Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385585454> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4385585454 abstract "High performance and on-time calculations of Machine Learning (ML) algorithms are essential for emerging technologies such as autonomous driving, Internet of Things (IoT) or edge computing. One of the major algorithms used in such systems is Convolutional Neural Networks (CNNs), which require high computational resources. That leads designers to leverage ML accelerators like GPGPUs to meet design constraints. However, selecting the most appropriate accelerator requires Design Space Exploration (DSE), which is usually time-consuming and needs high manual effort. In this paper, we present a novel automated approach, enabling designers to fast and accurately estimate the performance of CNNs for GPGPUs in the early stage of the design process. The proposed approach uses static analysis for feature extraction and Decision Tree regression analysis for the performance estimation model. Experimental results demonstrate that our approach can predict CNNs performance with an absolute percentage error of 5.73% compared to the actual hardware." @default.
- W4385585454 created "2023-08-05" @default.
- W4385585454 creator A5071742136 @default.
- W4385585454 creator A5086748944 @default.
- W4385585454 creator A5088510932 @default.
- W4385585454 date "2023-05-01" @default.
- W4385585454 modified "2023-09-25" @default.
- W4385585454 title "Fast and Accurate: Machine Learning Techniques for Performance Estimation of CNNs for GPGPUs" @default.
- W4385585454 cites W1979527452 @default.
- W4385585454 cites W2038666141 @default.
- W4385585454 cites W2213612645 @default.
- W4385585454 cites W2531409750 @default.
- W4385585454 cites W2946408574 @default.
- W4385585454 cites W3037110041 @default.
- W4385585454 cites W3102476541 @default.
- W4385585454 cites W3115175310 @default.
- W4385585454 cites W3132987155 @default.
- W4385585454 cites W3157708976 @default.
- W4385585454 cites W3203257953 @default.
- W4385585454 cites W3204029214 @default.
- W4385585454 cites W3213539149 @default.
- W4385585454 cites W4252743600 @default.
- W4385585454 doi "https://doi.org/10.1109/ipdpsw59300.2023.00127" @default.
- W4385585454 hasPublicationYear "2023" @default.
- W4385585454 type Work @default.
- W4385585454 citedByCount "0" @default.
- W4385585454 crossrefType "proceedings-article" @default.
- W4385585454 hasAuthorship W4385585454A5071742136 @default.
- W4385585454 hasAuthorship W4385585454A5086748944 @default.
- W4385585454 hasAuthorship W4385585454A5088510932 @default.
- W4385585454 hasConcept C111919701 @default.
- W4385585454 hasConcept C113775141 @default.
- W4385585454 hasConcept C119857082 @default.
- W4385585454 hasConcept C153083717 @default.
- W4385585454 hasConcept C154945302 @default.
- W4385585454 hasConcept C162307627 @default.
- W4385585454 hasConcept C2778456923 @default.
- W4385585454 hasConcept C41008148 @default.
- W4385585454 hasConcept C50644808 @default.
- W4385585454 hasConcept C52622490 @default.
- W4385585454 hasConcept C81363708 @default.
- W4385585454 hasConcept C84525736 @default.
- W4385585454 hasConcept C98045186 @default.
- W4385585454 hasConceptScore W4385585454C111919701 @default.
- W4385585454 hasConceptScore W4385585454C113775141 @default.
- W4385585454 hasConceptScore W4385585454C119857082 @default.
- W4385585454 hasConceptScore W4385585454C153083717 @default.
- W4385585454 hasConceptScore W4385585454C154945302 @default.
- W4385585454 hasConceptScore W4385585454C162307627 @default.
- W4385585454 hasConceptScore W4385585454C2778456923 @default.
- W4385585454 hasConceptScore W4385585454C41008148 @default.
- W4385585454 hasConceptScore W4385585454C50644808 @default.
- W4385585454 hasConceptScore W4385585454C52622490 @default.
- W4385585454 hasConceptScore W4385585454C81363708 @default.
- W4385585454 hasConceptScore W4385585454C84525736 @default.
- W4385585454 hasConceptScore W4385585454C98045186 @default.
- W4385585454 hasLocation W43855854541 @default.
- W4385585454 hasOpenAccess W4385585454 @default.
- W4385585454 hasPrimaryLocation W43855854541 @default.
- W4385585454 hasRelatedWork W1470425429 @default.
- W4385585454 hasRelatedWork W2602506882 @default.
- W4385585454 hasRelatedWork W2913302899 @default.
- W4385585454 hasRelatedWork W3021430260 @default.
- W4385585454 hasRelatedWork W3027997911 @default.
- W4385585454 hasRelatedWork W3185179407 @default.
- W4385585454 hasRelatedWork W4205478082 @default.
- W4385585454 hasRelatedWork W4287776258 @default.
- W4385585454 hasRelatedWork W4318350883 @default.
- W4385585454 hasRelatedWork W4328134586 @default.
- W4385585454 isParatext "false" @default.
- W4385585454 isRetracted "false" @default.
- W4385585454 workType "article" @default.