EVALUATION OF STRIP-MINING METHOD FOR VQ COMPRESSION ON AN SMP SYSTEM

Accession number;07A0187174
Title;EVALUATION OF STRIP-MINING METHOD FOR VQ COMPRESSION ON AN SMP SYSTEM
Author; WAKATANI AKIYOSHI (Konan Univ., Kobe, Jpn)
Journal Title;IEIC Technical Report (Institute of Electronics, Information and Communication Engineers)
Journal Code:S0532B
ISSN:0913-5685
VOL.106;NO.448(IE2006 138-184);PAGE.1-5(2007)
Figure&Table&Reference;
Pub. Country;Japan
Language;English
Abstract;Recent processors utilize a variety of parallel processing technologies to boost its performance, and thus it is required that multimedia applications can be efficiently parallelized and can be easily implemented on such a processor with parallel processing features. We implemented a parallel algorithm with "double strip-mining" method of optimal codeword search for VQ compression on a shared-memory parallel environment and evaluated the effectiveness of the parallel algorithm. We have two approaches for optimal codeword search: the p-dist approach and the c-dist approach. In general, the p-dist approach and the c-dist approach are suitable for a small codebook and a large codebook, respectively. Moreover, the p-dist approach with strip-mining method can achieve the same performance as the c-dist even for a large codebook, but the strip-mining method requires as large buffer area as the size of vectors. However, by applying strip-mining method to a loop with regard to vectors as well as that to codewords (double strip-mining), the buffer area can be reduced and results of our experiments find that this method can keep the same performance as the original strip-mining method with regard to the quality of the compression. (author abst.)