Evaluating Parallel Particle Advection Algorithms Over Various Workloads

dc.contributor.advisorChilds, Hank
dc.contributor.authorBinyahib, Roba
dc.date.accessioned2020-09-24T17:09:42Z
dc.date.available2020-09-24T17:09:42Z
dc.date.issued2020-09-24
dc.description.abstractWe consider the problem of efficient particle advection in a distributed- memory parallel setting, focusing on four popular parallelization algorithms. The performance of each of these algorithms varies based on the desired workload. Our research focuses on two important questions: (1) which parallelization techniques perform best for a given workload?, and (2) what are the unsolved problems in parallel particle advection? To answer these questions, we ran a “bake off” study between the algorithms with 216 tests, going to a concurrency up to 8192 cores and considering data sets as large as 34 billion cells with 300 million particles. We also performed a variety of optimizations to the algorithms, including fundamental enhancements to the “work requesting algorithm” and we introduce a new hybrid algorithm that we call “HyLiPoD.” Our findings inform tradeoffs between the algorithms and when domain scientists should switch between them to obtain better performance. Finally, we consider the future of parallel particle advection, i.e., how these algorithms will be run with in situ processing. This dissertation includes previously published co-authored material.en_US
dc.identifier.urihttps://hdl.handle.net/1794/25595
dc.language.isoen_US
dc.publisherUniversity of Oregon
dc.rightsAll Rights Reserved.
dc.subjectFlow Visualizationen_US
dc.subjectHigh Performance Computingen_US
dc.subjectScientific Visualizationen_US
dc.titleEvaluating Parallel Particle Advection Algorithms Over Various Workloads
dc.typeElectronic Thesis or Dissertation
thesis.degree.disciplineDepartment of Computer and Information Science
thesis.degree.grantorUniversity of Oregon
thesis.degree.leveldoctoral
thesis.degree.namePh.D.

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Binyahib_oregon_0171A_12694.pdf
Size:
6.23 MB
Format:
Adobe Portable Document Format