A Visual Analytics Framework for Analyzing Parallel and Distributed Computing Applications

Autor: Misbah Mubarak, Jianping Kelvin Li, Caitlin Ross, Kwan-Liu Ma, Suraj P. Kesavan, Takanori Fujiwara, Christopher D. Carothers, Robert Ross
Rok vydání: 2019
Předmět:
Zdroj: 2019 IEEE Visualization in Data Science (VDS).
Popis: To optimize the performance and efficiency of HPC applications, programmers and analysts often need to collect various performance metrics for each computer at different time points as well as the communication data between the computers. This results in a complex dataset that consists of multivariate time-series and communication network data, which makes debugging and performance tuning of HPC applications challenging. Automated analytical methods based on statistical analysis and unsupervised learning are often insufficient to support such tasks without the background knowledge from the application programmers. To better explore and analyze a wide spectrum of HPC datasets, effective visual data analytics techniques are needed. In this paper, we present a visual analytics framework for analyzing HPC datasets produced by parallel discrete-event simulations (PDES). Our framework leverages automated time-series analysis methods and effective visualizations to analyze both multivariate time-series and communication network data. Through several case studies for analyzing the performance of PDES, we show that our visual analytics techniques and system can be effective in reasoning multiple performance metrics, temporal behaviors of the simulation, and the communication patterns.
Databáze: OpenAIRE