SHERP

Digital Signal Processing Filtering with GPU

Cited 0 time in webofscience Cited 0 time in scopus
Authors
Anwar, Sajid; Sung, Wonyong
Issue Date
2009-07
Publisher
대한전자공학회 = The Institute of Electronics Engineers of Korea
Citation
대한전자공학회 2009년 하계종합학술대회 2009. 7
Keywords
FIRIIRGPUCUDAHomogenous SolutionParticular SolutionGPGPU
Abstract
This work designed digital filter kernels with GTX 260 GPU. Various FIR and IIR kernels are implemented. IIR filters due to its recursive nature have dependency on previously computed output samples. The dependency problem can be solved by separate computation of particular and homogeneous solutions. Comparing to CPU based implementation experimental results show speed improvement of 3 to 40 times for IIR and FIR filter kernels respectively.
Language
English
URI
http://www.ieek.or.kr

http://hdl.handle.net/10371/6177
Files in This Item:
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Electrical and Computer Engineering (전기·정보공학부)Others_전기·정보공학부
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse