Matches in SemOpenAlex for { <https://semopenalex.org/work/W1595548352> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W1595548352 endingPage "131" @default.
- W1595548352 startingPage "116" @default.
- W1595548352 abstract "This paper introduces a method to generate efficient vectorized implementations of small stride permutations using only vector load and vector shuffle instructions. These permutations are crucial for highperformance numerical kernels including the fast Fourier transform. Our generator takes as input only the specification of the target platform's SIMD vector ISA and the desired permutation. The basic idea underlying our generator is to model vector instructions as matrices and sequences of vector instructions as matrix formulas using the Kronecker product formalism. We design a rewriting system and a search mechanism that applies matrix identities to generate those matrix formulas that have vector structure and minimize a cost measure that we define. The formula is then translated into the actual vector program for the specified permutation. For three important classes of permutations, we show that our method yields a solution with the minimal number of vector shuffles. Inserting into a fast Fourier transform yields a significant speedup." @default.
- W1595548352 created "2016-06-24" @default.
- W1595548352 creator A5062806943 @default.
- W1595548352 creator A5076407181 @default.
- W1595548352 date "2008-04-01" @default.
- W1595548352 modified "2023-09-23" @default.
- W1595548352 title "Generating SIMD Vectorized Permutations" @default.
- W1595548352 cites W1568228897 @default.
- W1595548352 cites W2015326607 @default.
- W1595548352 cites W2038945443 @default.
- W1595548352 cites W2045810654 @default.
- W1595548352 cites W2072277531 @default.
- W1595548352 cites W2134572726 @default.
- W1595548352 cites W2136952590 @default.
- W1595548352 cites W3021880308 @default.
- W1595548352 cites W4244894488 @default.
- W1595548352 cites W4245987756 @default.
- W1595548352 doi "https://doi.org/10.1007/978-3-540-78791-4_8" @default.
- W1595548352 hasPublicationYear "2008" @default.
- W1595548352 type Work @default.
- W1595548352 sameAs 1595548352 @default.
- W1595548352 citedByCount "18" @default.
- W1595548352 countsByYear W15955483522012 @default.
- W1595548352 countsByYear W15955483522014 @default.
- W1595548352 countsByYear W15955483522015 @default.
- W1595548352 countsByYear W15955483522018 @default.
- W1595548352 countsByYear W15955483522019 @default.
- W1595548352 countsByYear W15955483522020 @default.
- W1595548352 crossrefType "book-chapter" @default.
- W1595548352 hasAuthorship W1595548352A5062806943 @default.
- W1595548352 hasAuthorship W1595548352A5076407181 @default.
- W1595548352 hasBestOaLocation W15955483521 @default.
- W1595548352 hasConcept C150552126 @default.
- W1595548352 hasConcept C173608175 @default.
- W1595548352 hasConcept C41008148 @default.
- W1595548352 hasConceptScore W1595548352C150552126 @default.
- W1595548352 hasConceptScore W1595548352C173608175 @default.
- W1595548352 hasConceptScore W1595548352C41008148 @default.
- W1595548352 hasLocation W15955483521 @default.
- W1595548352 hasLocation W15955483522 @default.
- W1595548352 hasOpenAccess W1595548352 @default.
- W1595548352 hasPrimaryLocation W15955483521 @default.
- W1595548352 hasRelatedWork W1439745913 @default.
- W1595548352 hasRelatedWork W1496703677 @default.
- W1595548352 hasRelatedWork W1515082385 @default.
- W1595548352 hasRelatedWork W1584265037 @default.
- W1595548352 hasRelatedWork W1585350690 @default.
- W1595548352 hasRelatedWork W2008876287 @default.
- W1595548352 hasRelatedWork W2009882312 @default.
- W1595548352 hasRelatedWork W3005521981 @default.
- W1595548352 hasRelatedWork W3096209535 @default.
- W1595548352 hasRelatedWork W4245302940 @default.
- W1595548352 isParatext "false" @default.
- W1595548352 isRetracted "false" @default.
- W1595548352 magId "1595548352" @default.
- W1595548352 workType "book-chapter" @default.