PREDICTING PARALLEL APPLICATION PERFORMANCE VIA MACHINE LEARNING APPROACHES

dc.contributor.authorSingh, Karan
dc.date.accessioned2007-07-31T15:25:21Z
dc.date.available2012-07-31T06:11:33Z
dc.date.issued2007-07-31T15:25:21Z
dc.description.abstractConsistently growing architectural complexity and machine scales make creating accurate performance models for large-scale applications increasingly challenging. Traditional analytic models are difficult and time-consuming to construct, and are often unable to capture full system and application complexity. To address these challenges, we automatically build models based on execution samples. We use multilayer neural networks, since they can represent arbitrary functions and handle noisy inputs robustly. In this thesis, we focus on two well known parallel applications whose variations in execution times are not well understood: SMG2000, a semicoarsening multigrid solver, and HPL, an open source implementation of LINPACK. We sparsely sample performance data on two radically different platforms across large, multi-dimensional parameter spaces and show that our models based on this data can predict performance within 2% to 7% of actual application runtimes.en_US
dc.description.sponsorshipNational Science Foundation Grant Number CCF-0444413; United States Department of Energy Grant Number W-7405-Eng-48en_US
dc.format.extent296834 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.otherbibid: 6476387
dc.identifier.urihttps://hdl.handle.net/1813/7972
dc.language.isoen_USen_US
dc.subjecthigh-performance computingen_US
dc.subjectperformance modelingen_US
dc.subjectartificial neural networksen_US
dc.titlePREDICTING PARALLEL APPLICATION PERFORMANCE VIA MACHINE LEARNING APPROACHESen_US
dc.typedissertation or thesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis.pdf
Size:
289.88 KB
Format:
Adobe Portable Document Format