NPACI's Teraflops IBM SP Accepted by SDSC after Testing on Scientific Applications, Including Thousand-Processor Jobs

Published 01/05/2000

Contact: David Hart, SDSC, dhart@sdsc.edu, 858-534-8314
Jeffrey Gluck, IBM, jgluck@us.ibm.com, 914-766-3839

SAN DIEGO, CA - The 1,152-processor IBM RS/6000 SP system at the San Diego Supercomputer Center (SDSC) was officially accepted by SDSC management December 30 after successfully completing a battery of tests that demonstrated stable operation, good performance, and high throughput. The test results show that the new machine will provide the capability to solve problems in days that typically require weeks, months, or years on smaller machines.

"This is a tribute to the terrific teamwork between IBM and SDSC staff who worked throughout the holidays to install the system," said Sid Karin, director of SDSC and the National Partnership for Advanced Computational Infrastructure (NPACI). "IBM's high-level attention and commitment to problem resolution will enable us to make the machine available to researchers tackling large scientific problems early this year."

The IBM SP computer, installed for NPACI at SDSC, has a peak speed of one teraflops -- a trillion floating-point operations per second -- and is the most powerful available to the U.S. academic community for unclassified research. The machine is ranked tenth on the list of Top 500 Supercomputer Sites ( http://www.top500.org/) maintained by the University of Tennessee and the University of Mannheim.

"This is a milestone achievement in IBM's rapidly evolving partnership with the team at San Diego Supercomputer Center," said Michael J. Henesey worldwide sales and marketing, IBM RS6000 Scientific and Technical Computing. "The significance here is the massive computational capability now available in an unclassified environment. This gives the research community the tool needed for breakthroughs in areas such climate modeling, mapping and modeling the human brain, and genomic research. At IBM, we're proud to be delivering on this commitment and also very focused on developing the next-generation systems that will attempt to satisfy the scientific community's insatiable desire for insight."

The highlight of the cooperative IBM and SDSC effort was the discovery and resolution of a problem in the mapping of memory to cache that led to excessive variation in program run-times. Working together, IBM and SDSC improved the cache management for large systems using Power3 SMP High Nodes. The operating system patch will be included in the next release of AIX.

As part of the acceptance tests, performance of four scientific applications on both the teraflops SP and NPACI's current production SP was compared for various numbers of processors from 1 to 128. The applications included AMBER for molecular dynamics; GAMESS for quantum chemistry; and PARTREE and SCF for astrophysics. In all cases, these applications ran 1.11 to 1.92 times faster on the teraflops SP.

One application, SCF, was also run on all 1,152 processors and showed good scaling over a large processor range. Using a fixed problem size per processor, the run-time on 1,152 processors was only 1.5 times slower than the time on two processors.

One further test demonstrated high node throughput. Over four consecutive days in December, the system's 144 compute nodes were in use more than 86% of the time, peaking at 95.7% usage on Christmas Day.

Also during acceptance testing, the system was unofficially tested as a participant in distributed.net's RC5-64 code-breaking challenge ( http://distributed.net/rc5/). While participating in force, the machine placed among the top five daily participants for a week. (See accompanying release.)

NPACI's IBM SP teraflops system at SDSC is the nation's most powerful computer system dedicated to unclassified research by qualified academic, government, and industry scientists and engineers. Allocations of time on the new IBM SP system will be made through national peer review, with preference given to problems that take advantage of the machine's unique capability. See http://www.npaci.edu/Allocations/ for more information.

The National Partnership for Advanced Computational Infrastructure (NPACI) unites 46 universities and research institutions to build the computational environment for tomorrow's scientific discovery. Led by UC San Diego and the San Diego Supercomputer Center (SDSC), NPACI is funded by the National Science Foundation's Partnerships for Advanced Computational Infrastructure (PACI) program and receives additional support from the State and University of California, other government agencies, and partner institutions. The NSF PACI program also supports the National Computational Science Alliance. For additional information about NPACI, see http://www.npaci.edu/, or contact David Hart at SDSC, 858-534-8314, dhart@sdsc.edu.