Lattice QCD on the IBM scalable POWERParallel Systems SP2

  • Authors:

  • C. Bernard;C. DeTar;S. Gottlieb;U. M. Heller;J. Hetrick;N. Ishizuka;L. Karkkainen;S. R. Lantz;K. Rummukainen;R. Sugar;D. Toussaint;M. Wingate

  • Affiliations:

  • Department of Physics, Washington University, St. Louis, MO;Department of Physics, University of Utah, Salt Lake City, UT;Department of Physics, Indiana University, Bloomington, IN;SCRI, The Florida State University, Tallahassee, FL;Department of Physics, University of Arizona, Tucson, AZ;Department of Physics, Washington University, St. Louis, MO;Nordita, DK-2100, Copenhagen, Denmark;Cornell Theory Center, Cornell University, Ithaca, NY;Department of Physics, Indiana University, Bloomington, IN;Department of Physics, University of California, Santa Barbara, CA;Department of Physics, University of Arizona, Tucson, AZ;Department of Physics, University of Colorado, Boulder, CO

  • Venue:
  • Supercomputing '95 Proceedings of the 1995 ACM/IEEE conference on Supercomputing
  • Year:
  • 1995

Quantified Score

Hi-index 0.00

Visualization

Abstract

A 512 node IBM Scalable POWERParallel Systems SP2 was installed at the Cornell Theory Center in October 1994. During the past couple of months we have been porting and optimizing code for carrying out lattice QCD calculations. Present performance is far from ideal, however, and optimization efforts are still under way. The rate limiting step in our code involves a rather generic inversion of a large, sparse system, based on a partial differential equation in a multidimensional space. The insights we have gained so far may be useful in diagnosing performance in a wide class of applications.