Originally published at: Supercharge Graph Analytics at Scale with GPU-CPU Fusion for 100x Performance | NVIDIA Technical Blog
Graphs form the foundation of many modern data and analytics capabilities to find relationships between people, places, things, events, and locations across diverse data assets. According to one study, by 2025 graph technologies will be used in 80% of data and analytics innovations, which will help facilitate rapid decision making across organizations. When working with…
Would the authors be able to explain why the max_change and maximum_iteration parameters are different between the CPU and GPU + CPU trials. How many iterations were run for each experiment?
Also by keeping the max_change parameter constant between increasing sized graphs, you’ll do less work because the PR vector mass will be distributed amongst more vertices. Do you have any experiments which vary the tolerance as 1/|V|?