Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cattaneo, Alberto, Ballard, M Keith, Kirby, Robert M., Shankar, Varun
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.22087
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908990189862912
author Cattaneo, Alberto
Ballard, M Keith
Kirby, Robert M.
Shankar, Varun
author_facet Cattaneo, Alberto
Ballard, M Keith
Kirby, Robert M.
Shankar, Varun
contents The rapid rise of scientific machine learning (SciML) has expanded the role of differentiable modeling, surrogate modeling, and data-driven constitutive laws in large-scale simulation. The JAX framework provides an attractive environment for these workflows through automatically differentiable programs, vectorization, GPU acceleration, and while enabling seamless learning of surrogate models. However, large-scale simulation still relies on mature HPC infrastructure. Libraries, such as PETSc, provide scalable MPI-based parallelism, robust linear and nonlinear solvers, and advanced preconditioning capabilities that remain difficult to reproduce in JAX-only workflows. We present JetSCI, a hybrid JAX-PETSc framework that unifies these complementary strengths. JetSCI uses JAX for GPU-parallel differentiable discretizations and PETSc for robust, scalable solution of the resulting systems on distributed-memory architectures, exposing multilevel parallelism through GPU acceleration within nodes and MPI parallelism across nodes. For finite element discretizations of heterogeneous micromechanics problems, JetSCI outperforms JAX-only implementations in efficiency and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22087
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle JetSCI: A Hybrid JAX-PETSc Framework for Scalable Differentiable Simulation
Cattaneo, Alberto
Ballard, M Keith
Kirby, Robert M.
Shankar, Varun
Mathematical Software
The rapid rise of scientific machine learning (SciML) has expanded the role of differentiable modeling, surrogate modeling, and data-driven constitutive laws in large-scale simulation. The JAX framework provides an attractive environment for these workflows through automatically differentiable programs, vectorization, GPU acceleration, and while enabling seamless learning of surrogate models. However, large-scale simulation still relies on mature HPC infrastructure. Libraries, such as PETSc, provide scalable MPI-based parallelism, robust linear and nonlinear solvers, and advanced preconditioning capabilities that remain difficult to reproduce in JAX-only workflows. We present JetSCI, a hybrid JAX-PETSc framework that unifies these complementary strengths. JetSCI uses JAX for GPU-parallel differentiable discretizations and PETSc for robust, scalable solution of the resulting systems on distributed-memory architectures, exposing multilevel parallelism through GPU acceleration within nodes and MPI parallelism across nodes. For finite element discretizations of heterogeneous micromechanics problems, JetSCI outperforms JAX-only implementations in efficiency and accuracy.
title JetSCI: A Hybrid JAX-PETSc Framework for Scalable Differentiable Simulation
topic Mathematical Software
url https://arxiv.org/abs/2604.22087