1. What contributions have the authors mentioned in the paper "Computational fluid dynamics using graphics processing units: challenges and opportunities" ?
In this review paper, the authors describe their experiences on the various algorithms developed and the speeds achieved.. This paper describes some of their recent experiences of using Graphics Processing Units as a paradigm for performing large-scale scientific computations.. Beginning with essentially no background in using GPUs for CFD, the authors have, over the years, implemented several methodologies of CFD on a GPU, and studied a number of flow problems.. The objective of this paper is to provide their assessment of learning, implementing, and applying the codes to problems of their interest.. Hence many of the experiences reported here are being quickly superseded with new products and compilers being released by GPU vendors such as NVIDIA.. Further code optimizations and tuning of the data structures may permit further speed-ups.
read more
2. What are the future works in "Computational fluid dynamics using graphics processing units: challenges and opportunities" ?
In the past three years, the authors have developed five different CFD algorithms, and have found speed-ups over a CPU of factors between 10-25, with a possibility of another factor of four gain through optimization.. 9 Copyright © 2011 by ASME A significant rewrite of the algorithm and the code may be necessary.. While this may be a hurdle to cross, the time investment may be worthwhile because multi-core architectures of one form or the other are going to be the necessary trend for high resolution / high performance computing.
read more
