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

arXiv: https://arxiv.org/abs/2003.00671 · HTML: https://mlsanity.com/paper/2003.00671/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research](https://mlsanity.com/paper/2109.08267/) (2021)
- [Compiler Optimization for Quantum Computing Using Reinforcement Learning](https://mlsanity.com/paper/2212.04508/) (2022)
- [BaCO: A Fast and Portable Bayesian Compiler Optimization Framework](https://mlsanity.com/paper/2212.11142/) (2022)
- [Learning Compiler Pass Orders using Coreset and Normalized Value Prediction](https://mlsanity.com/paper/2301.05104/) (2023)
- [Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces](https://mlsanity.com/paper/2410.15625/) (2024)
- [Compiler generated feedback for Large Language Models](https://mlsanity.com/paper/2403.14714/) (2024)
- [Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning](https://mlsanity.com/paper/2506.15701/) (2025)
- [Learning Space Partitions for Path Planning](https://mlsanity.com/paper/2106.10544/) (2021)
- [CompilerDream: Learning a Compiler World Model for General Code Optimization](https://mlsanity.com/paper/2404.16077/) (2024)
- [SuperCoder: Assembly Program Superoptimization with Large Language Models](https://mlsanity.com/paper/2505.11480/) (2025)
- [A Highly Configurable Hardware/Software Stack for DNN Inference Acceleration](https://mlsanity.com/paper/2111.15024/) (2021)
- [AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework](https://mlsanity.com/paper/2510.11759/) (2025)
- [A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler](https://mlsanity.com/paper/2409.11068/) (2024)
- [REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving](https://mlsanity.com/paper/2506.01374/) (2025)
- [BenchPress: A Deep Active Benchmark Generator](https://mlsanity.com/paper/2208.06555/) (2022)
- [X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation](https://mlsanity.com/paper/2304.14698/) (2023)
- [Target-independent XLA optimization using Reinforcement Learning](https://mlsanity.com/paper/2308.14364/) (2023)
- [CHEHAB RL: Learning to Optimize Fully Homomorphic Encryption Computations](https://mlsanity.com/paper/2601.19367/) (2026)
- [BenchDirect: A Directed Language Model for Compiler Benchmarks](https://mlsanity.com/paper/2303.01557/) (2023)
- [Towards VM Rescheduling Optimization Through Deep Reinforcement Learning](https://mlsanity.com/paper/2505.17359/) (2025)
- [Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction](https://mlsanity.com/paper/2510.13158/) (2025)
- [DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning](https://mlsanity.com/paper/2512.11342/) (2025)
- [LLM-Based Embeddings for Program Analysis and Optimization](https://mlsanity.com/paper/2608.07894/) (2026)

## Abstract (arXiv)

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.