{"title":"Unsteady Turbulent Simulations on a Cluster of Graphics Processors","authors":"E. Phillips, R. Davis, John Douglas Owens","doi":"10.2514/6.2009-4002","DOIUrl":null,"url":null,"abstract":"Author(s): Phillips, Everett H.; Davis, Roger L.; Owens, John D. | Abstract: This paper describes the GPU accelerated MBFLO2 multi-block turbulent flow solver completely in double precision using CUDA and the latest generation of GPU processors. On a cluster of 8 Tesla C2050 ''Fermi'' GPUs and Intel Xeon X5550 ''Nehalem'' quad-core CPUs, we achieve 9x speedup over the parallel CPU solver or 70x speedup over the serial solver. High performance is obtained by optimizing the data layout on the GPU, optimizing data transfers and using asynchronous memory copies to overlap GPU execution with communications. We test the solver on a turbulent flat plate and an unsteady turbulent cylinder with 3.2 million grid points. We confirm the GPU results are in agreement with turbulent flow theory. We discuss the GPU optimization techniques used to reach this level of performance.","PeriodicalId":153058,"journal":{"name":"40th Fluid Dynamics Conference and Exhibit","volume":"80 5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"40th Fluid Dynamics Conference and Exhibit","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2514/6.2009-4002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 24
Abstract
Author(s): Phillips, Everett H.; Davis, Roger L.; Owens, John D. | Abstract: This paper describes the GPU accelerated MBFLO2 multi-block turbulent flow solver completely in double precision using CUDA and the latest generation of GPU processors. On a cluster of 8 Tesla C2050 ''Fermi'' GPUs and Intel Xeon X5550 ''Nehalem'' quad-core CPUs, we achieve 9x speedup over the parallel CPU solver or 70x speedup over the serial solver. High performance is obtained by optimizing the data layout on the GPU, optimizing data transfers and using asynchronous memory copies to overlap GPU execution with communications. We test the solver on a turbulent flat plate and an unsteady turbulent cylinder with 3.2 million grid points. We confirm the GPU results are in agreement with turbulent flow theory. We discuss the GPU optimization techniques used to reach this level of performance.
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
