DocumentCode :
1697872
Title :
Improving the throughput of flexible-precision DSPS via algorithm transformation
Author :
Aggarwal, M. ; Shanbha, Naresh ; Ahuja, Narendra
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Univ., Urbana, IL, USA
Volume :
5
fYear :
1998
Firstpage :
3069
Abstract :
In this paper, we have presented a systematic technique to improve throughput of signal/image processing algorithms when implemented on flexible precision hardware. Many image/signal processing algorithms need 8-16 bit precision while the DSPs available are of much higher precision (32 bit). Significant performance gain can be obtained if multiple low precision computations can be performed in one cycle of a high precision DSP. We have proposed a framework based on algorithm transformation techniques of unfolding and retiming to systematically map low precision algorithms onto high precision DSPs. The improvement in throughput obtained by this framework is linearly related to the ratio of precision used by the processor and that required by the algorithm. The efficacy of this technique has been demonstrated on a IIR filter. We have also established some theoretical bounds on the maximum throughput that can be achieved using the proposed methodology
Keywords :
IIR filters; image processing; signal processing; transforms; 16 bit; 32 bit; 8 bit; IIR filter; algorithm transformation; flexible-precision DSP; image processing; performance gain; retiming; signal processing; systematic technique; throughput; unfolding; Digital signal processing; Hardware; High performance computing; IIR filters; Performance gain; Pipeline processing; Signal processing; Signal processing algorithms; Throughput; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
ISSN :
1520-6149
Print_ISBN :
0-7803-4428-6
Type :
conf
DOI :
10.1109/ICASSP.1998.678174
Filename :
678174
Link To Document :
بازگشت