Matches in SemOpenAlex for { <https://semopenalex.org/work/W2128120785> ?p ?o ?g. }
- W2128120785 abstract "Determining the best set of optimizations to apply to a kernel to be executed on the graphics processing unit (GPU) is a challenging problem. There are large sets of possible optimization configurations that can be applied, and many applications have multiple kernels. Each kernel may require a specific configuration to achieve the best performance, and moving an application to new hardware often requires a new optimization configuration for each kernel. In this work, we apply optimizations to GPU code using HMPP, a high-level directive-based language and source-to-source compiler that can generate CUDA / OpenCL code. However, programming with high-level languages may mean a loss of performance compared to using low-level languages. Our work shows that it is possible to improve the performance of a high-level language by using auto-tuning. We perform auto-tuning on a large optimization space on GPU kernels, focusing on loop permutation, loop unrolling, tiling, and specifying which loop(s) to parallelize, and show results on convolution kernels, codes in the PolyBench suite, and an implementation of belief propagation for stereo vision. The results show that our auto-tuned HMPP-generated implementations are significantly faster than the default HMPP implementation and can meet or exceed the performance of manually coded CUDA / OpenCL implementations." @default.
- W2128120785 created "2016-06-24" @default.
- W2128120785 creator A5014701179 @default.
- W2128120785 creator A5028727317 @default.
- W2128120785 creator A5030540477 @default.
- W2128120785 creator A5039304555 @default.
- W2128120785 creator A5058896802 @default.
- W2128120785 date "2012-05-01" @default.
- W2128120785 modified "2023-10-16" @default.
- W2128120785 title "Auto-tuning a high-level language targeted to GPU codes" @default.
- W2128120785 cites W1964031104 @default.
- W2128120785 cites W1967846636 @default.
- W2128120785 cites W1982733412 @default.
- W2128120785 cites W1992851788 @default.
- W2128120785 cites W2007451249 @default.
- W2128120785 cites W2021548416 @default.
- W2128120785 cites W2072277531 @default.
- W2128120785 cites W2083056254 @default.
- W2128120785 cites W2099625934 @default.
- W2128120785 cites W2107483876 @default.
- W2128120785 cites W2125277034 @default.
- W2128120785 cites W2128344236 @default.
- W2128120785 cites W2128539477 @default.
- W2128120785 cites W2129903625 @default.
- W2128120785 cites W2130289795 @default.
- W2128120785 cites W2136952590 @default.
- W2128120785 cites W2141331848 @default.
- W2128120785 cites W2146742876 @default.
- W2128120785 cites W2164197394 @default.
- W2128120785 cites W2165949176 @default.
- W2128120785 cites W2168242361 @default.
- W2128120785 cites W2997945685 @default.
- W2128120785 cites W4245206864 @default.
- W2128120785 cites W4246640573 @default.
- W2128120785 cites W4250700635 @default.
- W2128120785 cites W4251798485 @default.
- W2128120785 doi "https://doi.org/10.1109/inpar.2012.6339595" @default.
- W2128120785 hasPublicationYear "2012" @default.
- W2128120785 type Work @default.
- W2128120785 sameAs 2128120785 @default.
- W2128120785 citedByCount "300" @default.
- W2128120785 countsByYear W21281207852012 @default.
- W2128120785 countsByYear W21281207852013 @default.
- W2128120785 countsByYear W21281207852014 @default.
- W2128120785 countsByYear W21281207852015 @default.
- W2128120785 countsByYear W21281207852016 @default.
- W2128120785 countsByYear W21281207852017 @default.
- W2128120785 countsByYear W21281207852018 @default.
- W2128120785 countsByYear W21281207852019 @default.
- W2128120785 countsByYear W21281207852020 @default.
- W2128120785 countsByYear W21281207852021 @default.
- W2128120785 countsByYear W21281207852022 @default.
- W2128120785 countsByYear W21281207852023 @default.
- W2128120785 crossrefType "proceedings-article" @default.
- W2128120785 hasAuthorship W2128120785A5014701179 @default.
- W2128120785 hasAuthorship W2128120785A5028727317 @default.
- W2128120785 hasAuthorship W2128120785A5030540477 @default.
- W2128120785 hasAuthorship W2128120785A5039304555 @default.
- W2128120785 hasAuthorship W2128120785A5058896802 @default.
- W2128120785 hasBestOaLocation W21281207852 @default.
- W2128120785 hasConcept C111919701 @default.
- W2128120785 hasConcept C114614502 @default.
- W2128120785 hasConcept C169590947 @default.
- W2128120785 hasConcept C173608175 @default.
- W2128120785 hasConcept C199360897 @default.
- W2128120785 hasConcept C202491316 @default.
- W2128120785 hasConcept C21442007 @default.
- W2128120785 hasConcept C2778119891 @default.
- W2128120785 hasConcept C2779851693 @default.
- W2128120785 hasConcept C33923547 @default.
- W2128120785 hasConcept C41008148 @default.
- W2128120785 hasConcept C50630238 @default.
- W2128120785 hasConcept C74193536 @default.
- W2128120785 hasConcept C76970557 @default.
- W2128120785 hasConceptScore W2128120785C111919701 @default.
- W2128120785 hasConceptScore W2128120785C114614502 @default.
- W2128120785 hasConceptScore W2128120785C169590947 @default.
- W2128120785 hasConceptScore W2128120785C173608175 @default.
- W2128120785 hasConceptScore W2128120785C199360897 @default.
- W2128120785 hasConceptScore W2128120785C202491316 @default.
- W2128120785 hasConceptScore W2128120785C21442007 @default.
- W2128120785 hasConceptScore W2128120785C2778119891 @default.
- W2128120785 hasConceptScore W2128120785C2779851693 @default.
- W2128120785 hasConceptScore W2128120785C33923547 @default.
- W2128120785 hasConceptScore W2128120785C41008148 @default.
- W2128120785 hasConceptScore W2128120785C50630238 @default.
- W2128120785 hasConceptScore W2128120785C74193536 @default.
- W2128120785 hasConceptScore W2128120785C76970557 @default.
- W2128120785 hasLocation W21281207851 @default.
- W2128120785 hasLocation W21281207852 @default.
- W2128120785 hasOpenAccess W2128120785 @default.
- W2128120785 hasPrimaryLocation W21281207851 @default.
- W2128120785 hasRelatedWork W1678662003 @default.
- W2128120785 hasRelatedWork W2008492897 @default.
- W2128120785 hasRelatedWork W2063888806 @default.
- W2128120785 hasRelatedWork W2075046026 @default.
- W2128120785 hasRelatedWork W2104659803 @default.
- W2128120785 hasRelatedWork W2191246539 @default.
- W2128120785 hasRelatedWork W2755264124 @default.
- W2128120785 hasRelatedWork W2794923745 @default.