Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380366711> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4380366711 endingPage "102924" @default.
- W4380366711 startingPage "102924" @default.
- W4380366711 abstract "Hardware accelerated inference is a promising solution for exploiting graph convolutional networks (GCN) in latency-sensitive applications. Existing accelerators overlook an important barrier to widespread adoption: the input data (i.e., weighted graphs) of GCN inference diverge from scale and sparsity, causing the accelerators optimized for an array of graphs to lose efficiency on other graphs. This paper presents a reconfigurable GCN inference accelerator, VIDGCN, that switches between all possible GCN inference computation schemes to realize timely inference for all input graphs. VIDGCN incorporates an analytical performance model and a reconfigurable hardware design. The performance model allows users to find the optimal computation scheme for any given input graph. The hardware design reuses all the computation units under all computation schemes, and only distributes the data to the units in different ways. Evaluation on seven real-world graphs shows that VIDGCN outperforms state of the art, SGCNAX, by 1.79×, and consistently yields the ideal amount of memory accesses." @default.
- W4380366711 created "2023-06-13" @default.
- W4380366711 creator A5010726939 @default.
- W4380366711 creator A5013847859 @default.
- W4380366711 creator A5022262922 @default.
- W4380366711 creator A5022398389 @default.
- W4380366711 creator A5033955608 @default.
- W4380366711 creator A5038805650 @default.
- W4380366711 creator A5051170863 @default.
- W4380366711 creator A5078858975 @default.
- W4380366711 date "2023-08-01" @default.
- W4380366711 modified "2023-10-14" @default.
- W4380366711 title "VIDGCN: Embracing input data diversity with a configurable graph convolutional network accelerator" @default.
- W4380366711 cites W2027731328 @default.
- W4380366711 cites W2034861439 @default.
- W4380366711 cites W2162630660 @default.
- W4380366711 cites W2168190036 @default.
- W4380366711 cites W2794952988 @default.
- W4380366711 cites W2901504064 @default.
- W4380366711 cites W3016832937 @default.
- W4380366711 cites W3017228913 @default.
- W4380366711 cites W3046757167 @default.
- W4380366711 cites W3103168911 @default.
- W4380366711 cites W3105753905 @default.
- W4380366711 cites W3132695675 @default.
- W4380366711 cites W3157609068 @default.
- W4380366711 cites W3161042355 @default.
- W4380366711 cites W3200763437 @default.
- W4380366711 cites W3205727737 @default.
- W4380366711 cites W3206743063 @default.
- W4380366711 cites W4220721362 @default.
- W4380366711 cites W4226137788 @default.
- W4380366711 cites W4226439885 @default.
- W4380366711 cites W4285264230 @default.
- W4380366711 cites W4286371336 @default.
- W4380366711 doi "https://doi.org/10.1016/j.sysarc.2023.102924" @default.
- W4380366711 hasPublicationYear "2023" @default.
- W4380366711 type Work @default.
- W4380366711 citedByCount "0" @default.
- W4380366711 crossrefType "journal-article" @default.
- W4380366711 hasAuthorship W4380366711A5010726939 @default.
- W4380366711 hasAuthorship W4380366711A5013847859 @default.
- W4380366711 hasAuthorship W4380366711A5022262922 @default.
- W4380366711 hasAuthorship W4380366711A5022398389 @default.
- W4380366711 hasAuthorship W4380366711A5033955608 @default.
- W4380366711 hasAuthorship W4380366711A5038805650 @default.
- W4380366711 hasAuthorship W4380366711A5051170863 @default.
- W4380366711 hasAuthorship W4380366711A5078858975 @default.
- W4380366711 hasConcept C113775141 @default.
- W4380366711 hasConcept C11413529 @default.
- W4380366711 hasConcept C13164978 @default.
- W4380366711 hasConcept C132525143 @default.
- W4380366711 hasConcept C154945302 @default.
- W4380366711 hasConcept C173608175 @default.
- W4380366711 hasConcept C2776214188 @default.
- W4380366711 hasConcept C41008148 @default.
- W4380366711 hasConcept C42935608 @default.
- W4380366711 hasConcept C45374587 @default.
- W4380366711 hasConcept C76155785 @default.
- W4380366711 hasConcept C80444323 @default.
- W4380366711 hasConcept C82876162 @default.
- W4380366711 hasConcept C9390403 @default.
- W4380366711 hasConceptScore W4380366711C113775141 @default.
- W4380366711 hasConceptScore W4380366711C11413529 @default.
- W4380366711 hasConceptScore W4380366711C13164978 @default.
- W4380366711 hasConceptScore W4380366711C132525143 @default.
- W4380366711 hasConceptScore W4380366711C154945302 @default.
- W4380366711 hasConceptScore W4380366711C173608175 @default.
- W4380366711 hasConceptScore W4380366711C2776214188 @default.
- W4380366711 hasConceptScore W4380366711C41008148 @default.
- W4380366711 hasConceptScore W4380366711C42935608 @default.
- W4380366711 hasConceptScore W4380366711C45374587 @default.
- W4380366711 hasConceptScore W4380366711C76155785 @default.
- W4380366711 hasConceptScore W4380366711C80444323 @default.
- W4380366711 hasConceptScore W4380366711C82876162 @default.
- W4380366711 hasConceptScore W4380366711C9390403 @default.
- W4380366711 hasLocation W43803667111 @default.
- W4380366711 hasOpenAccess W4380366711 @default.
- W4380366711 hasPrimaryLocation W43803667111 @default.
- W4380366711 hasRelatedWork W2067951144 @default.
- W4380366711 hasRelatedWork W2776940252 @default.
- W4380366711 hasRelatedWork W2997106510 @default.
- W4380366711 hasRelatedWork W3038662377 @default.
- W4380366711 hasRelatedWork W4226275939 @default.
- W4380366711 hasRelatedWork W4318348488 @default.
- W4380366711 hasRelatedWork W4321192172 @default.
- W4380366711 hasRelatedWork W4322776108 @default.
- W4380366711 hasRelatedWork W4378806073 @default.
- W4380366711 hasRelatedWork W4380136464 @default.
- W4380366711 hasVolume "141" @default.
- W4380366711 isParatext "false" @default.
- W4380366711 isRetracted "false" @default.
- W4380366711 workType "article" @default.