Toward Early Stage Dynamic Power Estimation: Exploring Alternative Machine Learning Methods and Simulation Schemes

Philipp Fengler, Sani Nassif, Ulf Schlichtmann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With power becoming the dominant limiter of advanced nm-scale designs, the need to make early and accurate predictions gains importance. Further, due to the dominance of interconnect in such designs, the impact of physical design decisions on power grows as well. However, performing detailed power estimation, including interconnect parasitics, can be time-consuming with current-generation EDA tools. In this paper, we evaluate the accuracy and efficiency of alternative approaches to power estimation that leverage machine learning techniques to bridge the gap first between simple and complex simulation schemes and second between logic level (pre-Physical Design) and physical level (post-Physical Design). We demonstrate that careful matching of simulation granularity and machine learning techniques can lead to a significant reduction in effort with only a modest degradation in accuracy.

Original languageEnglish
Title of host publicationProceedings of the 25th International Symposium on Quality Electronic Design, ISQED 2024
PublisherIEEE Computer Society
ISBN (Electronic)9798350309270
DOIs
StatePublished - 2024
Externally publishedYes
Event25th International Symposium on Quality Electronic Design, ISQED 2024 - Hybrid, San Francisco, United States
Duration: 3 Apr 20245 Apr 2024

Publication series

NameProceedings - International Symposium on Quality Electronic Design, ISQED
ISSN (Print)1948-3287
ISSN (Electronic)1948-3295

Conference

Conference25th International Symposium on Quality Electronic Design, ISQED 2024
Country/TerritoryUnited States
CityHybrid, San Francisco
Period3/04/245/04/24

Keywords

  • graph neural network
  • linear regression
  • power modeling
  • switching activity

Fingerprint

Dive into the research topics of 'Toward Early Stage Dynamic Power Estimation: Exploring Alternative Machine Learning Methods and Simulation Schemes'. Together they form a unique fingerprint.

Cite this