Locality optimized shared-memory implementations of iterated runge-kutta methods

Authors:
Matthias Korch;Thomas Rauber
Affiliations:
University of Bayreuth, Department of Computer Science;University of Bayreuth, Department of Computer Science
Venue:
Euro-Par'07 Proceedings of the 13th international Euro-Par conference on Parallel Processing
Year:
2007

Citing 12
Cited 3

Supernode partitioning

POPL '88 Proceedings of the 15th ACM SIGPLAN-SIGACT symposium on Principles of programming languages
Parallel iteration of high-order Runge-Kutta methods with stepsize control

Journal of Computational and Applied Mathematics
The potential for parallelism in Runge-Kutta methods. Part 1: RK formulas in standard form

SIAM Journal on Numerical Analysis
Parallel and sequential methods for ordinary differential equations

Parallel and sequential methods for ordinary differential equations
Optimizing matrix multiply using PHiPAC: a portable, high-performance, ANSI C coding methodology

ICS '97 Proceedings of the 11th international conference on Supercomputing
A Compiler Optimization Algorithm for Shared-Memory Multiprocessors

IEEE Transactions on Parallel and Distributed Systems
LAPACK Users' guide (third ed.)

LAPACK Users' guide (third ed.)
Cache miss equations: a compiler framework for analyzing and tuning memory behavior

ACM Transactions on Programming Languages and Systems (TOPLAS)
Optimizing compilers for modern architectures: a dependence-based approach

Optimizing compilers for modern architectures: a dependence-based approach
Optimizing locality and scalability of embedded Runge--Kutta solvers using block-based pipelining

Journal of Parallel and Distributed Computing
Improving locality for ODE solvers by program transformations

Scientific Programming
Design and Implementation of the ScaLAPACK LU, QR, and Cholesky Factorization Routines

Scientific Programming

Dynamic selection of implementation variants of sequential iterated runge-kutta methods with tile size sampling

Proceedings of the 2nd ACM/SPEC International Conference on Performance engineering
An efficient time-step-based self-adaptive algorithm for predictor-corrector methods of Runge-Kutta type

Journal of Computational and Applied Mathematics
Locality improvement of data-parallel Adams-Bashforth methods through block-based pipelining of time steps

Euro-Par'12 Proceedings of the 18th international conference on Parallel Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 introduce different implementation variants for sequential and shared-memory computer systems and analyze their runtime and cache performance on two modern supercomputer systems.