Matches in SemOpenAlex for { <https://semopenalex.org/work/W2097477621> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2097477621 endingPage "42" @default.
- W2097477621 startingPage "33" @default.
- W2097477621 abstract "Efficient implementations of the Discrete Fourier Transform (DFT) for GPUs provide good performance with large data sizes, but are not competitive with CPU code for small data sizes. On the other hand, several applications perform multiple DFTs on small data sizes. In fact, even algorithms for large data sizes use a divide-and-conquer approach, where eventually small DFTs need to be performed. We discuss our DFT implementation, which is efficient for multiple small DFTs. One feature of our implementation is the use of the asymptotically slow matrix multiplication approach for small data sizes, which improves performance on the GPU due to its regular memory access and computational patterns. We combine this algorithm with the mixed radix algorithm for 1-D, 2-D, and 3-D complex DFTs. We also demonstrate the effect of different optimization techniques. When GPUs are used to accelerate a component of an application running on the host, it is important that decisions taken to optimize the GPU performance not affect the performance of the rest of the application on the host. One feature of our implementation is that we use a data layout that is not optimal for the GPU so that the overall effect on the application is better. Our implementation performs up to two orders of magnitude faster than cuFFT on an NVIDIA GeForce 9800 GTX GPU and up to one to two orders of magnitude faster than FFTW on a CPU for multiple small DFTs. Furthermore, we show that our implementation can accelerate the performance of a Quantum Monte Carlo application for which cuFFT is not effective. The primary contributions of this work lie in demonstrating the utility of the matrix multiplication approach and also in providing an implementation that is efficient for small DFTs when a GPU is used to accelerate an application running on the host." @default.
- W2097477621 created "2016-06-24" @default.
- W2097477621 creator A5079283230 @default.
- W2097477621 creator A5081004875 @default.
- W2097477621 date "2011-05-23" @default.
- W2097477621 modified "2023-09-28" @default.
- W2097477621 title "Small Discrete Fourier Transforms on GPUs" @default.
- W2097477621 cites W1607335281 @default.
- W2097477621 cites W1979502974 @default.
- W2097477621 cites W2008343731 @default.
- W2097477621 cites W2050288192 @default.
- W2097477621 cites W2061171222 @default.
- W2097477621 cites W2102182691 @default.
- W2097477621 cites W2102902545 @default.
- W2097477621 cites W2108600626 @default.
- W2097477621 cites W2114927422 @default.
- W2097477621 cites W2134572726 @default.
- W2097477621 cites W3145767355 @default.
- W2097477621 cites W3147878143 @default.
- W2097477621 doi "https://doi.org/10.5555/2007336.2007395" @default.
- W2097477621 hasPublicationYear "2011" @default.
- W2097477621 type Work @default.
- W2097477621 sameAs 2097477621 @default.
- W2097477621 citedByCount "6" @default.
- W2097477621 countsByYear W20974776212013 @default.
- W2097477621 countsByYear W20974776212015 @default.
- W2097477621 countsByYear W20974776212017 @default.
- W2097477621 countsByYear W20974776212020 @default.
- W2097477621 crossrefType "proceedings-article" @default.
- W2097477621 hasAuthorship W2097477621A5079283230 @default.
- W2097477621 hasAuthorship W2097477621A5081004875 @default.
- W2097477621 hasConcept C11413529 @default.
- W2097477621 hasConcept C121332964 @default.
- W2097477621 hasConcept C126831891 @default.
- W2097477621 hasConcept C17349429 @default.
- W2097477621 hasConcept C173608175 @default.
- W2097477621 hasConcept C177264268 @default.
- W2097477621 hasConcept C18903297 @default.
- W2097477621 hasConcept C199360897 @default.
- W2097477621 hasConcept C2776760102 @default.
- W2097477621 hasConcept C41008148 @default.
- W2097477621 hasConcept C459310 @default.
- W2097477621 hasConcept C62520636 @default.
- W2097477621 hasConcept C75172450 @default.
- W2097477621 hasConcept C83283714 @default.
- W2097477621 hasConcept C84114770 @default.
- W2097477621 hasConcept C86803240 @default.
- W2097477621 hasConceptScore W2097477621C11413529 @default.
- W2097477621 hasConceptScore W2097477621C121332964 @default.
- W2097477621 hasConceptScore W2097477621C126831891 @default.
- W2097477621 hasConceptScore W2097477621C17349429 @default.
- W2097477621 hasConceptScore W2097477621C173608175 @default.
- W2097477621 hasConceptScore W2097477621C177264268 @default.
- W2097477621 hasConceptScore W2097477621C18903297 @default.
- W2097477621 hasConceptScore W2097477621C199360897 @default.
- W2097477621 hasConceptScore W2097477621C2776760102 @default.
- W2097477621 hasConceptScore W2097477621C41008148 @default.
- W2097477621 hasConceptScore W2097477621C459310 @default.
- W2097477621 hasConceptScore W2097477621C62520636 @default.
- W2097477621 hasConceptScore W2097477621C75172450 @default.
- W2097477621 hasConceptScore W2097477621C83283714 @default.
- W2097477621 hasConceptScore W2097477621C84114770 @default.
- W2097477621 hasConceptScore W2097477621C86803240 @default.
- W2097477621 hasLocation W20974776211 @default.
- W2097477621 hasOpenAccess W2097477621 @default.
- W2097477621 hasPrimaryLocation W20974776211 @default.
- W2097477621 hasRelatedWork W1497484262 @default.
- W2097477621 hasRelatedWork W1974914484 @default.
- W2097477621 hasRelatedWork W1982401581 @default.
- W2097477621 hasRelatedWork W2021104567 @default.
- W2097477621 hasRelatedWork W2031445984 @default.
- W2097477621 hasRelatedWork W2059434713 @default.
- W2097477621 hasRelatedWork W2067431903 @default.
- W2097477621 hasRelatedWork W2077305459 @default.
- W2097477621 hasRelatedWork W2098497669 @default.
- W2097477621 hasRelatedWork W2102067213 @default.
- W2097477621 hasRelatedWork W2108600626 @default.
- W2097477621 hasRelatedWork W2118001135 @default.
- W2097477621 hasRelatedWork W2132159377 @default.
- W2097477621 hasRelatedWork W2171473263 @default.
- W2097477621 hasRelatedWork W2381203691 @default.
- W2097477621 hasRelatedWork W2762933290 @default.
- W2097477621 hasRelatedWork W2927310355 @default.
- W2097477621 hasRelatedWork W2948602771 @default.
- W2097477621 hasRelatedWork W2966584279 @default.
- W2097477621 hasRelatedWork W91577598 @default.
- W2097477621 isParatext "false" @default.
- W2097477621 isRetracted "false" @default.
- W2097477621 magId "2097477621" @default.
- W2097477621 workType "article" @default.