Title: Large-Scale Gas Turbine Simulations on GPU Clusters
Abstract: This chapter presents a strategy for implementing solvers for partial differential equations (PDEs) that rely heavily on stencil computations on three-dimensional, multiblock structured grids. As a starting point, a simple stencil computation arising from the discretization of the three-dimensional heat diffusion equation is considered. Building on this example, the steps taken to redevelop a complete computational fluid dynamics solver originally written in Fortran 77 that consists of many complicated stencil computations are then described. The new solver makes extensive use of automatic source code generation for the implementation of its stencil computations. This capability is provided by a recently developed software framework called SBLOCK and a description of this framework and the strategies it uses to achieve good performance on NVIDIA graphics processing unit (GPUs) is also included. As a final demonstration of the performance and scalability of the new solver, the chapter includes both single-GPU and multi-GPU benchmarks obtained on a 64-GPU cluster.
Publication Year: 2012
Publication Date: 2012-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot