Optimizing Amber for Device-to-Device GPU Communication
Samuel Khuvis, Karen A. Tomko, Scott R. Brozell, Chen-Chun Chen, Hari Subramoni, Dhabaleswar K. DK Panda · Practice and Experience in Advanced Research Computing · 2023
Although direct GPU-to-GPU communication has been possible in MPI libraries for over a decade, the limited availability of compatible hardware at academic HPC centers has discouraged the development of algorithms in scientific applications that take advantage of this capability. In this paper, we take Amber, a molecular dynamics code used to simulate proteins and nucleic acids, as a test case. We demonstrate the modifications necessary to implement GPU-to-GPU communication. Compared to the previous implementation, these modifications show an average of approximately 36% improvement in performance overall and 84% for the important explicit solvent subset of the benchmarks.