next up previous
Next: Current Status and Availability Up: PVM Previous: Applications

Grand Challenge Application Experiences with PVM

Over the past few years a number of applications have been developed using PVM. The table below list some of the applications.


These implementations have been done on various platforms.

During the last few years, ORNL material scientists and their collaborators at the University of Cincinnati, SERC at Daresbury, and the University of Bristol have been developing an algorithm for studying the physical properties of complex substitutionally disordered materials. A few important examples of physical systems and situations in which substitutional disorder plays a critical role in determining material properties include: high-strength alloys, high-temperature superconductors, magnetic phase transitions, and metal/insulator transitions. The algorithm being developed is an implementation of the Korringa, Kohn and Rostoker coherent potential approximation (KKR-CPA) method for calculating the electronic properties, energetics and other ground state properties of substitutionally disordered alloys [10]. The KKR-CPA method extends the usual implementation of density functional theory (LDA-DFT) [11] to substitutionally disordered materials [7]. In this sense it is a completely first principles theory of the properties of substitutionally disordered materials requiring as input only the atomic numbers of the species making up the solid.

The KKR-CPA algorithm contains several locations where parallelism can be exploited. These locations correspond to integrations in the KKR-CPA algorithm. Evaluating integrals typically involves the independent evaluation of a function at different locations and the merging of these data into a final value. The integration over energy was parallelized. The parallel implementation is based on a master/slave paradigm to reduce memory requirements and synchronization overhead. In the implementation one processor is responsible for reading the main input file, which contains the number of nodes to be used on each multiprocessor as well as the number and type of workstations to include, the problem description, and the location of relevant data files. This master processor also manages dynamic load balancing of the tasks through a simple pool-of-tasks scheme.

Using PVM the KKRCPA code is able to achieve over 200 Mflops utilizing a network of ten IBM RS/6000 workstations. Given this capability, the KKRCPA code is being used as a research code to solve important materials science problems. Since its development the KKRCPA code has been used to compare the electronic structure of two high temperature superconductors, Ba(Bitex2html_wrap_inline316Pbtex2html_wrap_inline318Otex2html_wrap_inline320 and (Batex2html_wrap_inline322Ktex2html_wrap_inline324)BiOtex2html_wrap_inline320, to explain anomalous experimental results from a high strength alloy, NiAl, and to study the effect of magnetic multilayers in CrV and CrMo alloys for their possible use in magnetic storage devices.

The goal of the groundwater modeling group is to develop state of the art parallel models for today's high performance parallel computers, which will enable researchers to model flow with higher resolution and greater accuracy than ever before. As a first step researchers at ORNL have developed a parallel 3-D finite element code called PFEM that models water flow through saturated-unsaturated media. PFEM solves the system of equations
where h is the pressure head, t is time, tex2html_wrap_inline332 is the saturated hydraulic conductivity tensor, tex2html_wrap_inline334 is the relative hydraulic conductivity or relative permeability, z is the potential head, q is the source/sink and F is the water capacity (tex2html_wrap_inline342, with tex2html_wrap_inline344 the moisture content) after neglecting the compressibility of the water and of the media.

Parallelization was accomplished by partitioning the physical domain and statically assigning subdomains to tasks. The present version uses only static load-balancing and relies on the user to define the partitioning. In each step of the solution the boundary region of each subdomain is exchanged with its neighboring regions.

Originally developed on an Intel iPSC/860 multiprocessor, a PVM version of PFEM was straightforward to create requiring an undergraduate student less than 3 weeks to complete. Presently, the PVM version of PFEM has been delivered to several members of the groundwater modeling group for validation testing using networks of workstations while they await the availability of parallel supercomputers.

next up previous
Next: Current Status and Availability Up: PVM Previous: Applications

Jack Dongarra
Fri Dec 13 15:35:04 EST 1996