JAX-Fluids 2.0: Towards HPC for differentiable CFD of compressible two-phase flows

Deniz A. Bezgin, Aaron B. Buhendwa, Nikolaus A. Adams

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In our effort to facilitate machine learning-assisted computational fluid dynamics (CFD), we introduce the second iteration of JAX-Fluids. JAX-Fluids is a Python-based fully-differentiable CFD solver designed for compressible single- and two-phase flows. In this work, the first version is extended to incorporate high-performance computing (HPC) capabilities. We introduce a parallelization strategy utilizing JAX primitive operations that scales efficiently on GPU (up to 512 NVIDIA A100 graphics cards) and TPU (up to 1024 TPU v3 cores) HPC systems. We further demonstrate stable parallel computation of automatic differentiation gradients across extended integration trajectories. The new code version offers enhanced two-phase flow modeling capabilities. In particular, a five-equation diffuse-interface model is incorporated which complements the level-set sharp-interface model. Additional algorithmic improvements include positivity-preserving limiters for increased robustness, support for stretched Cartesian meshes, refactored I/O handling, comprehensive post-processing routines, and an updated list of state-of-the-art high-order numerical discretization schemes. We verify newly added numerical models by showcasing simulation results for single- and two-phase flows, including turbulent boundary layer and channel flows, air-helium shock bubble interactions, and air-water shock drop interactions.

Original languageEnglish
Article number109433
JournalComputer Physics Communications
Volume308
DOIs
StatePublished - Mar 2025

Keywords

  • Computational fluid dynamics
  • Differential programming
  • Diffuse-interface
  • High-performance computing
  • JAX
  • Level-set
  • Machine learning
  • Navier-Stokes equations
  • Turbulence
  • Two-phase flows

Fingerprint

Dive into the research topics of 'JAX-Fluids 2.0: Towards HPC for differentiable CFD of compressible two-phase flows'. Together they form a unique fingerprint.

Cite this