eCommons

 

Unified framework for sparse and dense SPMD code generation(preliminary report)

dc.contributor.authorKotlyar, Vladimiren_US
dc.contributor.authorPingali, Keshaven_US
dc.contributor.authorStodghill, Paulen_US
dc.date.accessioned2007-04-23T18:09:20Z
dc.date.available2007-04-23T18:09:20Z
dc.date.issued1997-03en_US
dc.description.abstractWe describe a novel approach to sparse {\em and} dense SPMD code generation: we view arrays (sparse and dense) as distributed relations and parallel loop execution as distributed relational query evaluation. This approach provides for a uniform treatment of arbitrary sparse matrix formats and partitioning information formats. The relational algebra view of computation and communication sets provides new opportunities for the optimization of node program performance and the reduction of communucation set generation and index translation overhead.en_US
dc.format.extent260563 bytes
dc.format.extent218183 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypeapplication/postscript
dc.identifier.citationhttp://techreports.library.cornell.edu:8081/Dienst/UI/1.0/Display/cul.cs/TR97-1625en_US
dc.identifier.urihttps://hdl.handle.net/1813/7280
dc.language.isoen_USen_US
dc.publisherCornell Universityen_US
dc.subjectcomputer scienceen_US
dc.subjecttechnical reporten_US
dc.titleUnified framework for sparse and dense SPMD code generation(preliminary report)en_US
dc.typetechnical reporten_US

Files

Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
97-1625.pdf
Size:
254.46 KB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
97-1625.ps
Size:
213.07 KB
Format:
Postscript Files