Matches in SemOpenAlex for { <https://semopenalex.org/work/W2558367073> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2558367073 abstract "Sparse matrix vector multiplication (SpMV) is the workhorse for a wide range of linear algebra computations. In a serial setting, naive implementations for direct multiplication and transposed multiplication achieve very competitive performance. In parallel settings, especially on graphics hardware, it is widely believed that naive implementations cannot reach the performance of highly tuned parallel implementations and complex data formats. Most often, the cost for data conversion to these specialized formats as well as the cost for transpose operations are neglected, as they do not arise in all algorithms. In this paper, we revisit the naive implementation of SpMV for the GPU. Relying on recent advances in GPU hardware, such as fast hardware supported atomic operations and better cache performance, we show that a naive implementation can reach the performance of state-of-the-art SpMV implementations. In case the cost of format conversion and transposition cannot be amortized over many SpMV operations a naive implementation can even outperform state-of-the-art implementations significantly. Experimental results over a variety of data sets suggest that the adoption of the naive serial implementation to the GPU is not as inferior as it used to be on previous hardware generations. The integration of some naive strategies can potentially speed up state-of-the-art GPU SpMV implementations, especially in the transpose case." @default.
- W2558367073 created "2016-12-08" @default.
- W2558367073 creator A5014594342 @default.
- W2558367073 creator A5017743883 @default.
- W2558367073 creator A5058028526 @default.
- W2558367073 creator A5070162106 @default.
- W2558367073 date "2016-09-01" @default.
- W2558367073 modified "2023-10-16" @default.
- W2558367073 title "How naive is naive SpMV on the GPU?" @default.
- W2558367073 cites W1506342804 @default.
- W2558367073 cites W1508286210 @default.
- W2558367073 cites W1588915715 @default.
- W2558367073 cites W1981824841 @default.
- W2558367073 cites W1985938427 @default.
- W2558367073 cites W1993704253 @default.
- W2558367073 cites W1995649289 @default.
- W2558367073 cites W2009654791 @default.
- W2558367073 cites W2023930909 @default.
- W2558367073 cites W2035080386 @default.
- W2558367073 cites W2035278858 @default.
- W2558367073 cites W2087830284 @default.
- W2558367073 cites W2088866486 @default.
- W2558367073 cites W2096813338 @default.
- W2558367073 cites W2103877122 @default.
- W2558367073 cites W2126004407 @default.
- W2558367073 cites W2128853364 @default.
- W2558367073 cites W2162283062 @default.
- W2558367073 cites W2997945685 @default.
- W2558367073 cites W4243261006 @default.
- W2558367073 doi "https://doi.org/10.1109/hpec.2016.7761634" @default.
- W2558367073 hasPublicationYear "2016" @default.
- W2558367073 type Work @default.
- W2558367073 sameAs 2558367073 @default.
- W2558367073 citedByCount "12" @default.
- W2558367073 countsByYear W25583670732017 @default.
- W2558367073 countsByYear W25583670732019 @default.
- W2558367073 countsByYear W25583670732020 @default.
- W2558367073 countsByYear W25583670732021 @default.
- W2558367073 countsByYear W25583670732022 @default.
- W2558367073 countsByYear W25583670732023 @default.
- W2558367073 crossrefType "proceedings-article" @default.
- W2558367073 hasAuthorship W2558367073A5014594342 @default.
- W2558367073 hasAuthorship W2558367073A5017743883 @default.
- W2558367073 hasAuthorship W2558367073A5058028526 @default.
- W2558367073 hasAuthorship W2558367073A5070162106 @default.
- W2558367073 hasConcept C115537543 @default.
- W2558367073 hasConcept C121332964 @default.
- W2558367073 hasConcept C158693339 @default.
- W2558367073 hasConcept C173608175 @default.
- W2558367073 hasConcept C199360897 @default.
- W2558367073 hasConcept C200106649 @default.
- W2558367073 hasConcept C24890656 @default.
- W2558367073 hasConcept C26713055 @default.
- W2558367073 hasConcept C2778119891 @default.
- W2558367073 hasConcept C2780595030 @default.
- W2558367073 hasConcept C41008148 @default.
- W2558367073 hasConcept C62520636 @default.
- W2558367073 hasConceptScore W2558367073C115537543 @default.
- W2558367073 hasConceptScore W2558367073C121332964 @default.
- W2558367073 hasConceptScore W2558367073C158693339 @default.
- W2558367073 hasConceptScore W2558367073C173608175 @default.
- W2558367073 hasConceptScore W2558367073C199360897 @default.
- W2558367073 hasConceptScore W2558367073C200106649 @default.
- W2558367073 hasConceptScore W2558367073C24890656 @default.
- W2558367073 hasConceptScore W2558367073C26713055 @default.
- W2558367073 hasConceptScore W2558367073C2778119891 @default.
- W2558367073 hasConceptScore W2558367073C2780595030 @default.
- W2558367073 hasConceptScore W2558367073C41008148 @default.
- W2558367073 hasConceptScore W2558367073C62520636 @default.
- W2558367073 hasLocation W25583670731 @default.
- W2558367073 hasOpenAccess W2558367073 @default.
- W2558367073 hasPrimaryLocation W25583670731 @default.
- W2558367073 hasRelatedWork W1579918296 @default.
- W2558367073 hasRelatedWork W2040556424 @default.
- W2558367073 hasRelatedWork W2076165488 @default.
- W2558367073 hasRelatedWork W2161462353 @default.
- W2558367073 hasRelatedWork W2176391467 @default.
- W2558367073 hasRelatedWork W2366665520 @default.
- W2558367073 hasRelatedWork W2392023973 @default.
- W2558367073 hasRelatedWork W2558367073 @default.
- W2558367073 hasRelatedWork W2953648974 @default.
- W2558367073 hasRelatedWork W3038415719 @default.
- W2558367073 isParatext "false" @default.
- W2558367073 isRetracted "false" @default.
- W2558367073 magId "2558367073" @default.
- W2558367073 workType "article" @default.