FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W903362236> ?p ?o ?g. }

• W903362236 endingPage "23" @default.
• W903362236 startingPage "15" @default.
• W903362236 abstract "Kernel superposition, where an image is convolved with a spatially varying kernel, is commonly used in optics, astronomy, medical imaging and radiotherapy. This operation is computationally expensive and generally cannot benefit from the mathematical simplifications available for true convolutions. We systematically evaluated the performance of a number of implementations of a 2D Gaussian kernel superposition on several graphics processing units of two recent architectures. The 2D Gaussian kernel was used because of its importance in real-life applications and representativeness of expensive-to-evaluate, separable kernels. The implementations were based both on the gather approach found in the literature and on the scatter approach presented here. Our results show that, over a range of kernel sizes, the scatter approach delivers speedups of 2.1–14.5 or 1.3–4.9 times, depending on the architecture. These numbers were further improved to 4.8–28.5 and 3.7–16.8 times, respectively, when only “exact” implementations were compared. Speedups similar to those presented are expected for other separable kernels and, we argue, will also remain applicable for problems of higher dimensionality." @default.
• W903362236 created "2016-06-24" @default.
• W903362236 creator A5027518475 @default.
• W903362236 creator A5059681293 @default.
• W903362236 creator A5075192483 @default.
• W903362236 date "2015-10-01" @default.
• W903362236 modified "2023-09-23" @default.
• W903362236 title "Efficient scatter-based kernel superposition on GPU" @default.
• W903362236 cites W1511559872 @default.
• W903362236 cites W1592017725 @default.
• W903362236 cites W1932772409 @default.
• W903362236 cites W1992705935 @default.
• W903362236 cites W2001016110 @default.
• W903362236 cites W2022303284 @default.
• W903362236 cites W2022985124 @default.
• W903362236 cites W2023016496 @default.
• W903362236 cites W2024701229 @default.
• W903362236 cites W2055844022 @default.
• W903362236 cites W2057266887 @default.
• W903362236 cites W2072631737 @default.
• W903362236 cites W2079293456 @default.
• W903362236 cites W2096560676 @default.
• W903362236 cites W2099104461 @default.
• W903362236 cites W2099111745 @default.
• W903362236 cites W2104603373 @default.
• W903362236 cites W2109762925 @default.
• W903362236 cites W2115916992 @default.
• W903362236 cites W2133175895 @default.
• W903362236 cites W2133808911 @default.
• W903362236 cites W2135860851 @default.
• W903362236 cites W2141314576 @default.
• W903362236 cites W2150606860 @default.
• W903362236 cites W2155706753 @default.
• W903362236 cites W2159481344 @default.
• W903362236 cites W2162209822 @default.
• W903362236 cites W2541129984 @default.
• W903362236 cites W3000120212 @default.
• W903362236 cites W31392012 @default.
• W903362236 doi "https://doi.org/10.1016/j.jpdc.2015.07.003" @default.
• W903362236 hasPublicationYear "2015" @default.
• W903362236 type Work @default.
• W903362236 sameAs 903362236 @default.
• W903362236 citedByCount "3" @default.
• W903362236 countsByYear W9033622362015 @default.
• W903362236 countsByYear W9033622362016 @default.
• W903362236 crossrefType "journal-article" @default.
• W903362236 hasAuthorship W903362236A5027518475 @default.
• W903362236 hasAuthorship W903362236A5059681293 @default.
• W903362236 hasAuthorship W903362236A5075192483 @default.
• W903362236 hasBestOaLocation W9033622362 @default.
• W903362236 hasConcept C11413529 @default.
• W903362236 hasConcept C118615104 @default.
• W903362236 hasConcept C121332964 @default.
• W903362236 hasConcept C121684516 @default.
• W903362236 hasConcept C134306372 @default.
• W903362236 hasConcept C159985019 @default.
• W903362236 hasConcept C163716315 @default.
• W903362236 hasConcept C192562407 @default.
• W903362236 hasConcept C199360897 @default.
• W903362236 hasConcept C204323151 @default.
• W903362236 hasConcept C21442007 @default.
• W903362236 hasConcept C26713055 @default.
• W903362236 hasConcept C27753989 @default.
• W903362236 hasConcept C33923547 @default.
• W903362236 hasConcept C41008148 @default.
• W903362236 hasConcept C62520636 @default.
• W903362236 hasConcept C70710897 @default.
• W903362236 hasConcept C74193536 @default.
• W903362236 hasConceptScore W903362236C11413529 @default.
• W903362236 hasConceptScore W903362236C118615104 @default.
• W903362236 hasConceptScore W903362236C121332964 @default.
• W903362236 hasConceptScore W903362236C121684516 @default.
• W903362236 hasConceptScore W903362236C134306372 @default.
• W903362236 hasConceptScore W903362236C159985019 @default.
• W903362236 hasConceptScore W903362236C163716315 @default.
• W903362236 hasConceptScore W903362236C192562407 @default.
• W903362236 hasConceptScore W903362236C199360897 @default.
• W903362236 hasConceptScore W903362236C204323151 @default.
• W903362236 hasConceptScore W903362236C21442007 @default.
• W903362236 hasConceptScore W903362236C26713055 @default.
• W903362236 hasConceptScore W903362236C27753989 @default.
• W903362236 hasConceptScore W903362236C33923547 @default.
• W903362236 hasConceptScore W903362236C41008148 @default.
• W903362236 hasConceptScore W903362236C62520636 @default.
• W903362236 hasConceptScore W903362236C70710897 @default.
• W903362236 hasConceptScore W903362236C74193536 @default.
• W903362236 hasFunder F4320319985 @default.
• W903362236 hasFunder F4320334960 @default.
• W903362236 hasLocation W9033622361 @default.
• W903362236 hasLocation W9033622362 @default.
• W903362236 hasOpenAccess W903362236 @default.
• W903362236 hasPrimaryLocation W9033622361 @default.
• W903362236 hasRelatedWork W1485630101 @default.
• W903362236 hasRelatedWork W1536235319 @default.
• W903362236 hasRelatedWork W1575263621 @default.
• W903362236 hasRelatedWork W1964111820 @default.
• W903362236 hasRelatedWork W2108208685 @default.
• W903362236 hasRelatedWork W2111389017 @default.

• next