COMMET: orders-of-magnitude speed-up in finite element method via batch-vectorized neural constitutive updates

2025-10-01

AI Summary

Neural constitutive models (NCMs) face prohibitive computational overhead in large-scale finite element (FE) simulations due to repeated analytical differentiation of stress and stiffness—hindering practical deployment. To address this, we introduce COMMET, an open-source FE framework designed specifically for efficient NCM integration. Its core innovations are: (i) a rearchitected FE solver enabling batched, vectorized constitutive updates; (ii) computation graph optimization that replaces conventional automatic differentiation with explicit analytical derivative derivation; and (iii) MPI-based distributed-memory parallelization. Experimental results demonstrate that COMMET achieves over 1000× speedup versus non-vectorized automatic-differentiation implementations while preserving numerical accuracy. It is the first framework to enable high-fidelity FE simulation with NCMs at million-degree-of-freedom scale, establishing a new paradigm for large-scale, high-fidelity mechanical modeling of complex materials.

Technology Category

• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Machine Learning: Matrix & Tensor Methods
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Constitutive evaluations often dominate the computational cost of finite element (FE) simulations whenever material models are complex. Neural constitutive models (NCMs) offer a highly expressive and flexible framework for modeling complex material behavior in solid mechanics. However, their practical adoption in large-scale FE simulations remains limited due to significant computational costs, especially in repeatedly evaluating stress and stiffness. NCMs thus represent an extreme case: their large computational graphs make stress and stiffness evaluations prohibitively expensive, restricting their use to small-scale problems. In this work, we introduce COMMET, an open-source FE framework whose architecture has been redesigned from the ground up to accelerate high-cost constitutive updates. Our framework features a novel assembly algorithm that supports batched and vectorized constitutive evaluations, compute-graph-optimized derivatives that replace automatic differentiation, and distributed-memory parallelism via MPI. These advances dramatically reduce runtime, with speed-ups exceeding three orders of magnitude relative to traditional non-vectorized automatic differentiation-based implementations. While we demonstrate these gains primarily for NCMs, the same principles apply broadly wherever for-loop based assembly or constitutive updates limit performance, establishing a new standard for large-scale, high-fidelity simulations in computational mechanics.

Problem

• Accelerating expensive neural constitutive model evaluations in finite element simulations
• Overcoming computational bottlenecks in large-scale finite element analysis
• Enabling high-fidelity simulations by vectorizing constitutive updates and derivatives

Innovation

• Batched vectorized constitutive evaluations algorithm
• Compute-graph-optimized derivatives replace automatic differentiation
• Distributed-memory parallelism via MPI implementation