A graph-based visualization for monitoring of high-performance computing system

Ngan Vuong Thuy Nguyen, Bao Nguyen, Jon Hass, Tommy Dang

Keywords: visualization, HCI, HPC monitoring

TL;DR: application of Human-centered computing on HPC monitoring

Abstract: The primary role of visualization is to strengthen data exploration and analysis, especially for complex and high dimensional data. High-performance computing (HPC) systems are typically large and complicated instruments that generate massive performance and operation data. Monitoring the performance and operation of HPC systems are challenges for researchers. This work proposes a visual design using the idea of the bipartite graph to visualize the monitoring data of an HPC cluster at a university. We build a web-based prototype, called JobViewer, that integrates advanced methods in visualization and human-computer interaction (HCI) to demonstrate the benefits of visualization in monitoring an HPC. We also show real use cases and a user study to prove the efficiency of this approach.

Confirm No Double Submission: Yes

Withdraw On Reject: Yes