EUVIMEDEUVIMED entdecken
Crossref

FlowTune: End-to-End Automatic Logic Optimization Exploration via Domain-Specific Multiarmed Bandit

Walter Lau Neto, Yingjie Li, Pierre-Emmanuel Gaillardon, Cunxi Yu

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · 2023-06 · 42 (6) · 1912-1925

DOI: 10.1109/tcad.2022.3213611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023-06. Verfasst von Walter Lau Neto und 3 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Science Foundation, DARPA IDEA, NSF CAREER.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Design flows are the explicit combinations of design transformations, primarily involved in synthesis, placement, and routing processes, to accomplish the design of integrated circuits (ICs) and system-on-chip (SoC). Mostly, the flows are developed based on the knowledge of the experts. However, due to the large search space of design flows and the increasing design complexity, developing intellectual property (IP)-specific synthesis flows providing high quality of result (QoR) is extremely challenging. In recent years, machine learning (ML) has been increasingly used in electronic design automation (EDA), with the goal of reducing manual labor and speeding up the design closure process in current toolflows. Existing techniques, on the other hand, either necessitate a huge amount of labeled data and time-consuming training, or are constrained in terms of practical EDA toolflow integration due to computational overhead. This article presents a generic end-to-end sequential decision making framework FlowTune for synthesis tooflow optimization, with a novel high-performance domain-specific, multistage multiarmed bandit (MAB) approach. This framework addresses a wide range of optimization problems on Boolean optimization problems, such as And-Inv-Graphs (AIGs), conjunction normal form (CNF) minimization (# clauses) for Boolean satisfiability; logic synthesis and technology mapping, and, more importantly, end-to-end post place-and-route (PnR) optimizations. Moreover, we demonstrate the high extensibility and generalizability of the proposed domain-specific MAB approach with end-to-end FPGA design flow, evaluated at post-routing stage, with two different FPGA backend tools (OpenFPGA and VPR) and two different logic synthesis representations [AIGs and Majority-Inv-Graph (MIG)]. FlowTune is fully integrated with ABC (Mishchenko et al., 2010), Yosys (Wolf, 2016), VTR (Luu et al., 2014), LSOracle (Neto et al., 2019), OpenFPGA (Tang et al., 2019), and industrial tools, and is released publicly. The experimental results conducted on various design stages in the flow all demonstrate that our framework outperforms both handcrafted flows (Mishchenko et al., 2010) and ML explored flows (Yu et al., 2018), (Hosny et al., 2019) in QoRs, and is orders of magnitude faster compared to ML-based approaches.

Förderung

  • National Science Foundation
  • DARPA IDEA
  • NSF CAREER

Zitieren

APA

Neto, W. L., Li, Y., Gaillardon, P., & Yu, C. (2023). FlowTune: End-to-End Automatic Logic Optimization Exploration via Domain-Specific Multiarmed Bandit. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 42(6), 1912-1925. https://doi.org/10.1109/tcad.2022.3213611

Vancouver

Neto WL, Li Y, Gaillardon P, Yu C. FlowTune: End-to-End Automatic Logic Optimization Exploration via Domain-Specific Multiarmed Bandit. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2023;42(6):1912-1925. doi:10.1109/tcad.2022.3213611

BibTeX
@article{Neto2023,
  author = {Neto, Walter Lau and Li, Yingjie and Gaillardon, Pierre-Emmanuel and Yu, Cunxi},
  title = {FlowTune: End-to-End Automatic Logic Optimization Exploration via Domain-Specific Multiarmed Bandit},
  journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
  year = {2023},
  volume = {42},
  number = {6},
  pages = {1912--1925},
  doi = {10.1109/tcad.2022.3213611}
}
Kostenlos starten →