Matches in SemOpenAlex for { <https://semopenalex.org/work/W3127834963> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3127834963 abstract "Static power consumption is a critical challenge for IC designs, particularly for mobile and IoT applications. A final post-layout step in modern design flows involves a leakage recovery step that is embedded in signoff static timing analysis tools. The goal of such recovery is to make use of the positive slack (if any) and recover the leakage power by performing cell swaps with footprint compatible variants. Though such swaps result in unaltered routing, the hard constraint is not to introduce any new timing violations. This process can require up to tens of hours of runtime, just before the tapeout, when schedule and resource constraints are tightest. The physical design teams can benefit greatly from a fast predictor of the leakage recovery step: if the eventual recovery will be too small, the entire step can be skipped, and the resources can be allocated elsewhere. If we represent the circuit netlist as a graph with cells as vertices and nets connecting these cells as edges, the leakage recovery step is an optimization step, on this graph. If we can learn these optimizations over several graphs with various logic-cone structures, we can generalize the learning to unseen graphs. Using graph convolution neural networks, we develop a learning-based model, that predicts per-cell recoverable slack, and translate these slack values to equivalent power savings. For designs up to 1.6M instances, our inference step takes less than 12 seconds on a Tesla P100 GPU, and an additional feature extraction, post-processing steps consuming 420 seconds. The model is accurate with relative error under 6.2%, for the design-specific context." @default.
- W3127834963 created "2021-02-15" @default.
- W3127834963 creator A5039615312 @default.
- W3127834963 creator A5085478560 @default.
- W3127834963 date "2021-01-18" @default.
- W3127834963 modified "2023-10-01" @default.
- W3127834963 title "GRA-LPO" @default.
- W3127834963 cites W1997411420 @default.
- W3127834963 cites W1999291149 @default.
- W3127834963 cites W2003474320 @default.
- W3127834963 cites W2005653503 @default.
- W3127834963 cites W2040498220 @default.
- W3127834963 cites W2100905943 @default.
- W3127834963 cites W2120773999 @default.
- W3127834963 cites W2132178096 @default.
- W3127834963 cites W2148292098 @default.
- W3127834963 cites W2911181151 @default.
- W3127834963 cites W2944916746 @default.
- W3127834963 cites W2963165299 @default.
- W3127834963 cites W4205829060 @default.
- W3127834963 cites W4231119589 @default.
- W3127834963 doi "https://doi.org/10.1145/3394885.3431574" @default.
- W3127834963 hasPublicationYear "2021" @default.
- W3127834963 type Work @default.
- W3127834963 sameAs 3127834963 @default.
- W3127834963 citedByCount "5" @default.
- W3127834963 countsByYear W31278349632022 @default.
- W3127834963 countsByYear W31278349632023 @default.
- W3127834963 crossrefType "proceedings-article" @default.
- W3127834963 hasAuthorship W3127834963A5039615312 @default.
- W3127834963 hasAuthorship W3127834963A5085478560 @default.
- W3127834963 hasBestOaLocation W31278349631 @default.
- W3127834963 hasConcept C113775141 @default.
- W3127834963 hasConcept C11413529 @default.
- W3127834963 hasConcept C126255220 @default.
- W3127834963 hasConcept C149635348 @default.
- W3127834963 hasConcept C154945302 @default.
- W3127834963 hasConcept C173608175 @default.
- W3127834963 hasConcept C177650935 @default.
- W3127834963 hasConcept C206729178 @default.
- W3127834963 hasConcept C2776214188 @default.
- W3127834963 hasConcept C33923547 @default.
- W3127834963 hasConcept C41008148 @default.
- W3127834963 hasConceptScore W3127834963C113775141 @default.
- W3127834963 hasConceptScore W3127834963C11413529 @default.
- W3127834963 hasConceptScore W3127834963C126255220 @default.
- W3127834963 hasConceptScore W3127834963C149635348 @default.
- W3127834963 hasConceptScore W3127834963C154945302 @default.
- W3127834963 hasConceptScore W3127834963C173608175 @default.
- W3127834963 hasConceptScore W3127834963C177650935 @default.
- W3127834963 hasConceptScore W3127834963C206729178 @default.
- W3127834963 hasConceptScore W3127834963C2776214188 @default.
- W3127834963 hasConceptScore W3127834963C33923547 @default.
- W3127834963 hasConceptScore W3127834963C41008148 @default.
- W3127834963 hasLocation W31278349631 @default.
- W3127834963 hasOpenAccess W3127834963 @default.
- W3127834963 hasPrimaryLocation W31278349631 @default.
- W3127834963 hasRelatedWork W1509211761 @default.
- W3127834963 hasRelatedWork W1558545464 @default.
- W3127834963 hasRelatedWork W1984303163 @default.
- W3127834963 hasRelatedWork W2074301136 @default.
- W3127834963 hasRelatedWork W2117014006 @default.
- W3127834963 hasRelatedWork W2358725432 @default.
- W3127834963 hasRelatedWork W2372170743 @default.
- W3127834963 hasRelatedWork W3047022145 @default.
- W3127834963 hasRelatedWork W4233815414 @default.
- W3127834963 hasRelatedWork W99847340 @default.
- W3127834963 isParatext "false" @default.
- W3127834963 isRetracted "false" @default.
- W3127834963 magId "3127834963" @default.
- W3127834963 workType "article" @default.