Code modernization strategies for short-range non-bonded molecular dynamics simulations

TL;DR

This paper presents strategies for modernizing molecular dynamics simulations on HPC systems by restructuring data, applying vectorization, and implementing fine-grained parallelism with HPX, achieving significant speedups over traditional MPI approaches.

Contribution

It introduces a comprehensive approach combining data restructuring, vectorization, and HPX-based parallelism to enhance performance of molecular dynamics simulations on modern hardware.

Findings

Threefold speedup from vectorization and data restructuring.

1.4 times speedup using HPX over MPI in load-imbalanced systems.

Effective task granularity improves parallel efficiency.

Abstract

Modern HPC systems are increasingly relying on greater core counts and wider vector registers. Thus, applications need to be adapted to fully utilize these hardware capabilities. One class of applications that can benefit from this increase in parallelism are molecular dynamics simulations. In this paper, we describe our efforts at modernizing the ESPResSo++ molecular dynamics simulation package by restructuring its particle data layout for efficient memory accesses and applying vectorization techniques to benefit the calculation of short-range non-bonded forces, which results in an overall three times speedup and serves as a baseline for further optimizations. We also implement fine-grained parallelism for multi-core CPUs through HPX, a C++ runtime system which uses lightweight threads and an asynchronous many-task approach to maximize concurrency. Our goal is to evaluate the performance of an HPX-based approach compared to the bulk-synchronous MPI-based implementation. This requires the introduction of an additional layer to the domain decomposition scheme that defines the task granularity. On spatially inhomogeneous systems, which impose a corresponding load-imbalance in traditional MPI-based approaches, we demonstrate that by choosing an optimal task size, the efficient work-stealing mechanisms of HPX can overcome the overhead of communication resulting in an overall 1.4 times speedup compared to the baseline MPI version.