The ideas that got CASC started directly affect the culture of our organization today.
John May, acting director of CASC
John May, acting director of CASC, welcomes attendees to CASC's 20th anniversary event

Center for Applied Scientific Computing Marks 20th Anniversary

Wednesday, June 8, 2016

For 20 years, scientists from Lawrence Livermore National Laboratory’s (LLNL’s) Center for Applied Scientific Computing (CASC) have contributed scientific research and development in mathematics, computer science, and data science that have directly impacted national security and advanced basic science.

To celebrate the milestone, CASC hosted a two-hour event at the Central Cafeteria on June 2, 2016, featuring talks from current and former CASC and Computation leaders, reflections from alumni, posters highlighting landmark achievements from the past two decades, and the unveiling of a new logo.

“For people who are newer to CASC, this celebration was a great opportunity to hear about where we came from. The ideas that got CASC started directly affect the culture of our organization today,” says John May, acting director of CASC.

CASC was founded in March 1996 by Steven Ashby (now director of Pacific Northwest National Laboratory) after the Department of Energy moved the National Energy Research Supercomputer Center (NERSC) and the Center for Computational Sciences and Engineering (CCSE) from LLNL to Lawrence Berkeley National Laboratory. Though initially stunned by the move, many NERSC and CCSE computational and computer scientists chose to stay at LLNL.

CASC was conceived as a new home for applied mathematics and computer science research at LLNL. To ensure its future success, it was important that CASC have strong internal ties to LLNL and its programs as well as strong external ties with academia to ensure that CASC was always bringing in new ideas and personnel to perform cutting-edge research—values that still ring true to the organization 20 years later.

“The CASC model is a uniquely perfect blend of academic allegiance and mission relevance,” says Lori Diachin, director of CASC from 2010 to 2016. “It is a great point of pride for me to be associated with it.”

What began as just 12 scientists has now grown to more than 100 staff and postdoctoral researchers. They contribute to programs throughout the Laboratory, and they ensure that mathematical, algorithmic, and computer science research remains relevant to LLNL’s mission. CASC remains Livermore’s window to the broader computer science, computational physics, applied mathematics, and data science research communities.

Among some of CASC’s most successful projects are scalable linear solvers (hypre), adaptive mesh refinement (SAMRAI), subsurface flow (PARFLOW), ordinary differential equation and nonlinear solvers (SUNDIALS), source-to-source code translation (ROSE), neutron and radiation transport (Ardra), wave propagation (Serpentine codes), performance tools, and large-scale visualization tools. CASC scientists have helped LLNL research teams win several prestigious honors including two Gordon Bell Awards and five R&D100 awards.

May attributes CASC’s success over the years to a spirit of collaboration and innovation among its scientists, who work side by side with LLNL programs and application teams. While CASC continually brings in fresh ideas through its postdocs and students, May is especially proud of the longevity of CASC’s early staff. “When our first org chart was made in September 1996, we had about two dozen employees. Half of those people are still working in CASC today,” he says.

With the challenges of exascale computing looming and a likely shift in hardware architecture on the horizon, CASC scientists will have myriad opportunities to continue demonstrating the excellence that has become their brand by delivering solutions that will be critical to the Laboratory’s future mission success.