware which conceals the nodes' being dynamic in grid for programmer. Applying the functional programs under grid is extremely susceptible of errors. So in this article all methods of tolerance including diagnosing the fault and improving fault have been surveyed as a key feature in grid contexts.","PeriodicalId":89681,"journal":{"name":"International journal of society systems science","volume":"10 1","pages":"91"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of society systems science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1504/IJSSS.2018.10013663","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The newfangled phenomenon of grid, meaning to share the heterogeneous calculative sources and data between the independent organizations which are geographically disjoined. Grid functional programs usually need a great volume of distributed data or calculative sources for applying which does not usually exist in a single organisation. Nevertheless, due to the existence of the heterogeneous sources and the dynamic nature of grid, reaching a high level of functioning in this environment is so difficult. Regarding the grid environment's being heterogeneous and dynamic performing, these acts are not easy at all. Applying a MPI functional program on calculative grids needs fault tolerance and designing a middleware which conceals the nodes' being dynamic in grid for programmer. Applying the functional programs under grid is extremely susceptible of errors. So in this article all methods of tolerance including diagnosing the fault and improving fault have been surveyed as a key feature in grid contexts.