The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Authors: Xiaohui Duan (Shandong University, National Supercomputing Center in Wuxi); Jin Wang (International School for Advanced Studies, Italy); Ping Gao (Tsinghua University, National Supercomputing Center in Wuxi); Ming Ma (Tsinghua University); Lin Gan (Tsinghua University, National Supercomputing Center in Wuxi); Xin Liu (National Supercomputing Center in Wuxi); Haohuan Fu and Wei Xue (Tsinghua University, National Supercomputing Center in Wuxi); Dexun Chen (National Supercomputing Center in Wuxi); Guangwen Yang (Tsinghua University, National Supercomputing Center in Wuxi); and Weiguo Liu (Shandong University, National Supercomputing Center in Wuxi)
Abstract: Molecular dynamics (MD) simulation can provide an affordable way for inspecting microscopic phenomena, which is a powerful complement to real-world experiments. But the spatial scale of MD simulations is usually magnitudes smaller than experiment systems. In this paper, we present our work, redesigning the widely used inter-layer potential in structural superlubricity. By carrying out a specialized neighbor list for inter-layer potential computation, the total memory access amount is reduced significantly. Besides, a simple but efficient vectorization strategy is implemented based on the new neighbor list. In the extreme case, our work can scale to 38 million cores to achieve a sustainable performance of 61 PFLOPS, enabling a simulation of a superlubricity system of 32 um^2 with 7.2 billion atoms at 4.75 ns/day, which is 11,834 times of reported largest scale simulation in superlubricity systems in contact area and almost ten times faster in time-to-solution.
Back to Technical Papers Archive Listing