Accelerating MATLAB Image Processing Toolbox functions on GPUs

Authors:
Jingfei Kong;Martin Dimitrov;Yi Yang;Janaka Liyanage;Lin Cao;Jacob Staples;Mike Mantor;Huiyang Zhou
Affiliations:
University of Central Florida;University of Central Florida;North Carolina State University;University of Central Florida;University of Central Florida;University of Central Florida;AMD;North Carolina State University
Venue:
Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units
Year:
2010

Citing 4
Cited 3

Jump flooding in GPU with applications to Voronoi diagram and distance transform

I3D '06 Proceedings of the 2006 symposium on Interactive 3D graphics and games
Scan primitives for GPU computing

Proceedings of the 22nd ACM SIGGRAPH/EUROGRAPHICS symposium on Graphics hardware
2D Euclidean distance transform algorithms: A comparative survey

ACM Computing Surveys (CSUR)
Fast scan algorithms on graphics processors

Proceedings of the 22nd annual international conference on Supercomputing

fMRI analysis on the GPU-Possibilities and challenges

Computer Methods and Programs in Biomedicine
JaBEE: framework for object-oriented Java bytecode compilation and execution on graphics processor units

Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units
Three-dimensional thinning algorithms on graphics processing units and multicore CPUs

Concurrency and Computation: Practice & Experience

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present our effort in developing an open-source GPU (graphics processing units) code library for the MATLAB Image Processing Toolbox (IPT). We ported a dozen of representative functions from IPT and based on their inherent characteristics, we grouped these functions into four categories: data independent, data sharing, algorithm dependent and data dependent. For each category, we present a detailed case study, which reveals interesting insights on how to efficiently optimize the code for GPUs and highlight performance-critical hardware features, some of which have not been well explored in existing literature. Our results show drastic speedups for the functions in the data-independent or data-sharing category by leveraging hardware support judiciously; and moderate speedups for those in the algorithm-dependent category by careful algorithm selection and parallelization. For the functions in the last category, fine-grain synchronization and data-dependency requirements are the main obstacles to an efficient implementation on GPUs.