Ultrascale Visualization Assembling the scalable parallel visualization infrastructure needed to enable knowledge discovery at the petascale and instructing application scientists on how to best use these tools Kwan-Liu Ma (project webpage) University of California at Davis

Understanding the science behind ultra-scale simulations and high-throughput experiments requires scientists to extract meaning from massive datasets containing hundreds of terabytes or more. Parallel visualization can be a useful path to understanding data at this scale but is not without its own challenges especially across our diverse scientific user community. Research in visualization tools and techniques, partnered with the scientific users and dedicated to producing open source tools supported through workshops and other education activities, can significantly accelerate progress.

The SciDAC Institute for Ultrascale Visualization will assemble a comprehensive parallel visualization suite that is portable across platforms to enable scientific discovery at this scale and will instruct application scientists on how to best use these tools. The Institute will bring together leading experts from visualization, high-performance computing, and science application areas to make parallel visualization technology a commodity for SciDAC scientists and the broader community.

The Institute will also make recommendations to industry for revising hardware and software architectures and protocols to support large-scale visualization calculations. The education component will be responsible for organizing tutorials, benchmarking software and hardware, and organizing summer training for students.

One major way this Institute will serve the community is to encourage collaborations within the visualization community through a visitor program that will both expand existing ties in the Institute by bringing in additional expertise on various topic, as well as serve as an important conduit for distributing the tools, results and expertise of the Institute members. Workshops will be another important outreach component to the Institute and provide hands-on transfer of major visualization codes and analysis tools to a broad community. They will also provide a forum for focused, intensive activities between researchers.

Complementing the outreach program will be a comprehensive education program. The Institute will organize tutorials and demonstrations at major conferences and will organize summer schools to educate potential users of advanced visualization technology. Summer schools will also target university students who are participating in the development of high-performance visualization technology. These education activities will help to more quickly disseminate new technologies produced.

Specifically the Institute will:

• educate SciDAC application scientists and the broader community through an active outreach program, ensuring that knowledge and technologies are widely disseminated;
• develop high performance visualization strategies on diverse platforms including general-purpose clusters, dedicated visualization clusters, and especially high-end computing systems, leveraging existing technologies when appropriate;
• produce benchmarks of parallel visualization tools as guides for scientists and as methods to assess the capabilities of these tools on new ultra-scale systems.

This integrated set of activities is strengthened by connections to SciDAC science applications, which serve as early adopters of technology, and by connections to computer science partners, whose tools combine with those developed in the Institute to further aid in the scientific process.

SciDAC Institute: Visualization

Project Title: SciDAC Institute for Ultrascale Visualization

Principal Investigator: Kwan-Liu Ma
Affiliation: University of California at Davis

Project Webpage: iusv.ucdavis.edu

Participating Institutions and Co-Investigators:
Argonne National Laboratory - Robert Ross
Ohio State University - Han-Wei Shen
Sandia National Laboratories - Kenneth Moreland
University of California at Davis - Kwan-Liu Ma (PI), Nelson Max, John Owens
University of Tennessee at Knoxville - Jian Huang
University of Virginia - Greg Humphreys

Funding Partners: Office of Science — Office of Advanced Scientific Computing Research

Budget and Duration: Approximately $1.6 million per year for five years ¹

Other SciDAC Institutes
Othere SciDAC visualization efforts