Paper Info
Title
Hypercubic storage layout and transforms in arbitrary dimensions using GPUs and CUDA
Abstract
Many simulations in the physical sciences are expressed in terms of rectilinear arrays of variables. It is attractive to develop such simulations for use in 1-, 2-, 3- or arbitrary physical dimensions and also in a manner that supports exploitation of data-parallelism on fast modern processing devices. We report on data layouts and transformation algorithms that support both conventional and data-parallel memory layouts. We present our implementations expressed in both conventional serial C code as well as in NVIDIA's Compute Unified Device Architecture concurrent programming language for use on general purpose graphical processing units. We discuss: general memory layouts; specific optimizations possible for dimensions that are powers-of-two and common transformations, such as inverting, shifting and crinkling. We present performance data for some illustrative scientific applications of these layouts and transforms using several current GPU devices and discuss the code and speed scalability of this approach. Copyright © 2010 John Wiley & Sons, Ltd.
Year
DOI
Venue
2011
10.1002/cpe.1628
Concurrency and Computation: Practice and Experience
Keywords
DocType
Volume
present performance data,Hypercubic storage layout,cuda,gpus,fast modern processing device,conventional serial C code,physical science,crinkling,general memory layout,arbitrary dimension,hypercubic indexing.,Compute Unified Device Architecture,data-parallel memory layout,data-parallelism,arbitrary physical dimension,shifting,data layout,general purpose graphical processing
Journal
23
Issue
ISSN
Citations 
10
1532-0626
2
PageRank 
References 
Authors
0.56
22
2
Name
Order
Citations
PageRank
K. A. Hawick129366.26
D. P. Playne2756.13