Show simple item record

dc.contributor.authorSerpa, Matheus S.
dc.contributor.authorCruz, Eduardo H.M.
dc.contributor.authorDiener, Matthias
dc.contributor.authorKrause, Arthur M.
dc.contributor.authorNavaux, Philippe O.A.
dc.contributor.authorFarrés, Albert
dc.contributor.authorRosas, Claudia
dc.contributor.authorHanzich, Mauricio
dc.contributor.authorPanetta, Jairo
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2018-01-30T09:48:00Z
dc.date.available2018-01-30T09:48:00Z
dc.date.issued2017-11-16
dc.identifier.citationSerpa, M. S. [et al.]. Strategies to Improve the Performance of a Geophysics Model for Different Manycore Systems. A: Computer Architecture and High Performance Computing Workshops (SBAC-PADW), 2017 International Symposium on. "". IEEE, 2017, p. 49-54.
dc.identifier.isbn978-1-5386-4819-3
dc.identifier.urihttp://hdl.handle.net/2117/113373
dc.description.abstractMany software mechanisms for geophysics exploration in Oil & Gas industries are based on wave propagation simulation. To perform such simulations, state-of-art HPC architectures are employed, generating results faster and with more accuracy at each generation. The software must evolve to support the new features of each design to keep performance scaling. Furthermore, it is important to understand the impact of each change applied to the software, in order to improve the performance as most as possible. In this paper, we propose several optimization strategies for a wave propagation model for five architectures: Intel Haswell, Intel Knights Corner, Intel Knights Landing, NVIDIA Kepler and NVIDIA Maxwell. We focus on improving the cache memory usage, vectorization, and locality in the memory hierarchy. We analyze the hardware impact of the optimizations, providing insights of how each strategy can improve the performance. The results show that NVIDIA Maxwell improves over Intel Haswell, Intel Knights Corner, Intel Knights Landing and NVIDIA Kepler performance by up to 17.9x.
dc.description.sponsorshipThis research received funding from the EU H2020 Programme and from MCTI/RNP-Brazil under the HPC4E project, grant n.o 689772. It was also supported by Intel under the Modern Code Project, and Petrobras.
dc.format.extent6 p.
dc.language.isoeng
dc.publisherIEEE
dc.subjectÀrees temàtiques de la UPC::Enginyeria electrònica
dc.subject.lcshGeophysics--Data processing
dc.subject.otherOptimization
dc.subject.otherComputer architecture
dc.subject.otherProgram processors
dc.subject.otherMathematical model
dc.subject.otherAcoustic waves
dc.subject.otherHardware
dc.subject.otherCache memory
dc.titleStrategies to Improve the Performance of a Geophysics Model for Different Manycore Systems
dc.typeConference lecture
dc.subject.lemacGeofísica
dc.identifier.doi10.1109/SBAC-PADW.2017.17
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/8109005/
dc.rights.accessOpen Access
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/689772/EU/HPC for Energy/HPC4E
upcommons.citation.contributorComputer Architecture and High Performance Computing Workshops (SBAC-PADW), 2017 International Symposium on
upcommons.citation.publishedtrue
upcommons.citation.startingPage49
upcommons.citation.endingPage54


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder