Coupling Complementary Simulations for Combined Performance and Energy Optimization

2026-06-08

AI Summary

This work addresses the longstanding challenge in polymer simulation of balancing accuracy and computational efficiency. The authors propose a multiscale collaborative simulation framework that couples the continuum-scale Uneyama–Doi model with the particle-scale SOMA Monte Carlo method. A custom multi-GPU coordination library is developed to ensure temporal synchronization and efficient task distribution. Through algorithmic and hardware-aware optimizations—including GPU kernel fusion, memory coalescing, and asynchronous random number generation—the framework achieves substantial improvements in energy efficiency while preserving physical fidelity. Compared to the baseline SOMA implementation, the approach delivers a 13-fold speedup and reduces energy consumption by 96% (a 24.5× improvement), all while maintaining scientific consistency in the simulation outcomes.

Abstract

Polymer simulations are among the most computationally demanding workloads in soft-matter research, often requiring days of execution and high energy consumption to achieve physically meaningful results. In this work, we address these challenges through the coupling and optimization of two complementary simulation frameworks: the Uneyama-Doi Model (UDM) and the SOft coarse-grained Monte Carlo Acceleration (SOMA). UDM efficiently propagates concentration fields at the continuum level, while SOMA resolves chain-scale thermal fluctuations via particle-based Monte Carlo dynamics. Each model was individually optimized for GPU execution using kernel fusion, memory coalescing, asynchronous random-number generation yielding up to 70% (UDM) and 80% (SOMA) performance improvement. The coupling is performed through our proposed coordinator library that orchestrates data exchange and synchronizes time-stepping across multiple GPUs. Further management of coupling workload distribution enabled a 13x overall speedup and 24.5x reduction in total energy usage compared to the SOMA baseline, i. e., 96% energy saving. The proposed hybrid approach maintains the same scientific fidelity while drastically reducing the computational and energy footprint, showcasing the potential of energy-aware, cross-application co-design for sustainable high-performance simulations

Problem

• polymer simulations
• computational demand
• energy consumption
• soft-matter research
• high-performance simulations

Innovation

• hybrid simulation
• GPU optimization
• energy-aware computing
• multi-scale modeling
• co-design