Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Tsuyoshi Ichimura, Kohei Fujita, Hideaki Ito, Muneo Hori, Lalith Maddegedara

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.

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

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.

Paper Structure

This paper contains 9 sections, 2 equations, 5 figures, 2 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. Method
  3. Target problem
  4. Proposed method
  5. Numerical performance
  6. Application Example
  7. 3D dynamic nonlinear effects
  8. Effectiveness of NNs considering 3D dynamic nonlinear effects
  9. Concluding Remarks

Figures (5)

  • Figure 1: (a) 3D ground structure model with line A-B and point C. The $x,y$-coordinates of A, B, and C are (848, 1400), (848, 1900), and (848, 1648) m, respectively. (b) Close-up view of the region around line A-B. (c) Material properties of the soil structure.
  • Figure 2: Elapsed time per case.
  • Figure 3: Maximum velocity norm distribution at the surface for Kobe wave input
  • Figure 4: (a) Cross section of ground structure at line A-B. The "surface" indicate the ground surface, while "interface" indicates the interface between the first and bedrock layers. C indicate the obervation point. (b) Maximum velocity response in the $x$-direction along line A-B. The black dot indicates the response estimated by the NNs.
  • Figure 5: Reponse at point C for Kobe wave. (a) and (b) indicate responses to 3D and 1D dynamic nonlinear analysis, while (c) shows the estimated response by NNs. (d) indicate the velocity response spectra ($h=0.05$) for waves in (a), (b), and (c).