Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376454311> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4376454311 endingPage "28" @default.
- W4376454311 startingPage "22" @default.
- W4376454311 abstract "The explosive growth of machine learning applications has consequently created a demand for high-performance implementations of tensor contractions, both for dense and sparse tensors. Compilers, code generators and libraries are often limited in what sparse tensor representations are supported. We observe that tensor contractions can be thought of as iterating over the elements of a sparse tensor to perform an operation and accumulation; co-iteration over multiple tensors can be implemented with iteration and lookup. We recognize that the resulting code can be restructured by specifying a computation, its data layout, and how to iterate over that. We illustrate the need for this generality with two different implementations of block-based data layouts implementing sparse matrix-vector multiplication (SpMV). We show how to generate these implementations with a tensor iterator abstraction designed to be integrated into the MLIR compiler, and present measurements of nearby manual implementations to demonstrate the tradeoffs and complexities with these different implementations." @default.
- W4376454311 created "2023-05-14" @default.
- W4376454311 creator A5030152493 @default.
- W4376454311 creator A5035445731 @default.
- W4376454311 creator A5082013692 @default.
- W4376454311 creator A5091933067 @default.
- W4376454311 creator A5091933068 @default.
- W4376454311 date "2023-01-01" @default.
- W4376454311 modified "2023-09-30" @default.
- W4376454311 title "Tensor Iterators for Flexible High-Performance Tensor Computation" @default.
- W4376454311 cites W1538707437 @default.
- W4376454311 cites W2111667319 @default.
- W4376454311 cites W2590246587 @default.
- W4376454311 cites W3122286897 @default.
- W4376454311 cites W4290648346 @default.
- W4376454311 cites W4293329542 @default.
- W4376454311 doi "https://doi.org/10.1007/978-3-031-31445-2_2" @default.
- W4376454311 hasPublicationYear "2023" @default.
- W4376454311 type Work @default.
- W4376454311 citedByCount "0" @default.
- W4376454311 crossrefType "book-chapter" @default.
- W4376454311 hasAuthorship W4376454311A5030152493 @default.
- W4376454311 hasAuthorship W4376454311A5035445731 @default.
- W4376454311 hasAuthorship W4376454311A5082013692 @default.
- W4376454311 hasAuthorship W4376454311A5091933067 @default.
- W4376454311 hasAuthorship W4376454311A5091933068 @default.
- W4376454311 hasConcept C111472728 @default.
- W4376454311 hasConcept C11413529 @default.
- W4376454311 hasConcept C121332964 @default.
- W4376454311 hasConcept C124304363 @default.
- W4376454311 hasConcept C138885662 @default.
- W4376454311 hasConcept C155281189 @default.
- W4376454311 hasConcept C15744967 @default.
- W4376454311 hasConcept C163716315 @default.
- W4376454311 hasConcept C169590947 @default.
- W4376454311 hasConcept C173608175 @default.
- W4376454311 hasConcept C199360897 @default.
- W4376454311 hasConcept C202444582 @default.
- W4376454311 hasConcept C2524010 @default.
- W4376454311 hasConcept C26713055 @default.
- W4376454311 hasConcept C2777210771 @default.
- W4376454311 hasConcept C2780767217 @default.
- W4376454311 hasConcept C33923547 @default.
- W4376454311 hasConcept C41008148 @default.
- W4376454311 hasConcept C45374587 @default.
- W4376454311 hasConcept C459310 @default.
- W4376454311 hasConcept C542102704 @default.
- W4376454311 hasConcept C56372850 @default.
- W4376454311 hasConcept C62520636 @default.
- W4376454311 hasConcept C80444323 @default.
- W4376454311 hasConceptScore W4376454311C111472728 @default.
- W4376454311 hasConceptScore W4376454311C11413529 @default.
- W4376454311 hasConceptScore W4376454311C121332964 @default.
- W4376454311 hasConceptScore W4376454311C124304363 @default.
- W4376454311 hasConceptScore W4376454311C138885662 @default.
- W4376454311 hasConceptScore W4376454311C155281189 @default.
- W4376454311 hasConceptScore W4376454311C15744967 @default.
- W4376454311 hasConceptScore W4376454311C163716315 @default.
- W4376454311 hasConceptScore W4376454311C169590947 @default.
- W4376454311 hasConceptScore W4376454311C173608175 @default.
- W4376454311 hasConceptScore W4376454311C199360897 @default.
- W4376454311 hasConceptScore W4376454311C202444582 @default.
- W4376454311 hasConceptScore W4376454311C2524010 @default.
- W4376454311 hasConceptScore W4376454311C26713055 @default.
- W4376454311 hasConceptScore W4376454311C2777210771 @default.
- W4376454311 hasConceptScore W4376454311C2780767217 @default.
- W4376454311 hasConceptScore W4376454311C33923547 @default.
- W4376454311 hasConceptScore W4376454311C41008148 @default.
- W4376454311 hasConceptScore W4376454311C45374587 @default.
- W4376454311 hasConceptScore W4376454311C459310 @default.
- W4376454311 hasConceptScore W4376454311C542102704 @default.
- W4376454311 hasConceptScore W4376454311C56372850 @default.
- W4376454311 hasConceptScore W4376454311C62520636 @default.
- W4376454311 hasConceptScore W4376454311C80444323 @default.
- W4376454311 hasLocation W43764543111 @default.
- W4376454311 hasOpenAccess W4376454311 @default.
- W4376454311 hasPrimaryLocation W43764543111 @default.
- W4376454311 hasRelatedWork W1504651774 @default.
- W4376454311 hasRelatedWork W1950440938 @default.
- W4376454311 hasRelatedWork W2141386061 @default.
- W4376454311 hasRelatedWork W2155203789 @default.
- W4376454311 hasRelatedWork W2532971843 @default.
- W4376454311 hasRelatedWork W3037701827 @default.
- W4376454311 hasRelatedWork W3093074049 @default.
- W4376454311 hasRelatedWork W4242922013 @default.
- W4376454311 hasRelatedWork W4287757231 @default.
- W4376454311 hasRelatedWork W4293195602 @default.
- W4376454311 isParatext "false" @default.
- W4376454311 isRetracted "false" @default.
- W4376454311 workType "book-chapter" @default.