Matches in SemOpenAlex for { <https://semopenalex.org/work/W3046480212> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3046480212 abstract "Automated tuning of compute kernels is a popular area of research, mainly focused on finding optimal kernel parameters for a problem with fixed input sizes. This approach is good for deploying machine learning models, where the network topology is constant, but machine learning research often involves changing network topologies and hyperparameters. Traditional kernel auto-tuning has limited impact in this case; a more general selection of kernels is required for libraries to accelerate machine learning research. In this paper we present initial results using machine learning to select kernels in a case study deploying high performance SYCL kernels in libraries that target a range of heterogeneous devices from desktop GPUs to embedded accelerators. The techniques investigated apply more generally and could similarly be integrated with other heterogeneous programming systems. By combining auto-tuning and machine learning these kernel selection processes can be deployed with little developer effort to achieve high performance on new hardware." @default.
- W3046480212 created "2020-08-07" @default.
- W3046480212 creator A5007551404 @default.
- W3046480212 date "2020-05-01" @default.
- W3046480212 modified "2023-09-27" @default.
- W3046480212 title "Towards automated kernel selection in machine learning systems: A SYCL case study" @default.
- W3046480212 cites W151377110 @default.
- W3046480212 cites W1863336885 @default.
- W3046480212 cites W1997614470 @default.
- W3046480212 cites W2004683477 @default.
- W3046480212 cites W2016618963 @default.
- W3046480212 cites W2033088400 @default.
- W3046480212 cites W2107483876 @default.
- W3046480212 cites W2125027820 @default.
- W3046480212 cites W2194775991 @default.
- W3046480212 cites W2294798173 @default.
- W3046480212 cites W2887327791 @default.
- W3046480212 cites W2963163009 @default.
- W3046480212 cites W3102753670 @default.
- W3046480212 cites W3103983137 @default.
- W3046480212 cites W3105204543 @default.
- W3046480212 cites W3105362906 @default.
- W3046480212 cites W3144750446 @default.
- W3046480212 doi "https://doi.org/10.1109/ipdpsw50202.2020.00086" @default.
- W3046480212 hasPublicationYear "2020" @default.
- W3046480212 type Work @default.
- W3046480212 sameAs 3046480212 @default.
- W3046480212 citedByCount "2" @default.
- W3046480212 countsByYear W30464802122020 @default.
- W3046480212 countsByYear W30464802122023 @default.
- W3046480212 crossrefType "proceedings-article" @default.
- W3046480212 hasAuthorship W3046480212A5007551404 @default.
- W3046480212 hasBestOaLocation W30464802122 @default.
- W3046480212 hasConcept C111919701 @default.
- W3046480212 hasConcept C114614502 @default.
- W3046480212 hasConcept C119857082 @default.
- W3046480212 hasConcept C122280245 @default.
- W3046480212 hasConcept C12267149 @default.
- W3046480212 hasConcept C140417398 @default.
- W3046480212 hasConcept C154945302 @default.
- W3046480212 hasConcept C160446489 @default.
- W3046480212 hasConcept C199845137 @default.
- W3046480212 hasConcept C33923547 @default.
- W3046480212 hasConcept C41008148 @default.
- W3046480212 hasConcept C74193536 @default.
- W3046480212 hasConcept C81917197 @default.
- W3046480212 hasConcept C8642999 @default.
- W3046480212 hasConceptScore W3046480212C111919701 @default.
- W3046480212 hasConceptScore W3046480212C114614502 @default.
- W3046480212 hasConceptScore W3046480212C119857082 @default.
- W3046480212 hasConceptScore W3046480212C122280245 @default.
- W3046480212 hasConceptScore W3046480212C12267149 @default.
- W3046480212 hasConceptScore W3046480212C140417398 @default.
- W3046480212 hasConceptScore W3046480212C154945302 @default.
- W3046480212 hasConceptScore W3046480212C160446489 @default.
- W3046480212 hasConceptScore W3046480212C199845137 @default.
- W3046480212 hasConceptScore W3046480212C33923547 @default.
- W3046480212 hasConceptScore W3046480212C41008148 @default.
- W3046480212 hasConceptScore W3046480212C74193536 @default.
- W3046480212 hasConceptScore W3046480212C81917197 @default.
- W3046480212 hasConceptScore W3046480212C8642999 @default.
- W3046480212 hasLocation W30464802121 @default.
- W3046480212 hasLocation W30464802122 @default.
- W3046480212 hasOpenAccess W3046480212 @default.
- W3046480212 hasPrimaryLocation W30464802121 @default.
- W3046480212 hasRelatedWork W1028655896 @default.
- W3046480212 hasRelatedWork W1535136526 @default.
- W3046480212 hasRelatedWork W1932525473 @default.
- W3046480212 hasRelatedWork W1983263273 @default.
- W3046480212 hasRelatedWork W2028245348 @default.
- W3046480212 hasRelatedWork W2071570209 @default.
- W3046480212 hasRelatedWork W2092483655 @default.
- W3046480212 hasRelatedWork W2130792056 @default.
- W3046480212 hasRelatedWork W3100948281 @default.
- W3046480212 hasRelatedWork W3123056048 @default.
- W3046480212 isParatext "false" @default.
- W3046480212 isRetracted "false" @default.
- W3046480212 magId "3046480212" @default.
- W3046480212 workType "article" @default.