AutoPhase: Compiler Phase-Ordering for HLS with Deep Reinforcement Learning

Qijing Huang, Ameer Haj-Ali, William Moses, John Xiang, Ion Stoica, Krste Asanovic, John Wawrzynek

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The performance of the code generated by a compiler depends on the order in which the optimization passes are applied. In high-level synthesis, the quality of the generated circuit relates directly to the code generated by the front-end compiler. Choosing a good order-often referred to as the phase-ordering problem-is an NP-hard problem. In this paper, we evaluate a new technique to address the phase-ordering problem: deep reinforcement learning. We implement a framework in the context of the LLVM compiler to optimize the ordering for HLS programs and compare the performance of deep reinforcement learning to state-of-The-Art algorithms that address the phase-ordering problem. Overall, our framework runs one to two orders of magnitude faster than these algorithms, and achieves a 16% improvement in circuit performance over the-O3 compiler flag.

Original languageEnglish (US)
Title of host publicationProceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages308
Number of pages1
ISBN (Electronic)9781728111315
DOIs
StatePublished - Apr 2019
Externally publishedYes
Event27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019 - San Diego, United States
Duration: Apr 28 2019May 1 2019

Publication series

NameProceedings - 27th IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019

Conference

Conference27th Annual IEEE International Symposium on Field-Programmable Custom Computing Machines, FCCM 2019
Country/TerritoryUnited States
CitySan Diego
Period4/28/195/1/19

Keywords

  • Compiler
  • Deep Reinforcement Learning
  • HLS
  • Phase Ordering

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'AutoPhase: Compiler Phase-Ordering for HLS with Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this