An Empirical Study of the Performance of Scalable Locality on a Distributed Shared Memory System

TRICERATOPS

TriCollege Digital Repository

An Empirical Study of the Performance of Scalable Locality on a Distributed Shared Memory System

Show simple item record

dc.contributor.advisor Wonnacott, David G.
dc.contributor.author Douglas, Tim
dc.date.accessioned 2011-10-18T18:14:50Z
dc.date.available 2011-10-18T18:14:50Z
dc.date.issued 2011
dc.identifier.uri http://hdl.handle.net/10066/7569
dc.description.abstract We run an empirical study to determine the performance attainable using scalable locality on a distributed shared memory system. We utilize the PLUTO automatic parallelizer and locality optimizer on a one-dimensional Jacobi stencil with a distributed shared memory system provided by Intel’s Cluster OpenMP on commodity hardware. Unlike earlier works which base performance concerns on tile size, we discover tile sizes are less crucial, and instead threading issues and cache interference need particular attention. On our 56 processor cluster of 14 quad-core machines, with preliminary single-level tiling we are able to realize 121.3 GFLOPS, or 63% of linear speedup. Our data suggest that adding further cores would increase performance linearly. en
dc.description.sponsorship Haverford College. Dept. of Computer Science en
dc.language.iso en_US en
dc.rights.uri http://creativecommons.org/licenses/by-nc/3.0/us/
dc.subject.lcsh Distributed shared memory -- Evaluation
dc.title An Empirical Study of the Performance of Scalable Locality on a Distributed Shared Memory System en
dc.type Thesis (B.S.) en


Files in this item

Files Description Size Format
2011DouglasT_thesis.pdf Thesis 116.5Kb PDF
2011DouglasT_release.pdf **Archive Staff Only** 98.08Kb PDF

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc/3.0/us/ Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc/3.0/us/