Parallel Algorithm for Solving Systems of Ordinary Differential Equations for NVIDIA CUDA Platform

• Autorzy: Pala A.
• Konferencja: Środowiskowe Warsztaty Doktorantów Politechniki Opolskiej (VII ; 12–14.06.2013; Opole-Pokrzywna)
• Języki publikacji: EN

Abstrakty

EN

Parallel algorithm for solving systems of ordinary differential equations (ODEs) for Nvidia CUDA technology has been developed. This algorithm is based on concept of dividing systems of equations into individual equations or groups of equations which then are solved by separate threads. This article demonstrates initial results and analysis of working time of the algorithm in few examples of its application.

Słowa kluczowe

EN

parallel algorithm; ordinary differential equations; ODEs; Nvidia CUDA technology

PL

algorytm równoległy; równania różniczkowe zwyczajne; technologia NVIDIA CUDA

• Wydawca: Oficyna Wydawnicza Politechniki Opolskiej
• Czasopismo: Zeszyty Naukowe. Elektryka / Politechnika Opolska
• Rocznik: 2013
• Tom: z. 69
• Strony: 73--74
• Opis fizyczny: Bibliogr. 5 poz., tab.

Twórcy

autor

Pala A.

• Department of Electrical, Control and Computer Engineering Institute of Control and Computer Engineering

Bibliografia

• [1] INTEL CORPORATION: Intel Core i7 Extreme Edition Desktop Processor Comparison Chart, Intel Corporation 2012
• [2] NVIDIA CORPORATION: Nvidia Tesla Kepler GPU Computing Accelerators, Nvidia Corporation 2012
• [3] BURRAGE K.: Parallel and Sequential Methods for Ordinary Differential Equations. Clarendon Press, Oxford, 1995
• [4] PETCU D.: Parallelism in Solving Ordinary Differential Equations. Mathematical Monographs 64, Timisoara University Press, 1998
• [5] GEAR C.W.: Massive Parallelism Across Space in ODEs. Applied Numerical Mathematics 11, 1993