Matches in SemOpenAlex for { <https://semopenalex.org/work/W2787450728> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2787450728 endingPage "229" @default.
- W2787450728 startingPage "218" @default.
- W2787450728 abstract "The problem of partitioning dense matrices into sets of sub-matrices has received increased attention recently and is crucial when considering dense linear algebra and kernels with similar communication patterns on heterogeneous platforms. The problem of load balancing and minimizing communication is traditionally reducible to an optimization problem that involves partitioning a square into rectangles. This problem has been proven to be NP-Complete for an arbitrary number of partitions. In this paper, we present recent approaches that relax the restriction that all partitions be rectangles. The first approach uses an original mathematical technique to find the exact optimal partitioning. Due to the complexity of the technique, it has been developed for a small number of partitions only. However, even at a small scale, the optimal partitions found by this approach are often non-rectangular and sometimes non-intuitive. The second approach is the study of approximate partitioning methods utilizing recursive partitioning algorithms. In particular we use the work on optimal partitioning to improve pre-existing algorithms. In this paper we discuss the different perspectives this approach opens and present two algorithms, SNRPP which is a <inline-formula> <tex-math notation=LaTeX>$sqrt{frac{3}{2}}$</tex-math></inline-formula> approximation, and NRPP which is a <inline-formula><tex-math notation=LaTeX>$frac{2}{sqrt{3}}$</tex-math></inline-formula> approximation. While sub-optimal, the NRRP approach works for an arbitrary number of partitions. We use the first exact approach to analyse how close to the known optimal solutions the NRRP algorithm is for small numbers of partitions." @default.
- W2787450728 created "2018-02-23" @default.
- W2787450728 creator A5025268386 @default.
- W2787450728 creator A5028817761 @default.
- W2787450728 creator A5054692443 @default.
- W2787450728 creator A5069193596 @default.
- W2787450728 creator A5083569548 @default.
- W2787450728 creator A5084068586 @default.
- W2787450728 date "2019-01-01" @default.
- W2787450728 modified "2023-10-18" @default.
- W2787450728 title "Recent Advances in Matrix Partitioning for Parallel Computing on Heterogeneous Platforms" @default.
- W2787450728 cites W1494149077 @default.
- W2787450728 cites W1889647973 @default.
- W2787450728 cites W1979087811 @default.
- W2787450728 cites W2014953934 @default.
- W2787450728 cites W2020714618 @default.
- W2787450728 cites W2022146928 @default.
- W2787450728 cites W2051880204 @default.
- W2787450728 cites W2062065632 @default.
- W2787450728 cites W2067052471 @default.
- W2787450728 cites W2087085699 @default.
- W2787450728 cites W2087440962 @default.
- W2787450728 cites W2104373803 @default.
- W2787450728 cites W2104779926 @default.
- W2787450728 cites W2121893797 @default.
- W2787450728 cites W2144854112 @default.
- W2787450728 cites W2148090428 @default.
- W2787450728 cites W2154750565 @default.
- W2787450728 cites W2160556361 @default.
- W2787450728 cites W2478462544 @default.
- W2787450728 cites W4231150350 @default.
- W2787450728 doi "https://doi.org/10.1109/tpds.2018.2853151" @default.
- W2787450728 hasPublicationYear "2019" @default.
- W2787450728 type Work @default.
- W2787450728 sameAs 2787450728 @default.
- W2787450728 citedByCount "16" @default.
- W2787450728 countsByYear W27874507282019 @default.
- W2787450728 countsByYear W27874507282020 @default.
- W2787450728 countsByYear W27874507282021 @default.
- W2787450728 countsByYear W27874507282023 @default.
- W2787450728 crossrefType "journal-article" @default.
- W2787450728 hasAuthorship W2787450728A5025268386 @default.
- W2787450728 hasAuthorship W2787450728A5028817761 @default.
- W2787450728 hasAuthorship W2787450728A5054692443 @default.
- W2787450728 hasAuthorship W2787450728A5069193596 @default.
- W2787450728 hasAuthorship W2787450728A5083569548 @default.
- W2787450728 hasAuthorship W2787450728A5084068586 @default.
- W2787450728 hasBestOaLocation W27874507282 @default.
- W2787450728 hasConcept C106487976 @default.
- W2787450728 hasConcept C114614502 @default.
- W2787450728 hasConcept C118615104 @default.
- W2787450728 hasConcept C159985019 @default.
- W2787450728 hasConcept C192562407 @default.
- W2787450728 hasConcept C33923547 @default.
- W2787450728 hasConcept C41008148 @default.
- W2787450728 hasConcept C45357846 @default.
- W2787450728 hasConcept C94375191 @default.
- W2787450728 hasConceptScore W2787450728C106487976 @default.
- W2787450728 hasConceptScore W2787450728C114614502 @default.
- W2787450728 hasConceptScore W2787450728C118615104 @default.
- W2787450728 hasConceptScore W2787450728C159985019 @default.
- W2787450728 hasConceptScore W2787450728C192562407 @default.
- W2787450728 hasConceptScore W2787450728C33923547 @default.
- W2787450728 hasConceptScore W2787450728C41008148 @default.
- W2787450728 hasConceptScore W2787450728C45357846 @default.
- W2787450728 hasConceptScore W2787450728C94375191 @default.
- W2787450728 hasFunder F4320320366 @default.
- W2787450728 hasFunder F4320320847 @default.
- W2787450728 hasIssue "1" @default.
- W2787450728 hasLocation W27874507281 @default.
- W2787450728 hasLocation W27874507282 @default.
- W2787450728 hasLocation W27874507283 @default.
- W2787450728 hasLocation W27874507284 @default.
- W2787450728 hasLocation W27874507285 @default.
- W2787450728 hasOpenAccess W2787450728 @default.
- W2787450728 hasPrimaryLocation W27874507281 @default.
- W2787450728 hasRelatedWork W1587224694 @default.
- W2787450728 hasRelatedWork W1979597421 @default.
- W2787450728 hasRelatedWork W2007980826 @default.
- W2787450728 hasRelatedWork W2061531152 @default.
- W2787450728 hasRelatedWork W2077600819 @default.
- W2787450728 hasRelatedWork W2142036596 @default.
- W2787450728 hasRelatedWork W2911598644 @default.
- W2787450728 hasRelatedWork W3002753104 @default.
- W2787450728 hasRelatedWork W4225152035 @default.
- W2787450728 hasRelatedWork W4245490552 @default.
- W2787450728 hasVolume "30" @default.
- W2787450728 isParatext "false" @default.
- W2787450728 isRetracted "false" @default.
- W2787450728 magId "2787450728" @default.
- W2787450728 workType "article" @default.