Matches in SemOpenAlex for { <https://semopenalex.org/work/W2601646251> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2601646251 endingPage "3686" @default.
- W2601646251 startingPage "3675" @default.
- W2601646251 abstract "Emotion-aware computing can recognize, interpret, process, and simulate human affects. These programs in this area are compute-intensive applications, so they need to be executed in parallel. Loops usually have regular structures and programs spend significant amounts of time executing them, and thus loops are ideal candidates for exploiting the parallelism of sequential programs. However, it is difficult to decide which set of loops should be parallelized to improve program performance. The existing research is one-size-fits-all strategy and cannot guarantee to select profitable loops to be parallelized. This paper proposes a novel loop selection approach based on machine learning (ML-based) for selecting the profitable loops and paralleling them on multi-core by speculative multithreading (SpMT). It includes establishing sufficient training examples, building and applying prediction model to select profitable loops for speculative parallelization. Using the ML-based loop selection approach, an unseen emotion-aware sequential program can obtain a stable, much higher speedup than the one-size-fits-all approach. On Prophet, which is a generic SpMT processor to evaluate the performance of multithreaded programs, the novel loop selection approach is evaluated and reaches an average speedup of 1.87 on a 4-core processor. Experiment results show that the ML-based approach can obtain a significant increase in speedup, and Olden benchmarks deliver a better performance improvement of 6.70% on a 4-core than the one-size-fits-all approach." @default.
- W2601646251 created "2017-04-07" @default.
- W2601646251 creator A5032341976 @default.
- W2601646251 creator A5044062811 @default.
- W2601646251 creator A5084868970 @default.
- W2601646251 creator A5087981019 @default.
- W2601646251 creator A5091044298 @default.
- W2601646251 date "2017-01-01" @default.
- W2601646251 modified "2023-10-14" @default.
- W2601646251 title "Toward Emotion-Aware Computing: A Loop Selection Approach Based on Machine Learning for Speculative Multithreading" @default.
- W2601646251 cites W1979593478 @default.
- W2601646251 cites W1990386838 @default.
- W2601646251 cites W1996958605 @default.
- W2601646251 cites W1997524219 @default.
- W2601646251 cites W2016764587 @default.
- W2601646251 cites W2023128081 @default.
- W2601646251 cites W2023274306 @default.
- W2601646251 cites W2023832055 @default.
- W2601646251 cites W2028157367 @default.
- W2601646251 cites W2028297439 @default.
- W2601646251 cites W2033785728 @default.
- W2601646251 cites W2034886984 @default.
- W2601646251 cites W2043815962 @default.
- W2601646251 cites W2059145255 @default.
- W2601646251 cites W2059434253 @default.
- W2601646251 cites W2077208126 @default.
- W2601646251 cites W2091030628 @default.
- W2601646251 cites W2125340270 @default.
- W2601646251 cites W2156904680 @default.
- W2601646251 cites W2184902314 @default.
- W2601646251 cites W2266199501 @default.
- W2601646251 cites W2277897549 @default.
- W2601646251 cites W2282906402 @default.
- W2601646251 cites W2314318090 @default.
- W2601646251 cites W2478490256 @default.
- W2601646251 cites W2517682081 @default.
- W2601646251 cites W2525221147 @default.
- W2601646251 doi "https://doi.org/10.1109/access.2017.2684129" @default.
- W2601646251 hasPublicationYear "2017" @default.
- W2601646251 type Work @default.
- W2601646251 sameAs 2601646251 @default.
- W2601646251 citedByCount "7" @default.
- W2601646251 countsByYear W26016462512017 @default.
- W2601646251 countsByYear W26016462512019 @default.
- W2601646251 countsByYear W26016462512021 @default.
- W2601646251 countsByYear W26016462512022 @default.
- W2601646251 crossrefType "journal-article" @default.
- W2601646251 hasAuthorship W2601646251A5032341976 @default.
- W2601646251 hasAuthorship W2601646251A5044062811 @default.
- W2601646251 hasAuthorship W2601646251A5084868970 @default.
- W2601646251 hasAuthorship W2601646251A5087981019 @default.
- W2601646251 hasAuthorship W2601646251A5091044298 @default.
- W2601646251 hasBestOaLocation W26016462511 @default.
- W2601646251 hasConcept C114614502 @default.
- W2601646251 hasConcept C119857082 @default.
- W2601646251 hasConcept C138101251 @default.
- W2601646251 hasConcept C15296174 @default.
- W2601646251 hasConcept C154945302 @default.
- W2601646251 hasConcept C184670325 @default.
- W2601646251 hasConcept C199360897 @default.
- W2601646251 hasConcept C201410400 @default.
- W2601646251 hasConcept C33923547 @default.
- W2601646251 hasConcept C41008148 @default.
- W2601646251 hasConcept C81917197 @default.
- W2601646251 hasConceptScore W2601646251C114614502 @default.
- W2601646251 hasConceptScore W2601646251C119857082 @default.
- W2601646251 hasConceptScore W2601646251C138101251 @default.
- W2601646251 hasConceptScore W2601646251C15296174 @default.
- W2601646251 hasConceptScore W2601646251C154945302 @default.
- W2601646251 hasConceptScore W2601646251C184670325 @default.
- W2601646251 hasConceptScore W2601646251C199360897 @default.
- W2601646251 hasConceptScore W2601646251C201410400 @default.
- W2601646251 hasConceptScore W2601646251C33923547 @default.
- W2601646251 hasConceptScore W2601646251C41008148 @default.
- W2601646251 hasConceptScore W2601646251C81917197 @default.
- W2601646251 hasFunder F4320321001 @default.
- W2601646251 hasFunder F4320335787 @default.
- W2601646251 hasLocation W26016462511 @default.
- W2601646251 hasOpenAccess W2601646251 @default.
- W2601646251 hasPrimaryLocation W26016462511 @default.
- W2601646251 hasRelatedWork W108320310 @default.
- W2601646251 hasRelatedWork W1546628085 @default.
- W2601646251 hasRelatedWork W1567437828 @default.
- W2601646251 hasRelatedWork W1982011377 @default.
- W2601646251 hasRelatedWork W2010221388 @default.
- W2601646251 hasRelatedWork W2056713726 @default.
- W2601646251 hasRelatedWork W2169001628 @default.
- W2601646251 hasRelatedWork W2379604274 @default.
- W2601646251 hasRelatedWork W4242439656 @default.
- W2601646251 hasRelatedWork W4297694376 @default.
- W2601646251 hasVolume "5" @default.
- W2601646251 isParatext "false" @default.
- W2601646251 isRetracted "false" @default.
- W2601646251 magId "2601646251" @default.
- W2601646251 workType "article" @default.