Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160369968> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3160369968 abstract "Deep Learning Processor Unit (DPU) from XILINX is among the numerous accelerators that have been proposed to speed up the execution of Convolutional Neural Networks (CNNs) on embedded platforms. DPUs are available in different configurable sizes and can execute any given CNN. Neural network researchers are also rapidly bringing out newer CNN algorithms with improved performance (typically higher prediction accuracy) with a trade-off in size or energy consumption for embedded applications. To enable quick evaluation of choices among evolving CNN algorithms and accelerator configurations, we propose INFER (INterFerence-aware Estimation of Runtime). INFER is a framework to estimate the execution time of any CNN on a given size of DPU without actual implementation. Further, current FPGA platforms are capable of implementing multiple DPUs whereas many applications consist of multiple sub-tasks with each requiring separate and/or different CNNs. In such scenarios of concurrent use of multiple DPUs on an FPGA, INFER is also capable of estimating the additional time taken for execution due to the sharing of memory bandwidth. Our evaluation on various mixes of 16 standard CNNs and eight configurations of DPU shows that INFER has an average prediction error of 6.6%, which can be useful for design space exploration as well as scheduling in multi-DPU platforms." @default.
- W3160369968 created "2021-05-24" @default.
- W3160369968 creator A5013807519 @default.
- W3160369968 creator A5024148539 @default.
- W3160369968 creator A5074675503 @default.
- W3160369968 creator A5083734260 @default.
- W3160369968 date "2020-12-01" @default.
- W3160369968 modified "2023-09-30" @default.
- W3160369968 title "INFER: INterFerence-aware Estimation of Runtime for Concurrent CNN Execution on DPUs" @default.
- W3160369968 cites W2276486856 @default.
- W3160369968 cites W2616014673 @default.
- W3160369968 cites W2946425846 @default.
- W3160369968 cites W2962822620 @default.
- W3160369968 cites W2963163009 @default.
- W3160369968 cites W2965973489 @default.
- W3160369968 cites W2997106510 @default.
- W3160369968 cites W3013366513 @default.
- W3160369968 cites W3061070527 @default.
- W3160369968 cites W3100638618 @default.
- W3160369968 cites W3102169921 @default.
- W3160369968 doi "https://doi.org/10.1109/icfpt51103.2020.00018" @default.
- W3160369968 hasPublicationYear "2020" @default.
- W3160369968 type Work @default.
- W3160369968 sameAs 3160369968 @default.
- W3160369968 citedByCount "7" @default.
- W3160369968 countsByYear W31603699682021 @default.
- W3160369968 countsByYear W31603699682022 @default.
- W3160369968 countsByYear W31603699682023 @default.
- W3160369968 crossrefType "proceedings-article" @default.
- W3160369968 hasAuthorship W3160369968A5013807519 @default.
- W3160369968 hasAuthorship W3160369968A5024148539 @default.
- W3160369968 hasAuthorship W3160369968A5074675503 @default.
- W3160369968 hasAuthorship W3160369968A5083734260 @default.
- W3160369968 hasConcept C113775141 @default.
- W3160369968 hasConcept C120314980 @default.
- W3160369968 hasConcept C149635348 @default.
- W3160369968 hasConcept C154945302 @default.
- W3160369968 hasConcept C162324750 @default.
- W3160369968 hasConcept C206729178 @default.
- W3160369968 hasConcept C21547014 @default.
- W3160369968 hasConcept C2776221188 @default.
- W3160369968 hasConcept C2776257435 @default.
- W3160369968 hasConcept C2989134064 @default.
- W3160369968 hasConcept C31258907 @default.
- W3160369968 hasConcept C41008148 @default.
- W3160369968 hasConcept C42935608 @default.
- W3160369968 hasConcept C50644808 @default.
- W3160369968 hasConcept C81363708 @default.
- W3160369968 hasConceptScore W3160369968C113775141 @default.
- W3160369968 hasConceptScore W3160369968C120314980 @default.
- W3160369968 hasConceptScore W3160369968C149635348 @default.
- W3160369968 hasConceptScore W3160369968C154945302 @default.
- W3160369968 hasConceptScore W3160369968C162324750 @default.
- W3160369968 hasConceptScore W3160369968C206729178 @default.
- W3160369968 hasConceptScore W3160369968C21547014 @default.
- W3160369968 hasConceptScore W3160369968C2776221188 @default.
- W3160369968 hasConceptScore W3160369968C2776257435 @default.
- W3160369968 hasConceptScore W3160369968C2989134064 @default.
- W3160369968 hasConceptScore W3160369968C31258907 @default.
- W3160369968 hasConceptScore W3160369968C41008148 @default.
- W3160369968 hasConceptScore W3160369968C42935608 @default.
- W3160369968 hasConceptScore W3160369968C50644808 @default.
- W3160369968 hasConceptScore W3160369968C81363708 @default.
- W3160369968 hasLocation W31603699681 @default.
- W3160369968 hasOpenAccess W3160369968 @default.
- W3160369968 hasPrimaryLocation W31603699681 @default.
- W3160369968 hasRelatedWork W1882733036 @default.
- W3160369968 hasRelatedWork W1992741870 @default.
- W3160369968 hasRelatedWork W2160425906 @default.
- W3160369968 hasRelatedWork W2295680811 @default.
- W3160369968 hasRelatedWork W2524802307 @default.
- W3160369968 hasRelatedWork W2546696010 @default.
- W3160369968 hasRelatedWork W2787803743 @default.
- W3160369968 hasRelatedWork W3003304268 @default.
- W3160369968 hasRelatedWork W3147787617 @default.
- W3160369968 hasRelatedWork W4285708690 @default.
- W3160369968 isParatext "false" @default.
- W3160369968 isRetracted "false" @default.
- W3160369968 magId "3160369968" @default.
- W3160369968 workType "article" @default.