skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures

Abstract

Execution on massively threaded processors is one of the most critical challenges for high-performance computing (HPC) scientific visualization. Of the many fundamental changes we are seeing in HPC systems, one of the most profound is a reliance on new processor types optimized for execution bandwidth over latency hiding. Moreover, our current production scientific visualization software is not designed for these new types of architectures. In order to address this issue, the VTK-m framework serves as a container for algorithms, provides flexible data representation, and simplifies the design of visualization algorithms on new and future computer architecture.

Authors:
 [1];  [2];  [3];  [2];  [4];  [4];  [5];  [6];  [7];  [5];  [8];  [9];  [10];  [10]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. Univ. of Utah, Salt Lake City, UT (United States)
  4. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  5. Univ. of Oregon, Eugene, OR (United States)
  6. Intel, Santa Clara, CA (United States)
  7. Univ. of California, Davis, CA (United States)
  8. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  9. The Ohio State Univ., Columbus, OH (United States)
  10. Kitware, Clifton Park, NY (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1366945
Alternate Identifier(s):
OSTI ID: 1257810; OSTI ID: 1457265
Report Number(s):
SAND-2016-1719J; LLNL-JRNL-733058; LA-UR-15-27306
Journal ID: ISSN 0272-1716; 619843
Grant/Contract Number:  
AC04-94AL85000; AC52-07NA27344; AC52-06NA25396
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
IEEE Computer Graphics and Applications
Additional Journal Information:
Journal Volume: 36; Journal Issue: 3; Journal ID: ISSN 0272-1716
Publisher:
IEEE
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; 97 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; computer graphics; high-performance computing; visualization software; parallel algorithms; algorithmic structures; massively threaded processors; VTK-m framework; Computer Science

Citation Formats

Moreland, Kenneth, Sewell, Christopher, Usher, William, Lo, Li-ta, Meredith, Jeremy, Pugmire, David, Kress, James, Schroots, Hendrik, Ma, Kwan-Liu, Childs, Hank, Larsen, Matthew, Chen, Chun-Ming, Maynard, Robert, and Geveci, Berk. VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures. United States: N. p., 2016. Web. doi:10.1109/mcg.2016.48.
Moreland, Kenneth, Sewell, Christopher, Usher, William, Lo, Li-ta, Meredith, Jeremy, Pugmire, David, Kress, James, Schroots, Hendrik, Ma, Kwan-Liu, Childs, Hank, Larsen, Matthew, Chen, Chun-Ming, Maynard, Robert, & Geveci, Berk. VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures. United States. doi:10.1109/mcg.2016.48.
Moreland, Kenneth, Sewell, Christopher, Usher, William, Lo, Li-ta, Meredith, Jeremy, Pugmire, David, Kress, James, Schroots, Hendrik, Ma, Kwan-Liu, Childs, Hank, Larsen, Matthew, Chen, Chun-Ming, Maynard, Robert, and Geveci, Berk. Mon . "VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures". United States. doi:10.1109/mcg.2016.48. https://www.osti.gov/servlets/purl/1366945.
@article{osti_1366945,
title = {VTK-m: Accelerating the Visualization Toolkit for Massively Threaded Architectures},
author = {Moreland, Kenneth and Sewell, Christopher and Usher, William and Lo, Li-ta and Meredith, Jeremy and Pugmire, David and Kress, James and Schroots, Hendrik and Ma, Kwan-Liu and Childs, Hank and Larsen, Matthew and Chen, Chun-Ming and Maynard, Robert and Geveci, Berk},
abstractNote = {Execution on massively threaded processors is one of the most critical challenges for high-performance computing (HPC) scientific visualization. Of the many fundamental changes we are seeing in HPC systems, one of the most profound is a reliance on new processor types optimized for execution bandwidth over latency hiding. Moreover, our current production scientific visualization software is not designed for these new types of architectures. In order to address this issue, the VTK-m framework serves as a container for algorithms, provides flexible data representation, and simplifies the design of visualization algorithms on new and future computer architecture.},
doi = {10.1109/mcg.2016.48},
journal = {IEEE Computer Graphics and Applications},
issn = {0272-1716},
number = 3,
volume = 36,
place = {United States},
year = {2016},
month = {5}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Figures / Tables:

Figure 1 Figure 1: Implementing all of our visualization algorithms separately for every architecture (at left) we need to support leads to an unmanageable amount of software. By using VTK-m's abstract device model based on data parallel primitives (at right), we can reduce the amount of software to implement to a feasiblemore » level.« less

Save / Share: