08.27.12 - Permalink
Visualization has been an integral part of NCSA since its beginning. That tradition continues with the Blue Waters project. While the early visualization work is mostly concerned with testing software functionality and performance, says Dave Semeraro, Blue Waters visualization team leader, it is providing tantalizing glimpses of the science.
As Petascale Computing Resource Allocations (PRAC) teams exercise the Blue Waters Early Science System (BW-ESS), NCSA staff members are performing application tests to ascertain system and application performance. These tests, done in collaboration with BW-ESS users, have produced datasets that are, in turn, being used by the Blue Waters visualization staff to test scalable visualization tools. Such tools enable science teams to explore the very large volumes of data they will produce on the full system.
NCSA staff members have been collaborating with the science teams since the initial PRAC awards were made. These collaborations have provided insight into the size and type of data that each team will produce as well as their individual analysis needs. This collaboration immediately showed that the size of the data, the variety of data formats, and the domain specific analysis needs would be the defining factors in formulating an effective visualization strategy.
"The Blue Waters early science period has been instrumental in defining the visualization needs of the user community," explains Semeraro. "We have assisted users in large scale visualization projects. We have discovered and corrected flaws in some of our software. And we have added to the roster of supported software, all as direct result of the interactions we have had with the early science users. We look forward to continuing this interaction with a broader spectrum of PRAC users as the Blue Waters system moves into production."
For work with two of the BW-ESS teams, the visualization software packages VisIt and Paraview were chosen. Both suites offer the ability to ingest large volumes of data, utilize distributed memory parallelism, and read a variety of data formats. These software suites were installed on the BW-ESS.
Stan Woosley's supernova simulation team uses the VisIt software in their project. Blue Waters consultants collaborated with this team to verify that VisIt was installed properly and was adequate to visualize the data produced in their early science runs. Blue Waters visualization consultants have begun to use this data to explore the scalability of VisIt and to experiment with the visualization algorithms that the software provides.
Visualization team members also collaborated with the PRAC team lead by Brian O'Shea. His team uses the Enzo code to simulate star formation, and primarily depends on analysis software called YT that is designed for astrophysics research. In addition to installing the required software for analyzing Enzo data on the BW-ESS, the Enzo data was also used to test the data reader and rendering capabilities of other maintained analysis software.
Blue Waters user support team members continue to collaborate with BW-ESS users to verify functionality and performance of visualization software suites and to assist the science teams in exploring their data. As time passes data set sizes will grow and analysis will become far more challenging. Data output formats and algorithms may change as science teams continue their investigations.
Blue Waters consultants are ready to assist the science teams in the task of data visualization and analysis. For more information, contact Dave Semeraro (firstname.lastname@example.org) or Rob Sisneros (email@example.com).