Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307641039> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4307641039 endingPage "22" @default.
- W4307641039 startingPage "1" @default.
- W4307641039 abstract "Modern electronic design automation flows depend on both implementation and signoff tools to perform timing-constrained power optimization through Engineering Change Orders (ECOs), which involve gate sizing and threshold-voltage ( V th )-assignment of standard cells. However, the signoff ECO optimization is highly time-consuming, and the power improvement is hard to predict in advance. Ever since the industrial benchmarks released by the ISPD-2012 gate-sizing contest, active research has been conducted extensively to improve the optimization process. Nonetheless, previous works were mostly based on heuristics or analytical methods whose timing models were oversimplified and lacked of formal validations from commercial signoff tools. In this article, we propose ECO-graph neural networks (GNN), a transferable graph-learning-based framework, which harnesses GNNs to perform commercial-quality signoff power optimization through discrete ( V th -assignment. One of the highlights of our framework is that it generates tool-accurate optimization results instantly on unseen netlists that are not utilized in the training process. Furthermore, we propose a subgraph approximation technique to improve training and inferencing time of the proposed GNN model. We show that design instances with non-overlapping subgraphs can be optimized in parallel so as to improve the inference time of the learning-based model. Finally, we implement a GNN-based explanation method to interpret the optimization results achieved by our framework. Experimental results on 14 industrial designs, including a RISC-V-based multi-core system and the renowned ISPD-2012 benchmarks, demonstrate that our framework achieves up to 14× runtime improvement with similar signoff power optimization quality compared with Synopsys PrimeTime , an industry-leading signoff tool." @default.
- W4307641039 created "2022-11-04" @default.
- W4307641039 creator A5015819338 @default.
- W4307641039 creator A5021997733 @default.
- W4307641039 creator A5031945601 @default.
- W4307641039 creator A5089860537 @default.
- W4307641039 date "2023-05-17" @default.
- W4307641039 modified "2023-09-30" @default.
- W4307641039 title "ECO-GNN: Signoff Power Prediction Using Graph Neural Networks with Subgraph Approximation" @default.
- W4307641039 cites W1948792255 @default.
- W4307641039 cites W1972928733 @default.
- W4307641039 cites W1974368829 @default.
- W4307641039 cites W1993828091 @default.
- W4307641039 cites W1999291149 @default.
- W4307641039 cites W2003474320 @default.
- W4307641039 cites W2100905943 @default.
- W4307641039 cites W2131909792 @default.
- W4307641039 cites W2132233398 @default.
- W4307641039 cites W2143022706 @default.
- W4307641039 cites W2148995793 @default.
- W4307641039 cites W2167482691 @default.
- W4307641039 cites W2172629440 @default.
- W4307641039 cites W2894034160 @default.
- W4307641039 cites W2945592068 @default.
- W4307641039 cites W2998496395 @default.
- W4307641039 cites W3111098492 @default.
- W4307641039 cites W3112618461 @default.
- W4307641039 cites W3127834963 @default.
- W4307641039 cites W3152893301 @default.
- W4307641039 cites W3188917597 @default.
- W4307641039 cites W4205829060 @default.
- W4307641039 cites W4213191016 @default.
- W4307641039 doi "https://doi.org/10.1145/3569942" @default.
- W4307641039 hasPublicationYear "2023" @default.
- W4307641039 type Work @default.
- W4307641039 citedByCount "0" @default.
- W4307641039 crossrefType "journal-article" @default.
- W4307641039 hasAuthorship W4307641039A5015819338 @default.
- W4307641039 hasAuthorship W4307641039A5021997733 @default.
- W4307641039 hasAuthorship W4307641039A5031945601 @default.
- W4307641039 hasAuthorship W4307641039A5089860537 @default.
- W4307641039 hasBestOaLocation W43076410391 @default.
- W4307641039 hasConcept C111919701 @default.
- W4307641039 hasConcept C113775141 @default.
- W4307641039 hasConcept C119857082 @default.
- W4307641039 hasConcept C121332964 @default.
- W4307641039 hasConcept C127705205 @default.
- W4307641039 hasConcept C132525143 @default.
- W4307641039 hasConcept C142362112 @default.
- W4307641039 hasConcept C153349607 @default.
- W4307641039 hasConcept C154945302 @default.
- W4307641039 hasConcept C163258240 @default.
- W4307641039 hasConcept C168292644 @default.
- W4307641039 hasConcept C2776214188 @default.
- W4307641039 hasConcept C2777767291 @default.
- W4307641039 hasConcept C2984118289 @default.
- W4307641039 hasConcept C41008148 @default.
- W4307641039 hasConcept C50644808 @default.
- W4307641039 hasConcept C62520636 @default.
- W4307641039 hasConcept C80444323 @default.
- W4307641039 hasConcept C98045186 @default.
- W4307641039 hasConceptScore W4307641039C111919701 @default.
- W4307641039 hasConceptScore W4307641039C113775141 @default.
- W4307641039 hasConceptScore W4307641039C119857082 @default.
- W4307641039 hasConceptScore W4307641039C121332964 @default.
- W4307641039 hasConceptScore W4307641039C127705205 @default.
- W4307641039 hasConceptScore W4307641039C132525143 @default.
- W4307641039 hasConceptScore W4307641039C142362112 @default.
- W4307641039 hasConceptScore W4307641039C153349607 @default.
- W4307641039 hasConceptScore W4307641039C154945302 @default.
- W4307641039 hasConceptScore W4307641039C163258240 @default.
- W4307641039 hasConceptScore W4307641039C168292644 @default.
- W4307641039 hasConceptScore W4307641039C2776214188 @default.
- W4307641039 hasConceptScore W4307641039C2777767291 @default.
- W4307641039 hasConceptScore W4307641039C2984118289 @default.
- W4307641039 hasConceptScore W4307641039C41008148 @default.
- W4307641039 hasConceptScore W4307641039C50644808 @default.
- W4307641039 hasConceptScore W4307641039C62520636 @default.
- W4307641039 hasConceptScore W4307641039C80444323 @default.
- W4307641039 hasConceptScore W4307641039C98045186 @default.
- W4307641039 hasIssue "4" @default.
- W4307641039 hasLocation W43076410391 @default.
- W4307641039 hasOpenAccess W4307641039 @default.
- W4307641039 hasPrimaryLocation W43076410391 @default.
- W4307641039 hasRelatedWork W1984367069 @default.
- W4307641039 hasRelatedWork W2047815652 @default.
- W4307641039 hasRelatedWork W2087782335 @default.
- W4307641039 hasRelatedWork W2131215816 @default.
- W4307641039 hasRelatedWork W2140617575 @default.
- W4307641039 hasRelatedWork W2355108509 @default.
- W4307641039 hasRelatedWork W2599457842 @default.
- W4307641039 hasRelatedWork W3017292264 @default.
- W4307641039 hasRelatedWork W3149032315 @default.
- W4307641039 hasRelatedWork W4229971373 @default.
- W4307641039 hasVolume "28" @default.
- W4307641039 isParatext "false" @default.
- W4307641039 isRetracted "false" @default.
- W4307641039 workType "article" @default.