Advection-Based Sparse Data Management for Visualizing Unsteady Flow

作     者：Guo, Hanqi Zhang, Jiang Liu, Richen Liu, Lu Yuan, Xiaoru Huang, Jian Meng, Xiangfei Pan, Jingshan 

作者机构：Peking Univ Key Lab Machine Percept Minist Educ Sch EECS Beijing Peoples R China Peking Univ Ctr Computat Sci & Engn Beijing Peoples R China Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN USA Natl Supercomp Ctr Tianjin Tianjin Peoples R China Natl Supercomp Ctr Jinan Shandong Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS》 (IEEE Trans Visual Comput Graphics)

年 卷 期：2014年第20卷第12期

页      面：2555-2564页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 

基　　金：NSFC [61170204, 61232012] Chinese Academy of Sciences [XDA05040205] 

主　　题：Flow visualization Data management High performance visualization Key-value store 

摘      要：When computing integral curves and integral surfaces for large-scale unsteady flow fields. a major bottleneck is the widening gap between data access demands and the available bandwidth (both I/O and in-memory). In this work, we explore a novel advection-based scheme to manage flow field data for both efficiency and scalability. The key is to first partition flow field into blocklets (e.g. cells or very fine-grained blocks of cells), and then (pre)fetch and manage blocklets on-demand using a parallel key-value store. The benefits are (1) greatly increasing the scale of local-range analysis (e.g. source-destination queries, streak surface generation) that can fit within any given limit of hardware resources;(2) improving memory and I/O bandwidth-efficiencies as well as the scalability of naive task-parallel particle advection. We demonstrate our method using a prototype system that works on workstation and also in supercomputing environments. Results show significantly reduced I/O overhead compared to accessing raw flow data. and also high scalability on a supercomputer for a variety of applications.