# Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration

arXiv: https://arxiv.org/abs/2501.17168 · HTML: https://mlsanity.com/paper/2501.17168/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 74 references that are in the map.
- First posted on arXiv 21 Jan 2025.

## Builds on (most cited first, 17 of 17)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [Contemporary Symbolic Regression Methods and their Relative Performance](https://mlsanity.com/paper/2107.14351/) (2021)
- [Interpretable Scientific Discovery with Symbolic Regression: A Review](https://mlsanity.com/paper/2211.10873/) (2022)
- [Interpretable Policies for Reinforcement Learning by Genetic Programming](https://mlsanity.com/paper/1712.04170/) (2017)
- [evosax: JAX-based Evolution Strategies](https://mlsanity.com/paper/2212.04180/) (2022)
- [EvoJAX: Hardware-Accelerated Neuroevolution](https://mlsanity.com/paper/2202.05008/) (2022)
- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation](https://mlsanity.com/paper/2301.12457/) (2023)
- [EvoTorch: Scalable Evolutionary Computation in Python](https://mlsanity.com/paper/2302.12600/) (2023)
- [Taskflow: A Lightweight Parallel and Heterogeneous Task Graph Computing System](https://mlsanity.com/paper/2004.10908/) (2020)
- [TensorFlow Enabled Genetic Programming](https://mlsanity.com/paper/1708.03157/) (2017)
- [TensorGP -- Genetic Programming Engine in TensorFlow](https://mlsanity.com/paper/2103.07512/) (2021)
- [Tensorized NeuroEvolution of Augmenting Topologies for GPU Acceleration](https://mlsanity.com/paper/2404.01817/) (2024)
- [GPU-accelerated Evolutionary Multiobjective Optimization Using Tensorized RVEA](https://mlsanity.com/paper/2404.01159/) (2024)

## Built on by (most cited first, 4 of 4)

- [Kozax: Flexible and Scalable Genetic Programming in JAX](https://mlsanity.com/paper/2502.03047/) (2025)
- [Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic Programming](https://mlsanity.com/paper/2609.03352/) (2026)
- [TNLearn: An Open Source Python Package for Task-based Neurons](https://mlsanity.com/paper/2609.27564/) (2026)
- [MorphingNet: Symbolic Regression Where the Network Is the Formula](https://mlsanity.com/paper/2610.19942/) (2026)

## Abstract (arXiv)

Tree-based Genetic Programming (TGP) is a widely used evolutionary algorithm for tasks such as symbolic regression, classification, and robotic control. Due to the intensive computational demands of running TGP, GPU acceleration is crucial for achieving scalable performance. However, efficient GPU-based execution of TGP remains challenging, primarily due to three core issues: (1) the structural heterogeneity of program individuals, (2) the complexity of integrating multiple levels of parallelism, and (3) the incompatibility between high-performance CUDA execution and flexible Python-based environments. To address these issues, we propose EvoGP, a high-performance framework tailored for GPU acceleration of TGP via population-level parallel execution. First, EvoGP introduces a tensorized representation that encodes variable-sized trees into fixed-shape, memory-aligned arrays, enabling uniform memory access and parallel computation across diverse individuals. Second, EvoGP adopts an adaptive parallelism strategy that dynamically combines intra- and inter-individual parallelism based on dataset size, ensuring high GPU utilization across a broad spectrum of tasks. Third, EvoGP embeds custom CUDA kernels into the PyTorch runtime, achieving seamless integration with Python-based environments such as Gym, MuJoCo, Brax, and Genesis. Experimental results demonstrate that EvoGP achieves a peak throughput exceeding 1011 GPops/s. Specifically, this performance represents a speedup of up to 304× over existing GPU-based TGP implementations and 18× over state-of-the-art CPU-based libraries. Furthermore, EvoGP maintains comparable accuracy and exhibits improved scalability across large population sizes. EvoGP is open source and accessible at: https://github.com/EMI-Group/evogp.