Performance of the Shallow Water Equations on the CM-200 and CM-5 Parallel Supercomputers

Abstract

We describe the implementation of a fluid dynamical benchmark on two Thinking Machines Corporation parallel computers - the 65,536 processor CM-200 computer and the 1024-node CM-5 computer. The benchmark, the Shallow Water Equations, is frequently used as a model for both oceanographic and atmospheric circulation. We describe the steps involved in implementing the algorithm on the computers and we provide details of resulting performance. We have measured 5.2 Gflops (64-bit arithmetic) and 8.1 Gflops (32-bit) on the CM-200 while the CM-5 delivers 22.1 Gflops (64-bit) and 24 Gflops (32-bit). For comparison, performance of 1.53 Gflops was measured for the same algorithm on the CRAY Y-MP/8, 1.28 Gflops on the 256-node SUPRENUM-1 and 0.54 Gflops was measured on the 128-node Intel iPSC/860.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1992
Accession Number
ADA454596

Entities

People

  • Oliver A. Mcbryan

Organizations

  • University of Colorado Boulder

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Computer Science
  • Computers
  • Computing Devices
  • Corporations
  • Equations
  • Fluids
  • Information Operations
  • Mathematics
  • Shallow Water
  • Supercomputers
  • Water

Readers

  • Coastal Oceanography
  • Parallel and Distributed Computing.