The Art of Beating the Odds with Predictor-Guided Random Design Space Exploration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Arnold, Felix, Bouvier, Maxence, Amaudruz, Ryan, Andri, Renzo, Cavigelli, Lukas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909571133472768
author Arnold, Felix
Bouvier, Maxence
Amaudruz, Ryan
Andri, Renzo
Cavigelli, Lukas
author_facet Arnold, Felix
Bouvier, Maxence
Amaudruz, Ryan
Andri, Renzo
Cavigelli, Lukas
contents This work introduces an innovative method for improving combinational digital circuits through random exploration in MIG-based synthesis. High-quality circuits are crucial for performance, power, and cost, making this a critical area of active research. Our approach incorporates next-state prediction and iterative selection, significantly accelerating the synthesis process. This novel method achieves up to 14x synthesis speedup and up to 20.94% better MIG minimization on the EPFL Combinational Benchmark Suite compared to state-of-the-art techniques. We further explore various predictor models and show that increased prediction accuracy does not guarantee an equivalent increase in synthesis quality of results or speedup, observing that randomness remains a desirable factor.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17936
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Art of Beating the Odds with Predictor-Guided Random Design Space Exploration
Arnold, Felix
Bouvier, Maxence
Amaudruz, Ryan
Andri, Renzo
Cavigelli, Lukas
Machine Learning
Hardware Architecture
This work introduces an innovative method for improving combinational digital circuits through random exploration in MIG-based synthesis. High-quality circuits are crucial for performance, power, and cost, making this a critical area of active research. Our approach incorporates next-state prediction and iterative selection, significantly accelerating the synthesis process. This novel method achieves up to 14x synthesis speedup and up to 20.94% better MIG minimization on the EPFL Combinational Benchmark Suite compared to state-of-the-art techniques. We further explore various predictor models and show that increased prediction accuracy does not guarantee an equivalent increase in synthesis quality of results or speedup, observing that randomness remains a desirable factor.
title The Art of Beating the Odds with Predictor-Guided Random Design Space Exploration
topic Machine Learning
Hardware Architecture
url https://arxiv.org/abs/2502.17936