Show simple item record

dc.contributor.authorŚwirydowicz, Ken_US
dc.contributor.authorChalmers, Nen_US
dc.contributor.authorKarakus, Aen_US
dc.contributor.authorWarburton, Ten_US
dc.date.accessioned2018-01-19T12:55:12Z
dc.date.available2018-01-19T12:55:12Z
dc.identifier.urihttp://hdl.handle.net/10919/81866
dc.description.abstractThis paper is devoted to GPU kernel optimization and performance analysis of three tensor-product operators arising in finite element methods. We provide a mathematical background to these operations and implementation details. Achieving close-to-the-peak performance for these operators requires extensive optimization because of the operators' properties: low arithmetic intensity, tiered structure, and the need to store intermediate results inside the kernel. We give a guided overview of optimization strategies and we present a performance model that allows us to compare the efficacy of these optimizations against an empirically calibrated roofline.en_US
dc.relation.urihttp://arxiv.org/abs/1711.00903v2en_US
dc.subjectcs.MSen_US
dc.subjectcs.MSen_US
dc.subjectcs.DCen_US
dc.subjectcs.NAen_US
dc.subjectcs.PFen_US
dc.subjectmath.NAen_US
dc.titleAcceleration of tensor-product operations for high-order finite element methodsen_US
dc.typeArticle - Refereed
dc.description.notes31 pages, 11 figuresen_US
dc.identifier.orcidWarburton, T [0000-0002-3202-1151]en_US
pubs.organisational-group/Virginia Tech
pubs.organisational-group/Virginia Tech/All T&R Faculty
pubs.organisational-group/Virginia Tech/Science
pubs.organisational-group/Virginia Tech/Science/COS T&R Faculty
pubs.organisational-group/Virginia Tech/Science/Mathematics


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record