A Preliminary Study on Accelerating Simulation Optimization with GPU Implementation

This paper provides a preliminary study on utilizing GPUs to accelerate computation for three simulation optimization tasks with either first-order or second-order algorithms. Numerical experiments demonstrate the computational advantages of GPU implementation over CPU-only implementation, and show that the advantage further increases as the problem scale increases.

Authors: Jinghai He, Haoyu Liu, Yuhang Wu, Zeyu Zheng, Tingyu Zhu (in alphabetical order)

Published in Proceedings of the 2024 Winter Simulation Conference (WSC), 2024.

Download Paper