A study of I/O methods for parallel visualization of large-scale data

Hongfeng Yu, Kwan Liu Ma

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

This paper presents two parallel I/O methods for the visualization of time-varying volume data in a high-performance computing environment. We discuss the interplay between the parallel renderer, I/O strategy, and file system, and show the results of our study on the performance of the I/O strategies with and without MPI parallel I/O support. The targeted application is earthquake modeling using a large 3D unstructured mesh consisting of one hundred millions cells. Our test results on the HP/Compaq AlphaServer operated at the Pittsburgh Supercomputing Center demonstrate that the I/O methods effectively remove the I/O bottlenecks commonly present in time-varying data visualization, and therefore help significantly lower interframe delay. This high-performance visualization solution allows scientists to explore their data in the temporal, spatial, and visualization domains at high resolution. Such new explorability, likely not presently available to most computational science groups, will help lead to many new insights into the modeled physical and chemical processes.

Original languageEnglish (US)
Pages (from-to)167-183
Number of pages17
JournalParallel Computing
Volume31
Issue number2
DOIs
StatePublished - Feb 1 2005

Fingerprint

Parallel I/O
Visualization
Time-varying
High Performance
Computational Science
Data visualization
Data Visualization
File System
Chemical Processes
Unstructured Mesh
Physical process
Earthquake
Earthquakes
High Resolution
Likely
Computing
Cell
Modeling
Demonstrate
Strategy

Keywords

  • High-performance computing
  • MPI
  • Massively parallel supercomputing
  • Parallel I/O
  • Parallel rendering
  • Scientific visualization
  • Time-varying data
  • Volume rendering

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Hardware and Architecture
  • Computer Networks and Communications
  • Computer Graphics and Computer-Aided Design
  • Artificial Intelligence

Cite this

A study of I/O methods for parallel visualization of large-scale data. / Yu, Hongfeng; Ma, Kwan Liu.

In: Parallel Computing, Vol. 31, No. 2, 01.02.2005, p. 167-183.

Research output: Contribution to journalArticle

@article{ea17548bb5fa4005bc08f34741f7354c,
title = "A study of I/O methods for parallel visualization of large-scale data",
abstract = "This paper presents two parallel I/O methods for the visualization of time-varying volume data in a high-performance computing environment. We discuss the interplay between the parallel renderer, I/O strategy, and file system, and show the results of our study on the performance of the I/O strategies with and without MPI parallel I/O support. The targeted application is earthquake modeling using a large 3D unstructured mesh consisting of one hundred millions cells. Our test results on the HP/Compaq AlphaServer operated at the Pittsburgh Supercomputing Center demonstrate that the I/O methods effectively remove the I/O bottlenecks commonly present in time-varying data visualization, and therefore help significantly lower interframe delay. This high-performance visualization solution allows scientists to explore their data in the temporal, spatial, and visualization domains at high resolution. Such new explorability, likely not presently available to most computational science groups, will help lead to many new insights into the modeled physical and chemical processes.",
keywords = "High-performance computing, MPI, Massively parallel supercomputing, Parallel I/O, Parallel rendering, Scientific visualization, Time-varying data, Volume rendering",
author = "Hongfeng Yu and Ma, {Kwan Liu}",
year = "2005",
month = "2",
day = "1",
doi = "10.1016/j.parco.2005.02.004",
language = "English (US)",
volume = "31",
pages = "167--183",
journal = "Parallel Computing",
issn = "0167-8191",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - A study of I/O methods for parallel visualization of large-scale data

AU - Yu, Hongfeng

AU - Ma, Kwan Liu

PY - 2005/2/1

Y1 - 2005/2/1

N2 - This paper presents two parallel I/O methods for the visualization of time-varying volume data in a high-performance computing environment. We discuss the interplay between the parallel renderer, I/O strategy, and file system, and show the results of our study on the performance of the I/O strategies with and without MPI parallel I/O support. The targeted application is earthquake modeling using a large 3D unstructured mesh consisting of one hundred millions cells. Our test results on the HP/Compaq AlphaServer operated at the Pittsburgh Supercomputing Center demonstrate that the I/O methods effectively remove the I/O bottlenecks commonly present in time-varying data visualization, and therefore help significantly lower interframe delay. This high-performance visualization solution allows scientists to explore their data in the temporal, spatial, and visualization domains at high resolution. Such new explorability, likely not presently available to most computational science groups, will help lead to many new insights into the modeled physical and chemical processes.

AB - This paper presents two parallel I/O methods for the visualization of time-varying volume data in a high-performance computing environment. We discuss the interplay between the parallel renderer, I/O strategy, and file system, and show the results of our study on the performance of the I/O strategies with and without MPI parallel I/O support. The targeted application is earthquake modeling using a large 3D unstructured mesh consisting of one hundred millions cells. Our test results on the HP/Compaq AlphaServer operated at the Pittsburgh Supercomputing Center demonstrate that the I/O methods effectively remove the I/O bottlenecks commonly present in time-varying data visualization, and therefore help significantly lower interframe delay. This high-performance visualization solution allows scientists to explore their data in the temporal, spatial, and visualization domains at high resolution. Such new explorability, likely not presently available to most computational science groups, will help lead to many new insights into the modeled physical and chemical processes.

KW - High-performance computing

KW - MPI

KW - Massively parallel supercomputing

KW - Parallel I/O

KW - Parallel rendering

KW - Scientific visualization

KW - Time-varying data

KW - Volume rendering

UR - http://www.scopus.com/inward/record.url?scp=18144420440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18144420440&partnerID=8YFLogxK

U2 - 10.1016/j.parco.2005.02.004

DO - 10.1016/j.parco.2005.02.004

M3 - Article

AN - SCOPUS:18144420440

VL - 31

SP - 167

EP - 183

JO - Parallel Computing

JF - Parallel Computing

SN - 0167-8191

IS - 2

ER -