Solving problems on concurrent processors
Solving problems on concurrent processors
What have we learnt from using real parallel machines to solve real problems?
C3P Proceedings of the third conference on Hypercube concurrent computers and applications - Volume 2
OhHelp: a scalable domain-decomposing dynamic load balancing for particle-in-cell simulations
Proceedings of the 23rd international conference on Supercomputing
Hi-index | 0.00 |
We have developed a new algorithm for implementation of plasma particle-in-cell (PIC) simulation codes on concurrent processors. This algorithm, termed the universal concurrent PIC algorithm (UC-PIC), has been utilized in a one-dimensional electrostatic PIC code on the JPL Mark III Hypercube parallel computer. To decompose the problem using the UC-PIC algorithm, the physical domain of the simulation is divided into sub-domains, equal in number to the number of processors, such that all sub-domains have roughly equal numbers of particles. For problems with non-uniform particle densities, these sub-domains will be of unequal physical size. Each processor is assigned, a sub-domain, with nearest neighbor sub-domains assigned to nearest neighbor processors. Using this algorithm in the Mark III PIC code, the increase in speed in going from 1 to 32 processors for the dominant portion of code (push time, defined below) was 29, yielding a parallel efficiency of 90%. Although implemented on a hypercube concurrent computer, this algorithm should be also be efficient for PIC codes on other parallel architectures and on sequential computers where part of the data resides in external memory.