# AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1901.04615 · HTML: https://mlsanity.com/paper/1901.04615/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2019.

## Built on by (most cited first, 12 of 12)

- [Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve](https://mlsanity.com/paper/2601.21096/) (2026)
- [Learning to Combine Instructions in LLVM Compiler](https://mlsanity.com/paper/2202.12379/) (2022)
- [RL4ReAl: Reinforcement Learning for Register Allocation](https://mlsanity.com/paper/2204.02013/) (2022)
- [Generating GPU Compiler Heuristics using Reinforcement Learning](https://mlsanity.com/paper/2111.12055/) (2021)
- [A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler](https://mlsanity.com/paper/2409.11068/) (2024)
- [POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning](https://mlsanity.com/paper/2208.04238/) (2022)
- [SEER: Super-Optimization Explorer for HLS using E-graph Rewriting with MLIR](https://mlsanity.com/paper/2308.07654/) (2023)
- [Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering](https://mlsanity.com/paper/2602.06142/) (2026)
- [AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning](https://mlsanity.com/paper/2606.20373/) (2026)
- [ML-driven Hardware Cost Model for MLIR](https://mlsanity.com/paper/2302.11405/) (2023)
- [The Next 700 ML-Enabled Compiler Optimizations](https://mlsanity.com/paper/2311.10800/) (2023)
- [A Deep Learning Model for Predicting Transformation Legality](https://mlsanity.com/paper/2511.06120/) (2025)

## Abstract (arXiv)

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.