In the first week of April, the Pittsburgh Post-Gazette ran an editorial feature written by Pittsburgh Supercomputing Center scientific directors Michael Levine and Ralph Roskies and director of special projects James Kasdorf. These three individuals co-authored the proposal that led the National Science Foundation to fund the Pittsburgh Supercomputing Center (PSC) 25 years ago. On April 15, the center is hosting an open house commemorating its 25th anniversary. In advance of this milestone occasion, the OpEd piece addresses the role of supercomputing and presents a look back at some of the center’s biggest accomplishments.
The article starts off with an overview of how the PSC came into existence:
In the fall of 1984, the three of us joined forces to write a proposal to the National Science Foundation. We hoped to bring a supercomputing center to Pittsburgh. The availability of NSF funding to do this was a plum opportunity.
A supercomputing center, we thought, in addition to enabling extraordinary advances in science, could reinforce the research strengths of local universities and industries. It could also facilitate science education at all levels and add to Pittsburgh’s presence in computing, helping this region to attract business and retain its exceptional workforce.
On Jan. 17, 1986, after many suspense-filled months, the National Science Board approved funding for the Pittsburgh Supercomputing Center, a joint effort of Carnegie Mellon, the University of Pittsburgh and Westinghouse.
The piece, although targeted for a general audience, will interest the HPC crowd, too. The past quarter-century has ushered in tremendous progress in computational performance, and PSC’s history reflects the overall trends. The authors note the enormous discrepency between PSC’s first supercomputers and today’s machines. The center’s first supercomputer, a CRAY X-MP, was capable of 840 million flops (840 megaflops), while the fastest modern supercomputers are a million times more powerful and much more cost efficient. To illustrate the leap in computing power, a 2011-era laptop outperforms that CRAY X-MP with its $18 million pricetag.
The discussion goes on to address the merits of supercomputing, parallel processing and the need for ever “increasing amounts of computing.” On the last point, the authors state that the current level of computing has been “very productive but doesn’t take us as far toward solving these important problems as we’d like.” They cite climate modeling as one of these important problems:
Ideally, for example, [climate models] would include every tree and building on the planet. The catch, though, is that as a model focuses more sharply on fine detail, computing requirements expand. Computational scientists spend a good portion of their brain cycles to arrive at the optimum balance between realism in their models and available computing power.
The Pittsburgh Supercomputing Center Open House takes place on April 15 at 1 p.m. The event will highlight achievements from the past 25 years and will present Blacklight, the center’s newest computing resource.