# CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research

arXiv: https://arxiv.org/abs/2109.08267 · HTML: https://mlsanity.com/paper/2109.08267/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [A Survey of Machine Learning for Big Code and Naturalness](https://mlsanity.com/paper/1709.06182/) (2017)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](https://mlsanity.com/paper/2007.00708/) (2020)
- [Improving Generalization in Reinforcement Learning with Mixture Regularization](https://mlsanity.com/paper/2010.10814/) (2020)
- [Neural Code Comprehension: A Learnable Representation of Code Semantics](https://mlsanity.com/paper/1806.07336/) (2018)
- [A Geometric Perspective on Optimal Representations for Reinforcement Learning](https://mlsanity.com/paper/1901.11530/) (2019)
- [Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks](https://mlsanity.com/paper/1808.07412/) (2018)
- [A Survey on Compiler Autotuning using Machine Learning](https://mlsanity.com/paper/1801.04405/) (2018)
- [MLGO: a Machine Learning Guided Compiler Optimizations Framework](https://mlsanity.com/paper/2101.04808/) (2021)
- [NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning](https://mlsanity.com/paper/1909.13639/) (2019)
- [AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00671/) (2020)
- [Static Neural Compiler Optimization via Deep Reinforcement Learning](https://mlsanity.com/paper/2008.08951/) (2020)
- [A Reinforcement Learning Environment for Polyhedral Optimizations](https://mlsanity.com/paper/2104.13732/) (2021)
- [A Collaborative Filtering Approach for the Automatic Tuning of Compiler Optimisations](https://mlsanity.com/paper/2005.04092/) (2020)
- [Learning to Make Compiler Optimizations More Effective](https://mlsanity.com/paper/2102.13514/) (2021)
- [LS-CAT: A Large-Scale CUDA AutoTuning Dataset](https://mlsanity.com/paper/2103.14409/) (2021)
- [Collective Tuning Initiative](https://mlsanity.com/paper/1407.3487/) (2014)

## Built on by (most cited first, 30 of 41)

- [Large Language Models for Compiler Optimization](https://mlsanity.com/paper/2309.07062/) (2023)
- [Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://mlsanity.com/paper/2407.02524/) (2024)
- [TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs](https://mlsanity.com/paper/2308.13490/) (2023)
- [Autocomp: A Powerful and Portable Code Optimizer for Tensor Accelerators](https://mlsanity.com/paper/2505.18574/) (2025)
- [Learning Compiler Pass Orders using Coreset and Normalized Value Prediction](https://mlsanity.com/paper/2301.05104/) (2023)
- [MLGOPerf: An ML Guided Inliner to Optimize Performance](https://mlsanity.com/paper/2207.08389/) (2022)
- [Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning](https://mlsanity.com/paper/2506.15701/) (2025)
- [Reinforcement Learning in Practice: Opportunities and Challenges](https://mlsanity.com/paper/2202.11296/) (2022)
- [ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design](https://mlsanity.com/paper/2306.08888/) (2023)
- [CompilerDream: Learning a Compiler World Model for General Code Optimization](https://mlsanity.com/paper/2404.16077/) (2024)
- [Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation](https://mlsanity.com/paper/2201.05587/) (2022)
- [qgym: A Gym for Training and Benchmarking RL-Based Quantum Compilation](https://mlsanity.com/paper/2308.02536/) (2023)
- [Magellan: Autonomous Discovery of Novel Compiler Optimization Heuristics with AlphaEvolve](https://mlsanity.com/paper/2601.21096/) (2026)
- [RL4ReAl: Reinforcement Learning for Register Allocation](https://mlsanity.com/paper/2204.02013/) (2022)
- [AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework](https://mlsanity.com/paper/2510.11759/) (2025)
- [PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis](https://mlsanity.com/paper/2306.00210/) (2023)
- [A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler](https://mlsanity.com/paper/2409.11068/) (2024)
- [Agentic Harness for Real-World Compilers](https://mlsanity.com/paper/2603.20075/) (2026)
- [Profile Guided Optimization without Profiles: A Machine Learning Approach](https://mlsanity.com/paper/2112.14679/) (2021)
- [BenchPress: A Deep Active Benchmark Generator](https://mlsanity.com/paper/2208.06555/) (2022)
- [CATBench: A Compiler Autotuning Benchmarking Suite for Black-box Optimization](https://mlsanity.com/paper/2406.17811/) (2024)
- [Target-independent XLA optimization using Reinforcement Learning](https://mlsanity.com/paper/2308.14364/) (2023)
- [LoopTune: Optimizing Tensor Computations with Reinforcement Learning](https://mlsanity.com/paper/2309.01825/) (2023)
- [DiTOX: Fault Detection and Localization in the ONNX Optimizer](https://mlsanity.com/paper/2505.01892/) (2025)
- [Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering](https://mlsanity.com/paper/2602.06142/) (2026)
- [Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search](https://mlsanity.com/paper/2604.11109/) (2026)
- [PassNet: Scaling Large Language Models for Graph Compiler Pass Generation](https://mlsanity.com/paper/2605.29357/) (2026)
- [AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning](https://mlsanity.com/paper/2606.20373/) (2026)
- [Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence](https://mlsanity.com/paper/2609.35432/) (2026)
- [BenchDirect: A Directed Language Model for Compiler Benchmarks](https://mlsanity.com/paper/2303.01557/) (2023)

## Abstract (arXiv)

Interest in applying Artificial Intelligence (AI) techniques to compiler optimizations is increasing rapidly, but compiler research has a high entry barrier. Unlike in other domains, compiler and AI researchers do not have access to the datasets and frameworks that enable fast iteration and development of ideas, and getting started requires a significant engineering investment. What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field. We introduce CompilerGym, a set of environments for real world compiler optimization tasks, and a toolkit for exposing new optimization tasks to compiler researchers. CompilerGym enables anyone to experiment on production compiler optimization problems through an easy-to-use package, regardless of their experience with compilers. We build upon the popular OpenAI Gym interface enabling researchers to interact with compilers using Python and a familiar API. We describe the CompilerGym architecture and implementation, characterize the optimization spaces and computational efficiencies of three included compiler environments, and provide extensive empirical evaluations. Compared to prior works, CompilerGym offers larger datasets and optimization spaces, is 27x more computationally efficient, is fault-tolerant, and capable of detecting reproducibility bugs in the underlying compilers. In making it easy for anyone to experiment with compilers - irrespective of their background - we aim to accelerate progress in the AI and compiler research domains.