AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning

TL;DR

AutoPhase employs deep reinforcement learning to optimize compiler pass sequences, significantly improving code performance and generalizing well across diverse programs by intelligently reducing the search space.

Contribution

This paper introduces AutoPhase, a novel framework that applies deep reinforcement learning to the phase-ordering problem in compilers, leveraging random forests for efficient search space reduction.

Findings

AutoPhase improves circuit performance by 28% over -O3.

It achieves competitive results with fewer samples than existing methods.

AutoPhase generalizes effectively to real benchmarks and numerous random programs.

Abstract

The performance of the code a compiler generates depends on the order in which it applies the optimization passes. Choosing a good order--often referred to as the phase-ordering problem, is an NP-hard problem. As a result, existing solutions rely on a variety of heuristics. In this paper, we evaluate a new technique to address the phase-ordering problem: deep reinforcement learning. To this end, we implement AutoPhase: a framework that takes a program and uses deep reinforcement learning to find a sequence of compilation passes that minimizes its execution time. Without loss of generality, we construct this framework in the context of the LLVM compiler toolchain and target high-level synthesis programs. We use random forests to quantify the correlation between the effectiveness of a given pass and the program's features. This helps us reduce the search space by avoiding phase orderings that are unlikely to improve the performance of a given program. We compare the performance of AutoPhase to state-of-the-art algorithms that address the phase-ordering problem. In our evaluation, we show that AutoPhase improves circuit performance by 28% when compared to using the -O3 compiler flag, and achieves competitive results compared to the state-of-the-art solutions, while requiring fewer samples. Furthermore, unlike existing state-of-the-art solutions, our deep reinforcement learning solution shows promising result in generalizing to real benchmarks and 12,874 different randomly generated programs, after training on a hundred randomly generated programs.