Matches in SemOpenAlex for { <https://semopenalex.org/work/W2270323267> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2270323267 abstract "Traditionally, programmers and software tools have focused on mapping a single data-parallel kernel onto a heterogeneous computing system consisting of multiple general-purpose processors (CPUS) and graphics processing units (GPUs). These methodologies break down as application complexity grows to contain multiple communicating data-parallel kernels. This paper introduces MKMD, an automatic system for mapping multiple kernels across multiple computing devices in a seamless manner. MKMD is a two phased approach that combines coarse grain scheduling of indivisible kernels followed by opportunistic fine-grained workgroup-level partitioning to exploit idle resources. During this process, MKMD considers kernel dependencies and the underlying systems along with the execution time model built with a few sets of profile data. With the scheduling decision, MKMD transparently manages the order of executions and data transfers for each device. On a real machine with one CPU and two different GPUs, MKMD achieves a mean speedup of 1.89x compared to the in-order execution on the fastest device for a set of applications with multiple kernels. 53% of this speedup comes from the coarse-grained scheduling and the other 47% is the result of the fine-grained partitioning." @default.
- W2270323267 created "2016-06-24" @default.
- W2270323267 creator A5002075773 @default.
- W2270323267 creator A5058642630 @default.
- W2270323267 creator A5065946847 @default.
- W2270323267 date "2015-10-01" @default.
- W2270323267 modified "2023-10-16" @default.
- W2270323267 title "Orchestrating Multiple Data-Parallel Kernels on Multiple Devices" @default.
- W2270323267 cites W1966623795 @default.
- W2270323267 cites W1971391208 @default.
- W2270323267 cites W2052172035 @default.
- W2270323267 cites W2101028855 @default.
- W2270323267 cites W2112340065 @default.
- W2270323267 cites W2118911512 @default.
- W2270323267 cites W2121893797 @default.
- W2270323267 cites W2122917953 @default.
- W2270323267 cites W2146757372 @default.
- W2270323267 cites W2149294210 @default.
- W2270323267 cites W2150476673 @default.
- W2270323267 cites W2153375074 @default.
- W2270323267 cites W2159456929 @default.
- W2270323267 cites W2165100134 @default.
- W2270323267 cites W2167101788 @default.
- W2270323267 cites W2169049902 @default.
- W2270323267 cites W2293085049 @default.
- W2270323267 cites W4240835555 @default.
- W2270323267 cites W4246166885 @default.
- W2270323267 cites W4253760721 @default.
- W2270323267 cites W4301906759 @default.
- W2270323267 doi "https://doi.org/10.1109/pact.2015.14" @default.
- W2270323267 hasPublicationYear "2015" @default.
- W2270323267 type Work @default.
- W2270323267 sameAs 2270323267 @default.
- W2270323267 citedByCount "18" @default.
- W2270323267 countsByYear W22703232672016 @default.
- W2270323267 countsByYear W22703232672017 @default.
- W2270323267 countsByYear W22703232672018 @default.
- W2270323267 countsByYear W22703232672019 @default.
- W2270323267 countsByYear W22703232672020 @default.
- W2270323267 countsByYear W22703232672021 @default.
- W2270323267 countsByYear W22703232672022 @default.
- W2270323267 countsByYear W22703232672023 @default.
- W2270323267 crossrefType "proceedings-article" @default.
- W2270323267 hasAuthorship W2270323267A5002075773 @default.
- W2270323267 hasAuthorship W2270323267A5058642630 @default.
- W2270323267 hasAuthorship W2270323267A5065946847 @default.
- W2270323267 hasConcept C111919701 @default.
- W2270323267 hasConcept C114614502 @default.
- W2270323267 hasConcept C120314980 @default.
- W2270323267 hasConcept C162324750 @default.
- W2270323267 hasConcept C165696696 @default.
- W2270323267 hasConcept C172430144 @default.
- W2270323267 hasConcept C173608175 @default.
- W2270323267 hasConcept C206729178 @default.
- W2270323267 hasConcept C21442007 @default.
- W2270323267 hasConcept C21547014 @default.
- W2270323267 hasConcept C2777904410 @default.
- W2270323267 hasConcept C33923547 @default.
- W2270323267 hasConcept C38652104 @default.
- W2270323267 hasConcept C41008148 @default.
- W2270323267 hasConcept C68339613 @default.
- W2270323267 hasConcept C74193536 @default.
- W2270323267 hasConceptScore W2270323267C111919701 @default.
- W2270323267 hasConceptScore W2270323267C114614502 @default.
- W2270323267 hasConceptScore W2270323267C120314980 @default.
- W2270323267 hasConceptScore W2270323267C162324750 @default.
- W2270323267 hasConceptScore W2270323267C165696696 @default.
- W2270323267 hasConceptScore W2270323267C172430144 @default.
- W2270323267 hasConceptScore W2270323267C173608175 @default.
- W2270323267 hasConceptScore W2270323267C206729178 @default.
- W2270323267 hasConceptScore W2270323267C21442007 @default.
- W2270323267 hasConceptScore W2270323267C21547014 @default.
- W2270323267 hasConceptScore W2270323267C2777904410 @default.
- W2270323267 hasConceptScore W2270323267C33923547 @default.
- W2270323267 hasConceptScore W2270323267C38652104 @default.
- W2270323267 hasConceptScore W2270323267C41008148 @default.
- W2270323267 hasConceptScore W2270323267C68339613 @default.
- W2270323267 hasConceptScore W2270323267C74193536 @default.
- W2270323267 hasLocation W22703232671 @default.
- W2270323267 hasOpenAccess W2270323267 @default.
- W2270323267 hasPrimaryLocation W22703232671 @default.
- W2270323267 hasRelatedWork W1509211761 @default.
- W2270323267 hasRelatedWork W1531488649 @default.
- W2270323267 hasRelatedWork W1585350690 @default.
- W2270323267 hasRelatedWork W1966344015 @default.
- W2270323267 hasRelatedWork W2074226157 @default.
- W2270323267 hasRelatedWork W2133693067 @default.
- W2270323267 hasRelatedWork W2366027386 @default.
- W2270323267 hasRelatedWork W2391299576 @default.
- W2270323267 hasRelatedWork W2582456645 @default.
- W2270323267 hasRelatedWork W3216598260 @default.
- W2270323267 isParatext "false" @default.
- W2270323267 isRetracted "false" @default.
- W2270323267 magId "2270323267" @default.
- W2270323267 workType "article" @default.