Implementing an Ode Code on Distributed Memory Computers
نویسندگان
چکیده
1 Abstract In this paper it is shown how to adapt an existing package (VODE) for solving systems of ordinary diierential equations on serial computers to distributed memory parallel computers. The approach taken is based on waveform relaxation in which the problem is decomposed into a sequence of subproblems and which are then solved independently using VODE on each processor. Communication between subtasks is provided by a generic software environment p4. This approach allows the development of general purpose parallel software for ODEs which is both reliable and portable.
منابع مشابه
Adaptive Time-Dependent CFD on Distributed Unstructured Meshes
Two recent trends in software for CFD problems are the use of unstructured adaptive meshes and the need to implement the software on distributed memory parallel computers. The subject of this paper is the implementation of one particular code of this type for the solution of time-dependent compressible Euler and Navier Stokes problems. The software described here uses the method of lines with t...
متن کاملThe Rthreads Distributed Shared Memory System
Rthreads (Remote threads) is a software distributed shared memory system that supports sharing of global variables on clusters of computers with physically distributed memory. Rthreads uses explicit function calls for access of distributed shared data. Unique aspects of Rthreads are: Synchronization primitives are syntactically and semantically closely related to the POSIX thread model (Pthread...
متن کاملParallel and Distributed Programming with Pthreads and Rthreads
This paper describes Rthreads (Remote threads), a software distributed shared memory system that supports sharing of global variables on clusters of computers with physically distributed memory. Other DSM systems either use virtual memory to implement coherence on networks of workstations or require programmers to adopt a special programming model. Rthreads uses primitives to read and write rem...
متن کاملThe performance of a spectral simulation code for turbulence on parallel computers with distributed memory
The performance of a pseudo spectral turbulence simulation code on various supercomputers, with either shared memory or distributed memory, is presented. The communication with the memory is intense, and careful consideration of the two memory configurations is needed to obtain high performance. The investigations of the performance show that the scaling with the number of processors is excelle...
متن کاملA Message-Passing Distributed Memory Parallel Algorithm for a Dual-Code Thin Layer, Parabolized Navier-Stokes Solver
In this study, the results of parallelization of a 3-D dual code (Thin Layer, Parabolized Navier-Stokes solver) for solving supersonic turbulent flow around body and wing-body combinations are presented. As a serial code, TLNS solver is very time consuming and takes a large part of memory due to the iterative and lengthy computations. Also for complicated geometries, an exceeding number of grid...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1994