The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Authors: Sandro Rigo, Thiago Maltempi, Marcio Pereira, and Hervé Yviquel (University of Campinas); Jessé Costa (Pará Federal University); and Guido Araujo (University of Campinas)
Abstract: Remote Time Migration (RTM) poses substantial computational challenges, demanding large memory and extended processing times. Our RTM implementation processes three-dimensional fields on multiple NVIDIA GPUs using the Revolve algorithm for checkpointing. However, transferring data between the host and GPU memory introduces a bottleneck.
We introduced a checkpoint prefetching mechanism to overcome this, anticipating memory transfers from host to GPU. Additionally, we integrated GPU data compression using the cuZFP library to reduce data transfer sizes further. The experimental results demonstrated significant performance improvements, achieving a speedup of 1.98x - 2.53x in our benchmark dataset. Prefetching + compression techniques together could reduce host-to-GPU memory transfers by up to 16x.
Best Poster Finalist (BP): no
Poster: PDF
Poster summary: PDF
Back to Poster Archive Listing