LBVis: Interactive Dynamic Load Balancing Visualization for Parallel Particle Tracing

We propose an interactive visual analytical approach to exploring and diagnosing the dynamic load balance (data and task partition) process of parallel particle tracing in flow visualization. To understand the complex nature of the parallel processes, it is necessary to integrate the information of...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Jiang, Yang, Changhe, Li, Yanda, Chen, Li, Yuan, Xiaoru
Format: Conference Proceeding
Language:English
Subjects:
Data visualization
Heuristic algorithms
Layout
load balancing
Load management
Parallel particle tracing
Performance analysis
Scalability
visual analytics
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an interactive visual analytical approach to exploring and diagnosing the dynamic load balance (data and task partition) process of parallel particle tracing in flow visualization. To understand the complex nature of the parallel processes, it is necessary to integrate the information of the behaviors and patterns of the computing processes, data changes and movements, task status and exchanges, and gain the insight of the relationships among them. In our proposed approach, the data and task behaviors are visualized through a graph with a fine-designed layout, in which node glyphs are dedicated to showing the status of processes and the links represent the data or task transfer between different computation rounds and processes. User interactions are supported to facilitate the exploration of performance analysis. We provide a case study to demonstrate that the proposed approach enables users to identify the bottlenecks during this process, and thus help optimize the related algorithms.
ISSN:2165-8773
DOI:10.1109/PacificVis48177.2020.1029