Domain decomposition and particle pushing for multiprocessing computers

Mankofsky, A.; Seftor, J. L.; Chang, Chein‐Chi; Ko, K.; Mondelli, A.; Drobot, A.; Moura, José J. G.; Aimonetti, W.D.; Brandon, S.; Nielsen, Dale; Dyer, Kathleen M.

doi:10.1016/0010-4655(88)90034-3

Cited by 8 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Porting a large and complex application code from a uniprocessor to a multiprocessor machine is a difficult and timeconsuming task. Vectorizing and multitasking large codes on 'traditional' supercomputers such as the Cray-2 and Cray Y-MP still currently requires a high degree of expertise [52,53]. The implementation on MIMD distributed memory machines, in which data are passed between processors by an explicit message-passing scheme, is at least as difficult.…”

Section: Portability and Software Engineering Issuesmentioning

confidence: 99%

Characterizing the parallel performance of a large‐scale, particle‐in‐cell plasma simulation code

Walker

1990

Concurrency: Pract. Exper.

View full text Add to dashboard Cite

The efficient implementation of particle‐in‐cell (PIC) plasma simulation codes on distributed memory concurrent computers is made difficult by the conflicting aims of balancing the computational load and minimizing interprocessor communication. This paper surveys previous work on PIC plasma simulation codes on advanced architecture computers, identifies the main issues in parallelizing such codes, and discusses different decomposition schemes. For MIMD concurrent computers the adaptive Eulerian (AE) decomposition scheme is attractive because it seeks to maintain approximate load balance dynamically while avoiding excessive non‐local communication. The load balance and communication characteristics of a large‐scale AE/PIC code on the hypercube are investigated by simulating the behavior of the parallel code on a Cray‐2. The results show that for the three‐dimensional problems studied, in which the particle distribution is highly inhomogeneous, the communication of data between the particle and mesh decompositions dominates the communication overhead. Performing the load balancing may also make a significant contribution to the concurrent overhead if the grain size is sufficiently small. The advantages of the simulation approach in investigating the behavior of concurrent large‐scale applications are discussed, together with portability and software engineering issues.

show abstract

Section: Portability and Software Engineering Issuesmentioning

confidence: 99%

Characterizing the parallel performance of a large‐scale, particle‐in‐cell plasma simulation code

Walker

1990

Concurrency: Pract. Exper.

View full text Add to dashboard Cite

show abstract

Numerical modelling of the stationary Maxwell–Lorentz system in technical devices

Westermann

1994

Int J Numerical Modelling

View full text Add to dashboard Cite

SUMMARYThe particle-in-cell method is coupled with boundary-fitted co-ordinates in order to model the stationary Maxwell-Lorentz problem in technical devices. New numerical algorithms describing the transition between the grid model and the mesh-free model are developed and the existing techniques of finite difference schemes for equidistant grids are extended to non-equidistant, arbitrarily shaped, convex four-point meshes. The modelling process is described, and both the numerical approximation and the algorithms are discussed. Applications in different technical devices show the flexibility of the method.

show abstract

Particle-in-cell simulations with moving boundaries—adaptive mesh generation

Westermann

1994

Journal of Computational Physics

View full text Add to dashboard Cite

Domain decomposition and particle pushing for multiprocessing computers

Cited by 8 publications

References 1 publication

Characterizing the parallel performance of a large‐scale, particle‐in‐cell plasma simulation code

Characterizing the parallel performance of a large‐scale, particle‐in‐cell plasma simulation code

Numerical modelling of the stationary Maxwell–Lorentz system in technical devices

Particle-in-cell simulations with moving boundaries—adaptive mesh generation

Contact Info

Product

Resources

About