Simulation-based analysis of parallel runge-kutta solvers

Authors:
Matthias Korch;Thomas Rauber
Affiliations:
Department of Mathematics, Physics, and Computer Science, University of Bayreuth;Department of Mathematics, Physics, and Computer Science, University of Bayreuth
Venue:
PARA'04 Proceedings of the 7th international conference on Applied Parallel Computing: state of the Art in Scientific Computing
Year:
2004

Citing 8
Cited 0

Solving ordinary differential equations I (2nd revised. ed.): nonstiff problems

Solving ordinary differential equations I (2nd revised. ed.): nonstiff problems
The working set model for program behavior

Communications of the ACM
Optimizing locality for ODE solvers

ICS '01 Proceedings of the 15th international conference on Supercomputing
Simics: A Full System Simulation Platform

Computer
SimpleScalar: An Infrastructure for Computer System Modeling

Computer
Using complete machine simulation to understand computer system behavior

Using complete machine simulation to understand computer system behavior
A fast and accurate framework to analyze and optimize cache memory behavior

ACM Transactions on Programming Languages and Systems (TOPLAS)
Restructuring computations for temporal data cache locality

International Journal of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

We use simulation-based analysis to compare and investigate different shared-memory implementations of parallel and sequential embedded Runge-Kutta solvers for systems of ordinary differential equations. The results of the analysis help to provide a better understanding of the locality and scalability behavior of the implementations and can be used as a starting point for further optimizations.