Interprocessor Communication Speed And Performance In Distributed-memory Parallel Processors
- 24 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636897,p. 315-324
- https://doi.org/10.1109/isca.1989.714567
Abstract
We have simulated several numerical and non-numerical algorithms on five distributed-memory parallel processors (DMPPs). All five DMPPs have the same topology (a torus), and the same number of nodes. The architectures differ only in the communication speed between neighboring nodes, while the computation unit is kept unchanged. The goal of the paper is to quantify the effect that interprocessor communication speed and synchronization overhead have on the performance of the DMPPs. After introducing the rationale for this study and reviewing related work, we present and discuss the results of the simulations.Keywords
This publication has 25 references indexed in Scilit:
- Iterative algorithms for solution of large sparse systems of linear equations on hypercubesIEEE Transactions on Computers, 1988
- Efficient mapping and implementation of matrix algorithms on a hypercubeThe Journal of Supercomputing, 1988
- Development of Parallel Methods for a $1024$-Processor HypercubeSIAM Journal on Scientific and Statistical Computing, 1988
- Modified Cyclic Algorithms for Solving Triangular Systems on Distributed-Memory MultiprocessorsSIAM Journal on Scientific and Statistical Computing, 1988
- Nearest-Neighbor Mapping of Finite Element Graphs onto Processor MeshesIEEE Transactions on Computers, 1987
- Stencils and Problem Partitionings: Their Influence on the Performance of Multiple Processor SystemsIEEE Transactions on Computers, 1987
- Hypercube Algorithms and ImplementationsSIAM Journal on Scientific and Statistical Computing, 1987
- Reduction of the Effects of the Communication Delays in Scientific Algorithms on Message Passing MIMD ArchitecturesSIAM Journal on Scientific and Statistical Computing, 1987
- Generalized conjugate-gradient acceleration of nonsymmetrizable iterative methodsLinear Algebra and its Applications, 1980
- Orthomin, an Iterative Method for Solving Sparse Sets of Simultaneous Linear EquationsPublished by Society of Petroleum Engineers (SPE) ,1976