文章基本信息

标题：An Efficient Acceleration of Solving Heat and Mass Transfer Equations with the First Kind Boundary Conditions in Capillary Porous Radially Composite Cylinder Using Programmable Graphics Hardware
本地全文：下载
作者：Hira Narang ; Fan Wu ; Abdul Rafae Mohammed 等
期刊名称：Journal of Computer and Communications
印刷版ISSN：2327-5219
电子版ISSN：2327-5227
出版年度：2019
卷号：7
期号：7
页码：267-281
DOI：10.4236/jcc.2019.77022
出版社：Scientific Research Publishing
摘要：With the latest advances in computing technology, a huge amount of efforts have gone into simulation of a range of scientific phenomena in engineering fields. One such case is the simulation of heat and mass transfer in capillary porous media, which is becoming more and more necessary in analyzing a number of eventualities in science and engineering applications. However, this procedure of numerical solution of heat and mass transfer equations for capillary porous media is very time consuming. Therefore, this paper pursuit is at making use of one of the acceleration methods developed in the graphics community that exploits a graphical processing unit (GPU), which is applied to the numerical solutions of such heat and mass transfer equations. The nVidia Compute Unified Device Architecture (CUDA) programming model offers a correct approach of applying parallel computing to applications with graphical processing unit. This paper suggests a true improvement in the performance while solving the heat and mass transfer equations for capillary porous radially composite cylinder with the first type of boundary conditions. This heat and mass transfer simulation is carried out through the usage of CUDA platform on nVidia Quadro FX 4800 graphics card. Our experimental outcomes exhibit the drastic overall performance enhancement when GPU is used to illustrate heat and mass transfer simulation. GPU can considerably accelerate the performance with a maximum found speedup of more than 5-fold times. Therefore, the GPU is a good strategy to accelerate the heat and mass transfer simulation in porous media.
关键词：Numerical Solution;Heat and Mass Transfer;General Purpose Graphics Processing Unit (GPGPU);CUDA