dc.creatorRocha
dc.creatorRodrigo C. O.; Pereira
dc.creatorAlyson D.; Ramos
dc.creatorLuiz; Goes
dc.creatorLuis F. W.
dc.date2017
dc.dateabr
dc.date2017-11-13T13:22:24Z
dc.date2017-11-13T13:22:24Z
dc.date.accessioned2018-03-29T05:55:10Z
dc.date.available2018-03-29T05:55:10Z
dc.identifierConcurrency And Computation-practice & Experience. Wiley-blackwell, v. 29, p. , 2017.
dc.identifier1532-0626
dc.identifier1532-0634
dc.identifierWOS:000398717400011
dc.identifier10.1002/cpe.4053
dc.identifierhttp://onlinelibrary.wiley.com/doi/10.1002/cpe.4053/full
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/327877
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1364902
dc.descriptionThe stencil pattern is important in many scientific and engineering domains, spurring great interest from researchers and industry. In recent years, various optimizations have been proposed for parallel stencil applications running on graphics processing units (GPUs). In particular, tiling is a technique that can significantly enhance application performance by improving data locality and by reducing the volume of communication between host memory and GPU. In addition, tiling enables stencil applications to process inputs that are larger than the physical GPU memory. However, implementing tiling efficiently is complex, time-consuming, and error-prone. In this paper, we propose transparently optimized automatic stencil tiling (TOAST), an automatic tiling mechanism for iterative stencil computations running on GPUs; TOAST has 3 main benefits: (1) It incorporates an optimization model that seeks to maximize data reuse within tiles while respecting the amount of dynamically available GPU memory; (2) it offers a virtualized GPU memory for stencil computations, allowing for large input data; and (3) it performs optimal tiling transparently to the developer of the parallel stencil application. The current implementation of TOAST augments the PSkel framework with an internal solver based on genetic algorithms. Our experimental results show that TOAST improves the performance of iterative stencil applications by up to 13 x compared with their multithreaded (central processing unit-based) optimized versions and up to 48 x compared with a naive tiling approach on GPU. The TOAST mechanism is able to automatically achieve a low percentual overhead of data management compared with actual stencil computation.
dc.description29
dc.description8
dc.languageEnglish
dc.publisherWiley-Blackwell
dc.publisherHoboken
dc.relationConcurrency and Computation-Practice & Experience
dc.rightsfechado
dc.sourceWOS
dc.subjectAutotuning
dc.subjectGpu
dc.subjectOptimization Model
dc.subjectParallel Skeletons
dc.subjectStencil Computation
dc.subjectTiling
dc.titleToast: Automatic Tiling For Iterative Stencil Computations On Gpus
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución