Show simple item record

Array Program Transformation with Loo.py by Example: High-Order Finite Elements

dc.contributor.authorKlöckner, Andreas
dc.contributor.authorWilcox, Lucas C.
dc.contributor.authorWarburton, T.
dc.date2016
dc.date.accessioned2016-05-09T21:58:24Z
dc.date.available2016-05-09T21:58:24Z
dc.date.issued2016
dc.identifier.citationARRAY'16 (June 14, 2016). Santa Barbara, CA, USA.en_US
dc.identifier.urihttp://hdl.handle.net/10945/48656
dc.descriptionThe article of record as published may be found at http://dx.doi.org/10.1145/en_US
dc.description.abstractTo concisely and effectively demonstrate the capabilities of our program transformation system Loo.py, we examine a transformation path from two real-world Fortran subroutines as found in a weather model to a single high-performance computational kernel suitable for execution on modern GPU hardware. Along the transformation path, we encounter kernel fusion, vectorization, prefetching, parallelization, and algorithmic changes achieved by mechanized conversion between imperative and functional/substitution-based code, among a number more. We conclude with performance results that demonstrate the effects and support the effectiveness of the applied transformations.en_US
dc.description.sponsorshipUS Navy ONR grant number N00014-14-1-0117en_US
dc.description.sponsorshipNational Science Foundation under grant numbers DMS-1418961 and CCF-1524433en_US
dc.description.sponsorshipNvidia Corporationen_US
dc.description.sponsorshipUS Navy ONR grant numbers N00014-15-WX-01603 and N00014-13-1-0873en_US
dc.format.extent8 p.en_US
dc.rightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.en_US
dc.titleArray Program Transformation with Loo.py by Example: High-Order Finite Elementsen_US
dc.typeArticleen_US
dc.contributor.corporateNaval Postgraduate School (U.S.)en_US
dc.subject.authorcode generationen_US
dc.subject.authorhigh-level languageen_US
dc.subject.authorGPUen_US
dc.subject.authorsubstitution ruleen_US
dc.subject.authorembedded languageen_US
dc.subject.authorhigh-performanceen_US
dc.subject.authorprogram transformationen_US
dc.subject.authorOpenCLen_US
dc.description.funderUS Navy ONR grant number N00014-14-1-0117en_US
dc.description.funderNational Science Foundation under grant numbers DMS-1418961 and CCF-1524433en_US
dc.description.funderUS Navy ONR grant numbers N00014-15-WX-01603 and N00014-13-1-0873en_US


Files in this item

Thumbnail
Name:
Wilcox_Array_Program_2016.pdf
Size:
178.0Kb
Format:
PDF
Description:
Article
View/Open

This item appears in the following Collection(s)

Show simple item record