Show simple item record

dc.contributor.authorDaga, Mayanken_US
dc.contributor.authorScogland, Thomas R. W.en_US
dc.contributor.authorFeng, Wu-chunen_US
dc.date.accessioned2013-06-19T14:36:02Z
dc.date.available2013-06-19T14:36:02Z
dc.date.issued2011-07-01
dc.identifierhttp://eprints.cs.vt.edu/archive/00001159/en_US
dc.identifier.urihttp://hdl.handle.net/10919/19401
dc.description.abstractThe graphics processing unit (GPU) continues to make significant strides as an accelerator in commodity cluster computing for high-performance computing (HPC). For example, three of the top five fastest supercomputers in the world, as ranked by the TOP500, employ GPUs as accelerators. Despite this increasing interest in GPUs, however, optimizing the performance of a GPU-accelerated compute node requires deep technical knowledge of the underlying architecture. Although significant literature exists on how to optimize GPU performance on the more mature NVIDIA CUDA architecture, the converse is true for OpenCL on the AMD GPU. Consequently, we present and evaluate architecture-aware optimizations for the AMD GPU. The most prominent optimizations include (i) explicit use of registers, (ii) use of vector types, (iii) removal of branches, and (iv) use of image memory for global data. We demonstrate the efficacy of our AMD GPU optimizations by applying each optimization in isolation as well as in concert to a large-scale, molecular modeling application called GEM. Via these AMD-specific GPU optimizations, the AMD Radeon HD 5870 GPU delivers 65% better performance than with the wellknown NVIDIA-specific optimizations.en_US
dc.format.mimetypeapplication/pdfen_US
dc.publisherDepartment of Computer Science, Virginia Polytechnic Institute & State Universityen_US
dc.relation.ispartofComputer Science Technical Reportsen_US
dc.subjectSoftware engineeringen_US
dc.titleArchitecture-Aware Optimization on a 1600-core Graphics Processoren_US
dc.typeTechnical reporten_US
dc.identifier.trnumberTR-11-08en_US
dc.type.dcmitypeTexten_US
dc.identifier.sourceurlhttp://eprints.cs.vt.edu/archive/00001159/01/Arch-Aware-Opt.pdf


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record