Title:	HYBRID SCHEDULING FRAMEWORK FOR PARALLEL VISUALIZATION OF LARGE-SCALE MULTIPHYSICS SIMULATION DATA
Author(s):	Yi Cao, Zeyao Mo, Zhiwei Ai, Huawei Wang and Li Xiao
ISBN:	978-989-8533-91-3
Editors:	Katherine Blashki and Yingcai Xiao
Year:	2019
Edition:	Single
Keywords:	Multiphysics, Multifield Visualization, Parallel Visualization, In Situ Visualization
Type:	Full Paper
First Page:	223
Last Page:	230
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	Following the recent rapid growth in supercomputer performance, many real-world problems in fields such as climate change and weather forecasting, nuclear energy, and electromagnetic environments can be solved via multiphysics simulation. However, current multifield visualization has difficulty handling multiphysics parallel simulation data. First, it is difficult to correctly visualize overlapping multifield data with semitransparent properties because of the complex distribution of partitioned data domains across multicore processors. Second, the interactive visualization performance of large-scale multifield data in serial processing mode on a personal computer is often slow because multiphysics simulations can produce large-scale data sets, i.e., of the order of gigabytes to terabytes. This paper introduces a hybrid scheduling framework for parallel visualization of computational multifield data, which is used to overcome problems both in correct visual representation and in efficient visualization of large-scale computational multifield data. The proposed framework supports scalable in situ visualization of 8.5 billion mesh cells on the 10 k cores of China’s TianHe-2 supercomputer, which could help domain scientists understand multiphysics phenomena more clearly and with greater accuracy.
	Go Back