skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: The PVM (Parallel Virtual Machine) system: Supercomputer level concurrent computation on a network of IBM RS/6000 power stations

Conference ·
OSTI ID:6274699
 [1];  [2]
  1. Emory Univ., Atlanta, GA (USA). Dept. of Mathematics and Computer Science
  2. Oak Ridge National Lab., TN (USA)

The PVM (Parallel Virtual Machine) system enables supercomputer level concurrent computations to be performed on interconnected networks of heterogeneous computer systems. Specifically, a network of 13 IBM RS/6000 powerstations has been successfully used to execute production quality runs of superconductor modeling codes at more than 250 Mflops. This work demonstrates the effectiveness of cooperative concurrent processing for high performance applications, and shows that supercomputer level computations may be attained at a fraction of the cost on distributed computing platforms. This paper describes the PVM programming environment and user facilities, as they apply to hardware platforms comprising a network of IBM RS/6000 powerstations. The salient design features of PVM will be discussed; including heterogeneity, scalability, multilanguage support, provisions for fault tolerance, the use of multiprocessors and scalar machines, an interactive graphical front end, and support for profiling, tracing, and visual analysis. The PVM system has been used extensively, and a range of production quality concurrent applications have been successfully executed using PVM on a variety of networked platforms. The paper will mention representative examples, and discuss two in detail. The first is a material sciences problem that was originally developed on a Cray 2. This application code calculates the electronic structure of metallic alloys from first principles and is based on the KKR-CPA algorithm. The second is a molecular dynamics simulation for calculating materials properties. Performance results for both applicants on networks of RS/6000 powerstations will be presented, and accompanied by discussions of the other advantages of PVM and its potential as a complement or alternative to conventional supercomputers.

Research Organization:
Oak Ridge National Lab., TN (USA)
Sponsoring Organization:
DOE/ER
DOE Contract Number:
AC05-84OR21400
OSTI ID:
6274699
Report Number(s):
CONF-9104166-2; ON: DE91007844
Resource Relation:
Conference: IBM large scale analysis and modeling conference, Park City, UT (USA), 24-26 Apr 1991
Country of Publication:
United States
Language:
English