Publication
Measurement-Based Probabilistic Timing Analysis for Graphics Processor Units
dc.contributor.author | Berezovskyi, Kostiantyn | |
dc.contributor.author | Guet, Fabrice | |
dc.contributor.author | Santinelli, Luca | |
dc.contributor.author | Bletsas, Konstantinos | |
dc.contributor.author | Tovar, Eduardo | |
dc.date.accessioned | 2017-02-03T09:19:32Z | |
dc.date.embargo | 2117 | |
dc.date.issued | 2016 | |
dc.description | Architecture of Computing Systems (ARCS 2016). 4 to 7, Apr, 2016. Nuremberg, Germany. | pt_PT |
dc.description.abstract | Purely analytical worst-case execution time (WCET) estimation approaches for Graphics Processor Units (GPUs) cannot go far because of insufficient public information for the hardware. Therefore measurement-based probabilistic timing analysis (MBPTA) seems the way forward. We recently demonstrated MBPTA for GPUs, based on Extreme Value Theory (EVT) of the “Block Maxima” paradigm. In this newer work, we formulate and experimentally evaluate a more robust MBPTA approach based on the EVT “Peak over Threshold” paradigm with a complete set of tests for verifying EVT applicability. It optimally selects parameters to best-fit the input measurements for more accurate probabilistic WCET estimates. Different system configuration parameters (cache arrangements, thread block size) and their effect on the pWCET are considered, enhancing models of worst-case GPU behavior. | pt_PT |
dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
dc.identifier.doi | 10.1007/978-3-319-30695-7_17 | pt_PT |
dc.identifier.uri | http://hdl.handle.net/10400.22/9498 | |
dc.language.iso | eng | pt_PT |
dc.publisher | Springer Verlag | pt_PT |
dc.relation | Embedded Multi-Core Systems for Mixed Criticality Applications in Dynamic and Changeable Real-Time Environments | |
dc.relation | Guaranteed Component Assembly with Round Trip Analysis for Energy Efficient High-integrity Multi-core Systems | |
dc.relation.ispartofseries | Lecture Notes in Computer Science;Vol. 9637 | |
dc.relation.publisherversion | http://link.springer.com/chapter/10.1007/978-3-319-30695-7_17 | pt_PT |
dc.subject | Computer Communication Networks | pt_PT |
dc.subject | Computer System Implementation | pt_PT |
dc.subject | Algorithm Analysis and Problem Complexity | pt_PT |
dc.subject | Software Engineering | pt_PT |
dc.title | Measurement-Based Probabilistic Timing Analysis for Graphics Processor Units | pt_PT |
dc.type | conference object | |
dspace.entity.type | Publication | |
oaire.awardTitle | Embedded Multi-Core Systems for Mixed Criticality Applications in Dynamic and Changeable Real-Time Environments | |
oaire.awardTitle | Guaranteed Component Assembly with Round Trip Analysis for Energy Efficient High-integrity Multi-core Systems | |
oaire.awardURI | info:eu-repo/grantAgreement/EC/FP7/621429/EU | |
oaire.awardURI | info:eu-repo/grantAgreement/EC/FP7/333053/EU | |
oaire.citation.conferencePlace | Nuremberg, Germany, April 4–7, 2016 | pt_PT |
oaire.citation.endPage | 236 | pt_PT |
oaire.citation.startPage | 223 | pt_PT |
oaire.citation.title | Proceedings of 29th International Conference | pt_PT |
oaire.citation.volume | Vol. 9637 | pt_PT |
oaire.fundingStream | FP7 | |
oaire.fundingStream | FP7 | |
person.familyName | Tovar | |
person.givenName | Eduardo | |
person.identifier.ciencia-id | 6017-8881-11E8 | |
person.identifier.orcid | 0000-0001-8979-3876 | |
person.identifier.scopus-author-id | 7006312557 | |
project.funder.identifier | http://doi.org/10.13039/501100008530 | |
project.funder.identifier | http://doi.org/10.13039/501100008530 | |
project.funder.name | European Commission | |
project.funder.name | European Commission | |
rcaap.rights | openAccess | pt_PT |
rcaap.type | conferenceObject | pt_PT |
relation.isAuthorOfPublication | 80b63d8a-2e6d-484e-af3c-55849d0cb65e | |
relation.isAuthorOfPublication.latestForDiscovery | 80b63d8a-2e6d-484e-af3c-55849d0cb65e | |
relation.isProjectOfPublication | c05ca6d0-eb47-46e6-93ae-3218a8c9ee48 | |
relation.isProjectOfPublication | 17322fe8-c558-4180-88af-8ed0b847498c | |
relation.isProjectOfPublication.latestForDiscovery | 17322fe8-c558-4180-88af-8ed0b847498c |