Performance Evaluation of Fully Anisotropic Elastic Wave Propagation on NVIDIA Volta GPUs

Summary In this work, we evaluate the effect of some traditional approaches to improve finite difference codes in NVIDIA Volta GPUs. We observe how each optimization affects the throughput of each of the regions of the algorithm. Additionally, our study covers both an evaluation of speedup for weak and strong scaling when enabling all the hardware cores available in Voltas, alongside with the resulting throughput on the Power 9 processor to which Voltas are connected and other Intel-based HPC architectures.