GridCuda: A Grid-Enabled CUDA Programming Toolkit

Author

Liang, Tyng-Yeu ; Chang, Yu-Wei

Author_Institution

Dept. of Electr. Eng., Kaohsiung, Taiwan

fYear

2011

fDate

22-25 March 2011

Firstpage

141

Lastpage

146

Abstract

A grid-enabled programming toolkit called GridCuda is proposed in this paper. This programming toolkit provides a platform for users to write programs with the CUDA API, and exploit GPGPU resources available in computational grids to execute their programs. Whenever the CUDA functions in user programs are invoked, they will be transparently redirected to remote GPGPUs for execution by means of remote procedure calls. This programming toolkit also supports multithreaded programming so that the work of a CUDA program can be distributed over multiple GPGPUs for parallel execution.

Keywords

application program interfaces; computer graphic equipment; coprocessors; grid computing; multi-threading; parallel architectures; resource allocation; CUDA API; GPGPU; GridCuda; computational grids; general purpose graphic processor unit; grid-enabled CUDA programming toolkit; multithreaded programming; remote procedure calls; transparent resource allocation; Driver circuits; Graphics processing unit; Instruction sets; Kernel; Programming; Resource management; Servers; CUDA; GPGPU; computational grids; multithreaded; transparent resource allocation;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Information Networking and Applications (WAINA), 2011 IEEE Workshops of International Conference on

Conference_Location

Biopolis

Print_ISBN

978-1-61284-829-7

Electronic_ISBN

978-0-7695-4338-3

Type

conf

DOI

10.1109/WAINA.2011.82

Filename

5763452