Matches in SemOpenAlex for { <https://semopenalex.org/work/W2070897293> ?p ?o ?g. }
- W2070897293 endingPage "26" @default.
- W2070897293 startingPage "1" @default.
- W2070897293 abstract "General-purpose GPU-based systems are highly attractive, as they give potentially massive performance at little cost. Realizing such potential is challenging due to the complexity of programming. This article presents a compiler-based approach to automatically generate optimized OpenCL code from data parallel OpenMP programs for GPUs. A key feature of our scheme is that it leverages existing transformations, especially data transformations, to improve performance on GPU architectures and uses automatic machine learning to build a predictive model to determine if it is worthwhile running the OpenCL code on the GPU or OpenMP code on the multicore host. We applied our approach to the entire NAS parallel benchmark suite and evaluated it on distinct GPU-based systems. We achieved average (up to) speedups of 4.51× and 4.20× (143× and 67×) on Core i7/NVIDIA GeForce GTX580 and Core i7/AMD Radeon 7970 platforms, respectively, over a sequential baseline. Our approach achieves, on average, greater than 10× speedups over two state-of-the-art automatic GPU code generators." @default.
- W2070897293 created "2016-06-24" @default.
- W2070897293 creator A5027001025 @default.
- W2070897293 creator A5028870701 @default.
- W2070897293 creator A5077188995 @default.
- W2070897293 date "2014-12-08" @default.
- W2070897293 modified "2023-10-17" @default.
- W2070897293 title "Automatic and Portable Mapping of Data Parallel Programs to OpenCL for GPU-Based Heterogeneous Systems" @default.
- W2070897293 cites W1537323515 @default.
- W2070897293 cites W1552624537 @default.
- W2070897293 cites W1782174992 @default.
- W2070897293 cites W1966124831 @default.
- W2070897293 cites W1982020565 @default.
- W2070897293 cites W1987564528 @default.
- W2070897293 cites W1992851788 @default.
- W2070897293 cites W2005985523 @default.
- W2070897293 cites W2007516655 @default.
- W2070897293 cites W2016352575 @default.
- W2070897293 cites W2016357834 @default.
- W2070897293 cites W2017579069 @default.
- W2070897293 cites W2028122240 @default.
- W2070897293 cites W2033139628 @default.
- W2070897293 cites W2048205898 @default.
- W2070897293 cites W2053546108 @default.
- W2070897293 cites W2056579078 @default.
- W2070897293 cites W2077143534 @default.
- W2070897293 cites W2083304636 @default.
- W2070897293 cites W2098426571 @default.
- W2070897293 cites W2099404643 @default.
- W2070897293 cites W2099680095 @default.
- W2070897293 cites W2101483132 @default.
- W2070897293 cites W2105874735 @default.
- W2070897293 cites W2111309482 @default.
- W2070897293 cites W2121893797 @default.
- W2070897293 cites W2124556751 @default.
- W2070897293 cites W2126026097 @default.
- W2070897293 cites W2129232868 @default.
- W2070897293 cites W2131135493 @default.
- W2070897293 cites W2140375692 @default.
- W2070897293 cites W2142769604 @default.
- W2070897293 cites W2149234156 @default.
- W2070897293 cites W2150476673 @default.
- W2070897293 cites W2154786353 @default.
- W2070897293 cites W2159481344 @default.
- W2070897293 cites W2160241055 @default.
- W2070897293 cites W2160875256 @default.
- W2070897293 cites W2166536280 @default.
- W2070897293 cites W2166918318 @default.
- W2070897293 cites W2167101788 @default.
- W2070897293 cites W2170634604 @default.
- W2070897293 cites W4235447137 @default.
- W2070897293 cites W4235762625 @default.
- W2070897293 doi "https://doi.org/10.1145/2677036" @default.
- W2070897293 hasPublicationYear "2014" @default.
- W2070897293 type Work @default.
- W2070897293 sameAs 2070897293 @default.
- W2070897293 citedByCount "39" @default.
- W2070897293 countsByYear W20708972932015 @default.
- W2070897293 countsByYear W20708972932016 @default.
- W2070897293 countsByYear W20708972932017 @default.
- W2070897293 countsByYear W20708972932018 @default.
- W2070897293 countsByYear W20708972932019 @default.
- W2070897293 countsByYear W20708972932020 @default.
- W2070897293 countsByYear W20708972932021 @default.
- W2070897293 crossrefType "journal-article" @default.
- W2070897293 hasAuthorship W2070897293A5027001025 @default.
- W2070897293 hasAuthorship W2070897293A5028870701 @default.
- W2070897293 hasAuthorship W2070897293A5077188995 @default.
- W2070897293 hasBestOaLocation W20708972931 @default.
- W2070897293 hasConcept C111919701 @default.
- W2070897293 hasConcept C126831891 @default.
- W2070897293 hasConcept C13280743 @default.
- W2070897293 hasConcept C166957645 @default.
- W2070897293 hasConcept C169590947 @default.
- W2070897293 hasConcept C173608175 @default.
- W2070897293 hasConcept C177264268 @default.
- W2070897293 hasConcept C185798385 @default.
- W2070897293 hasConcept C18903297 @default.
- W2070897293 hasConcept C199360897 @default.
- W2070897293 hasConcept C205649164 @default.
- W2070897293 hasConcept C21442007 @default.
- W2070897293 hasConcept C2776760102 @default.
- W2070897293 hasConcept C2778119891 @default.
- W2070897293 hasConcept C41008148 @default.
- W2070897293 hasConcept C50630238 @default.
- W2070897293 hasConcept C78766204 @default.
- W2070897293 hasConcept C79581498 @default.
- W2070897293 hasConcept C86803240 @default.
- W2070897293 hasConcept C95457728 @default.
- W2070897293 hasConceptScore W2070897293C111919701 @default.
- W2070897293 hasConceptScore W2070897293C126831891 @default.
- W2070897293 hasConceptScore W2070897293C13280743 @default.
- W2070897293 hasConceptScore W2070897293C166957645 @default.
- W2070897293 hasConceptScore W2070897293C169590947 @default.
- W2070897293 hasConceptScore W2070897293C173608175 @default.
- W2070897293 hasConceptScore W2070897293C177264268 @default.
- W2070897293 hasConceptScore W2070897293C185798385 @default.
- W2070897293 hasConceptScore W2070897293C18903297 @default.