{"title":"The Value of Automation: A Study of MPI Application Migration Methods","authors":"Karolina Sarnowska-Upton, A. Grimshaw","doi":"10.1109/TrustCom.2013.149","DOIUrl":null,"url":null,"abstract":"This paper presents a user study of the process of migrating MPI applications manually. The gathered data quantifies the scale of the challenge that researchers face when attempting to use shared computing resources. Migrating to one site took on average 2.5 hours where the majority of the time was spent on learning, compiling, and debugging. Less experienced researchers took almost 50% more time and overall spread their effort across more days. Consequently, they took on average three weeks to migrate to four sites. The study data is used to investigate the speedup that can be gained by automating the migration process. How much more efficient application migration can be when utilizing FEAM, the Framework for Efficient Application Migration, instead of just manual methods is modeled in terms of time. While an ideal solution for general automation of application migration would enable computations to run on any available compute resource with minimal user interaction and in a tuned manner, FEAM focuses on what can be automated without recompiling applications. The calculations predict that using FEAM results in a 1.6x speedup on average or just under an hour of effort saved per site. This equates to more than two day of saved effort per site. The results presented in this paper underline the value of automation in the context of application migration.","PeriodicalId":206739,"journal":{"name":"2013 12th IEEE International Conference on Trust, Security and Privacy in Computing and Communications","volume":"87 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 12th IEEE International Conference on Trust, Security and Privacy in Computing and Communications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TrustCom.2013.149","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
This paper presents a user study of the process of migrating MPI applications manually. The gathered data quantifies the scale of the challenge that researchers face when attempting to use shared computing resources. Migrating to one site took on average 2.5 hours where the majority of the time was spent on learning, compiling, and debugging. Less experienced researchers took almost 50% more time and overall spread their effort across more days. Consequently, they took on average three weeks to migrate to four sites. The study data is used to investigate the speedup that can be gained by automating the migration process. How much more efficient application migration can be when utilizing FEAM, the Framework for Efficient Application Migration, instead of just manual methods is modeled in terms of time. While an ideal solution for general automation of application migration would enable computations to run on any available compute resource with minimal user interaction and in a tuned manner, FEAM focuses on what can be automated without recompiling applications. The calculations predict that using FEAM results in a 1.6x speedup on average or just under an hour of effort saved per site. This equates to more than two day of saved effort per site. The results presented in this paper underline the value of automation in the context of application migration.