jFoF: GPU Cluster Finding with Gradient Propagation

TL;DR

jFoF is a GPU-native, differentiable halo finder that significantly accelerates astrophysical simulation analysis and enables gradient-based optimization of structure formation models.

Contribution

It introduces a fully GPU-accelerated, differentiable Friends-of-Friends halo finder with novel neighbor-search strategies and gradient propagation capabilities.

Findings

Achieves up to 10x speedup over CPU implementations.

Maintains consistent halo catalogs across implementations.

Enables gradient-based optimization of halo connectivity.

Abstract

We present jFoF, a fully GPU-native Friends-of-Friends (FoF) halo finder designed for both high-performance simulation analysis and differentiable modeling. Implemented in JAX, jFoF achieves end-to-end acceleration by performing all neighbor searches, label propagation, and group construction directly on GPUs, eliminating costly host--device transfers. We introduce two complementary neighbor-search strategies, a standard k-d tree and a novel linked-cell grid, and demonstrate that jFoF attains up to an order-of-magnitude speedup compared to optimized CPU implementations while maintaining consistent halo catalogs. Beyond performance, jFoF enables gradient propagation through discrete halo-finding operations via both frozen-assignment and topological optimization modes. Using a topological optimization approach via a REINFORCE-style estimator, our approach allows smooth optimization of halo connectivity and membership, bridging continuous simulation fields with discrete structure catalogs. These capabilities make jFoF a foundation for differentiable inference, enabling end-to-end, gradient-based optimization of structure formation models within GPU-accelerated astrophysical pipelines. We make our code publicly available at https://github.com/bhorowitz/jFOF/.