Matches in SemOpenAlex for { <https://semopenalex.org/work/W2555931724> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2555931724 endingPage "1549" @default.
- W2555931724 startingPage "1535" @default.
- W2555931724 abstract "Workload partitioning and the subsequent work item-to-thread mapping are key aspects to face when implementing any efficient GPU application. Different techniques have been proposed to deal with such issues, ranging from the computationally simplest static to the most complex dynamic ones. Each of them finds the best use depending on the workload characteristics (static for more regular workloads, dynamic for irregular workloads). Nevertheless, no one of them provides a sound tradeoff when applied in both cases. Static approaches lead to load unbalancing with irregular problems, while the computational overhead introduced by the dynamic or semi-dynamic approaches often worsens the overall application performance when run on regular problems. This article presents an efficient dynamic technique for workload partitioning and work item-to-thread mapping whose complexity is significantly reduced with respect to the other dynamic approaches in literature. The article shows how the partitioning and mapping algorithm has been implemented by fully taking advantage of the GPU device characteristics with the aim of minimizing the involved computational overhead. The article shows, compares, and analyses the experimental results obtained by applying the proposed approach and several static, dynamic, and semi-dynamic techniques at the state of the art to different benchmarks and over different GPU technologies (i.e., NVIDIA Fermi, Kepler, and Maxwell) to understand when and how each technique best applies." @default.
- W2555931724 created "2016-11-30" @default.
- W2555931724 creator A5053217543 @default.
- W2555931724 creator A5088231786 @default.
- W2555931724 date "2017-06-01" @default.
- W2555931724 modified "2023-10-16" @default.
- W2555931724 title "A Dynamic Approach for Workload Partitioning on GPU Architectures" @default.
- W2555931724 cites W1504291959 @default.
- W2555931724 cites W1506342804 @default.
- W2555931724 cites W1770249075 @default.
- W2555931724 cites W1893178273 @default.
- W2555931724 cites W1985291160 @default.
- W2555931724 cites W2019708326 @default.
- W2555931724 cites W2022219663 @default.
- W2555931724 cites W2022541337 @default.
- W2555931724 cites W2035080386 @default.
- W2555931724 cites W2059966434 @default.
- W2555931724 cites W2085248745 @default.
- W2555931724 cites W2087977509 @default.
- W2555931724 cites W2107173440 @default.
- W2555931724 cites W2109473404 @default.
- W2555931724 cites W2126739950 @default.
- W2555931724 cites W2128853364 @default.
- W2555931724 cites W2165633563 @default.
- W2555931724 cites W2208875625 @default.
- W2555931724 cites W2502734103 @default.
- W2555931724 doi "https://doi.org/10.1109/tpds.2016.2631166" @default.
- W2555931724 hasPublicationYear "2017" @default.
- W2555931724 type Work @default.
- W2555931724 sameAs 2555931724 @default.
- W2555931724 citedByCount "3" @default.
- W2555931724 countsByYear W25559317242018 @default.
- W2555931724 crossrefType "journal-article" @default.
- W2555931724 hasAuthorship W2555931724A5053217543 @default.
- W2555931724 hasAuthorship W2555931724A5088231786 @default.
- W2555931724 hasConcept C111919701 @default.
- W2555931724 hasConcept C113775141 @default.
- W2555931724 hasConcept C120314980 @default.
- W2555931724 hasConcept C138101251 @default.
- W2555931724 hasConcept C173608175 @default.
- W2555931724 hasConcept C202491316 @default.
- W2555931724 hasConcept C2778476105 @default.
- W2555931724 hasConcept C2779960059 @default.
- W2555931724 hasConcept C41008148 @default.
- W2555931724 hasConceptScore W2555931724C111919701 @default.
- W2555931724 hasConceptScore W2555931724C113775141 @default.
- W2555931724 hasConceptScore W2555931724C120314980 @default.
- W2555931724 hasConceptScore W2555931724C138101251 @default.
- W2555931724 hasConceptScore W2555931724C173608175 @default.
- W2555931724 hasConceptScore W2555931724C202491316 @default.
- W2555931724 hasConceptScore W2555931724C2778476105 @default.
- W2555931724 hasConceptScore W2555931724C2779960059 @default.
- W2555931724 hasConceptScore W2555931724C41008148 @default.
- W2555931724 hasIssue "6" @default.
- W2555931724 hasLocation W25559317241 @default.
- W2555931724 hasOpenAccess W2555931724 @default.
- W2555931724 hasPrimaryLocation W25559317241 @default.
- W2555931724 hasRelatedWork W1579918296 @default.
- W2555931724 hasRelatedWork W2058254833 @default.
- W2555931724 hasRelatedWork W2092071486 @default.
- W2555931724 hasRelatedWork W2133693067 @default.
- W2555931724 hasRelatedWork W2168921806 @default.
- W2555931724 hasRelatedWork W2170268965 @default.
- W2555931724 hasRelatedWork W2391167130 @default.
- W2555931724 hasRelatedWork W3033052750 @default.
- W2555931724 hasRelatedWork W3148394109 @default.
- W2555931724 hasRelatedWork W4283067488 @default.
- W2555931724 hasVolume "28" @default.
- W2555931724 isParatext "false" @default.
- W2555931724 isRetracted "false" @default.
- W2555931724 magId "2555931724" @default.
- W2555931724 workType "article" @default.