國立高雄大學圖資館 |

Language: English

Back

GPGPU programming and the pitfalls o...

Gordon, Brian Patrick.

GPGPU programming and the pitfalls of naive data handling.

Record Type:	Electronic resources : Monograph/item
Title/Author:	GPGPU programming and the pitfalls of naive data handling.
Author:	Gordon, Brian Patrick.
Description:	57 p.
Notes:	Source: Masters Abstracts International, Volume: 48-06, page: 3797.
Notes:	Adviser: Sohum Sohoni.
Contained By:	Masters Abstracts International48-06.
Subject:	Engineering, Computer.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1477485
ISBN:	9781124052014

GPGPU programming and the pitfalls of naive data handling.
Gordon, Brian Patrick.

GPGPU programming and the pitfalls of naive data handling. - 57 p.

Source: Masters Abstracts International, Volume: 48-06, page: 3797.

Thesis (M.S.)--Oklahoma State University, 2010.

Scope and Method of Study. The purpose of this study was to implement a known bottleneck of a model based video encoder in code that runs on a modern graphics card using various methods. The study then looks the degree of speedup as well as the new bottlenecks for each implementation. The study also compares and contrasts the effectiveness of each method at improving the performance of the encoder.

ISBN: 9781124052014Subjects--Topical Terms:

384375
Engineering, Computer.

GPGPU programming and the pitfalls of naive data handling.
LDR:01940nmm 2200313 4500 001 280852
005 20110119095010.5
008 110301s2010 ||||||||||||||||| ||eng d
020 $a 9781124052014
035 $a (UMI)AAI1477485
035 $a AAI1477485
040 $a UMI $c UMI
100 1 $a Gordon, Brian Patrick. $3 492998
245 1 0 $a GPGPU programming and the pitfalls of naive data handling.
300 $a 57 p.
500 $a Source: Masters Abstracts International, Volume: 48-06, page: 3797.
500 $a Adviser: Sohum Sohoni.
502 $a Thesis (M.S.)--Oklahoma State University, 2010.
520 $a Scope and Method of Study. The purpose of this study was to implement a known bottleneck of a model based video encoder in code that runs on a modern graphics card using various methods. The study then looks the degree of speedup as well as the new bottlenecks for each implementation. The study also compares and contrasts the effectiveness of each method at improving the performance of the encoder.
520 $a Findings and Conclusions. While moving the highly parallel error calculation to the graphics card reduced the time required to perform the computation, the program still ran slower. Through analysis of the processors performance counters, the image data appears to move through system memory even though its origin and destination are in graphics memory. This inefficient handling of the data that should remain in graphics memory is removing any potential speedup from using the graphics card as a highly parallel coprocessor to accelerate the slowest part of the original program.
590 $a School code: 0664.
650 4 $a Engineering, Computer. $3 384375
650 4 $a Engineering, Electronics and Electrical. $3 226981
690 $a 0464
690 $a 0544
710 2 $a Oklahoma State University. $b Electrical Engineering. $3 492989
773 0 $t Masters Abstracts International $g 48-06.
790 1 0 $a Sohoni, Sohum, $e advisor
790 1 0 $a Johnson, Louis $e committee member
790 1 0 $a Chandler, Damon $e committee member
790 $a 0664
791 $a M.S.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1477485