Iterated Runge-Kutta methods on distributed memory multiprocessors
نویسندگان
چکیده
In this article, we consider the iterated Runge–Kutta (IRK) method which is an iteration method based on a predictor–corrector scheme for the solution of ordinary differential equations. The method uses embedded formulae to control the stepsize. We present different algorithms of the IRK method on distributed memory multiprocessors using appropriate communication primitives. The theoretical performance analysis and a runtime simulation allow us to value the presented algorithms. An implementation on the Intel iPSC/860 confirms the predicted runtimes.
منابع مشابه
Diagonal Implicitly Iterated Runge Kutta Methods on Distributed Memory Multiprocessors
We investigate the parallel implementation of the diagonal implicitly iterated Runge Kutta DIIRK method an iteration method based on a predictor corrector scheme This method is appropriate for the solution of sti systems of ordinary di erential equations ODEs and provides embedded formulae to control the stepsize We discuss di erent strate gies for the implementation of the DIIRK method on dist...
متن کاملParallel Iterated Runge Kutta Methods and Applications
The iterated Runge Kutta IRK method is an iteration scheme for the numerical solu tion of initial value problems IVP of ordinary di erential equations ODEs that is based on a predictor corrector method with an Runge Kutta RK method as corrector Embed ded approximation formulae are used to control the stepsize We present di erent parallel algorithms of the IRK method on distributed memory multip...
متن کاملLocality Optimized Shared-Memory Implementations of Iterated Runge-Kutta Methods
Iterated Runge-Kutta (IRK) methods are a class of explicit solution methods for initial value problems of ordinary differential equations (ODEs) which possess a considerable potential for parallelism across the method and the ODE system. In this paper, we consider the sequential and parallel implementation of IRK methods with the main focus on the optimization of the locality behavior. We intro...
متن کاملComparing Task and Data Parallel Execution Schemes for the DIIRK Method
We investigate the parallel implementation of the diagonal{ implicitly iterated Runge{Kutta method, an iteration method which is appropriate for the solution of stii systems of ordinary diierential equations. We discuss diierent strategies for the implementation of the method on distributed memory multiprocessors, which mainly diier in the data distribution and the order of independent computat...
متن کاملParallel Execution of Embedded Runge-Kutta Methods
In this paper, we consider the parallel solution of nonstii ordinary diierential equations with two diierent classes of Runge-Kutta (RK) methods providing embedded solutions: classical embedded RK methods and iterated RK methods which were constructed especially for parallel execution. For embedded Runge-Kutta methods, mainly the potential system parallelism is exploited. Iterated RK methods pr...
متن کامل