Accelerating Nonlinear Time-History Analysis with Complex Constitutive Laws via Heterogeneous Memory Management: From 3D Seismic Simulation to Neural Network Training

TL;DR

This paper introduces a heterogeneous memory management framework that accelerates nonlinear time-history simulations with complex laws, enabling high-fidelity 3D evaluations and efficient neural network surrogate modeling.

Contribution

A novel memory management approach leveraging CPU-GPU bandwidth to overcome GPU memory limitations in large-scale nonlinear simulations.

Findings

Significant reduction in time-to-solution and energy consumption.

Successful development of a neural network surrogate model from massive datasets.

Enhanced capability for high-fidelity 3D seismic and scientific simulations.

Abstract

Nonlinear time-history evolution problems employing high-fidelity physical models are essential in numerous scientific domains. However, these problems face a critical dual bottleneck: the immense computational cost of time-stepping and the massive memory requirements for maintaining a vast array of state variables. To address these challenges, we propose a novel framework based on heterogeneous memory management for massive ensemble simulations of general nonlinear time-history problems with complex constitutive laws. Taking advantage of recent advancements in CPU-GPU interconnect bandwidth, our approach actively leverages the large capacity of host CPU memory while simultaneously maximizing the throughput of the GPU. This strategy effectively overcomes the GPU memory wall, enabling memory-intensive simulations. We evaluate the performance of the proposed method through comparisons with conventional implementations, demonstrating significant improvements in time-to-solution and energy-to-solution. Furthermore, we demonstrate the practical utility of this framework by developing a Neural Network-based surrogate model using the generated massive datasets. The results highlight the effectiveness of our approach in enabling high-fidelity 3D evaluations and its potential for broader applications in data-driven scientific discovery.