Parallel Cfd on Commodity Processors
نویسندگان
چکیده
In recent years, the cost of microprocessors for PCs has reduced dramatically. This has led to the introduction of a new class of computing facility commonly known as Beowulf systems, in which commodity-off-the-shelf PCs and networking components are combined into a single cost-effective parallel system. We report our experiences in implementing a number of CFD codes on a 32-processor Beowulf-class system at CLRC’s Daresbury Laboratory. Codes, which were originally developed for Cray T3D and T3E systems, range through combustion DNS, external aerodynamics, LES and environmental codes. These codes have different features that allow the Beowulf system to be thoroughly tested. We find that, whilst the cost-effectiveness of these Beowulf systems can be demonstrated, there can be significant problems involved in porting applications to these machines. Results from our experiences will be presented and issues arising will be discussed. The performance of our Beowulf machine will be compared to more traditional parallel systems. David R. Emerson and Mike Ashworth.
منابع مشابه
Navier-Stokes Computations on Commodity Computers
In this paper we discuss and demonstrate the feasibility of solving high-fidelity, nonlinear computational fluid dynamics (CFD) problems of practical interest on commodity machines, namely Pentium Pro PC’s. Such calculations have now become possible due to the progress in computational power and memory of the off-the-shelf commodity computers, along with the growth in bandwidth and communicatio...
متن کاملParallelization of a State-of-the-Art Industrial CFD Package for Execution on Networks of Workstations and Massively Parallel Processors
Parallelizing TfC, a state-of-the-art industrial 3d CFD code for execution on both networks of workstations (NOWs) and massively parallel processors (MPPs) is one of the main objectives in the interdisciplinary research project SEMPA3. In this paper, the concept for parallelizing TfC is presented as well as results obtained with a first prototype.
متن کاملSpeeding up the Stress Analysis of Hollow Circular FGM Cylinders by Parallel Finite Element Method
In this article, a parallel computer program is implemented, based on Finite Element Method, to speed up the analysis of hollow circular cylinders, made from Functionally Graded Materials (FGMs). FGMs are inhomogeneous materials, which their composition gradually varies over volume. In parallel processing, an algorithm is first divided to independent tasks, which may use individual or shared da...
متن کاملDynamic Load Balancing for Finite Element Calculations on Parallel Computers
Computational requirements of full scale computational fluid dynamics change as computation progresses on a parallel machine. The change in computational intensity causes workload imbalance of processors, which in turn requires a large amount of data movement at runtime. If parallel CFD is to be successful on a parallel or massively parallel machine, balancing of the runtime load is indispensab...
متن کاملImplementing Data - Parallel Programs
Parallel computing is moving rapidly from an era of \Big Iron" to a future that will be dominated by systems built from commodity components. Users will be able to construct high-performance systems by clustering oo-the-shelf processors using widely available high-speed switches. A key question is how to organize the supporting software to best leverage these commodity hardware systems. We addr...
متن کامل