Dallas, TEXAS — The National Computational Science Alliance (Alliance) research booth at SC2000 (R804) will include an Itanium-based system running a popular ab intitio quantum chemistry code on Microsoft’s 64-bit Windows operating system.
The code will also run on an eight-processor Itanium-based server cluster with 64-bit Windows in the Kuck and Associates, Inc. (KAI) booth (849). KAI is a subsidiary of Intel.
Developed by Alex Granovsky’s research group at Moscow State University, this quantum chemistry code, called PC-GAMESS, is a highly tuned and extended version of the GAMESS (for General Atomic and Molecular Electronic Structure System) code. GAMESS was developed at the Department of Energy’s Ames Laboratory at Iowa State University. Porting the Granovsky team’s code to an Itanium-based server cluster running 64-bit Windows began several weeks ago, when members of the National Center for Supercomputing Application’s (NCSA) cluster development team began working with Granovsky to get the application running on Intel’s new Itanium architecture and specifically in the Windows operating system designed for Itanium-based systems. With the support of Intel, Granovsky spent about two weeks at NCSA in Champaign, IL, the leading-edge site for the Alliance.
“It is very significant that this application is up and running so quickly on 64-bit Windows and an Itanium-based server cluster and that we have seen very good performance levels,” said Rob Pennington, head of cluster development efforts for NCSA and the Alliance. “This required a high level of cooperation among NCSA, Moscow State University, and our colleagues in the private sector, particularly Intel. It is an excellent example of the commitment within the private sector to high-performance computing on commodity systems.”
Todd Needham, manager, Research Programs Group at Microsoft Research, added that the success in porting this quantum chemistry code to 64-bit Windows shows that 64-bit Windows is a stable and scalable operating system in the Itanium-based sever cluster environment.
“We are serious about providing an operating system for the growing number of scientific researchers who are using the cluster platform to do their work,” he said. “Itanium-based server clusters are an important component in the future of high-performance computing, and we intend to be part of that future.”
For Intel, porting the code to Itanium-based server clusters is another success story for its brand new Itanium architecture. “This is an important code for advanced R&D used in both science and industry, so having this application available on Itanium-based server clusters is a valuable enabling technology that will help drive scientific innovation toward new insights and new products in the pharmaceutical and chemical industries ,” said Tom Gibbs, director of Industry Marketing, Intel Corporation.
Members of NCSA’s cluster development team configured the eight-processor Itanium-based cluster that was used to port PC-GAMESS. That cluster included MPICH–a middleware tool developed by Argonne National Laboratory that implements Message Passing Interface (MPI) on most computer systems. The cluster also included a middleware layer called Virtual Machine Interface (VMI), developed by NCSA cluster team member Avneesh Pant. VMI makes it possible for MPICH to work transparently across different interconnects and operating systems within a cluster and allows MPICH to be fine-tuned to the Itanium-based server cluster environment.
SC2000, the annual high-performance computing and networking conference, will be held in Dallas, Nov. 4-10. The exhibit hall opens at 7 p.m. Monday, Nov. 6, with a VIP reception. Regular exhibit hall hours will be 10 a.m. – 6 p.m. Tuesday, Nov. 7 and Wednesday, Nov. 8, and 10 a.m. – 4 p.m. Thursday, Nov. 9.
The National Computational Science Alliance is a partnership to prototype an advanced computational infrastructure for the 21st century and includes more than 50 academic, government and industry research partners from across the United States. The Alliance is one of two partnerships funded by the National Science Foundation’s Partnerships for Advanced Computational Infrastructure (PACI) program, and receives cost-sharing at partner institutions. NSF also supports the National Partnership for Advanced Computational Infrastructure (NPACI), led by the San Diego Supercomputer Center.
The National Center for Supercomputing Applications is the leading-edge site for the National Computational Science Alliance. NCSA is a leader in the development and deployment of cutting-edge high-performance computing, networking, and information technologies. The National Science Foundation, the state of Illinois, the University of Illinois, industrial partners, and other federal agencies fund NCSA.