基于AltiVec技术的小波变换优化算法  

An Optimized Algorithm of Wavelet Transform Based on Altivec

作　　者：谢学军[1] 孙加兴[1] 李滨[1] 黄蕾[1] 樊治平[1] 

机构地区：[1]工业和信息化部软件与集成电路促进中心,集成电路部,北京100038

出　　处：《中国集成电路》2009年第8期54-57,61,共5页China lntegrated Circuit

摘　　要：小波变换克服了传统傅立叶变换的缺点,具有良好的时频局部化性能,从而使得小波理论在图像处理领域得到广泛的应用。PowerPC G4系列以后的CPU中增加了SIMD扩展指令集,并命名为AltiVec技术,利用这些指令可以显著提高需要处理大量数据运算的软件的效率。本文提出了一种基于AltiVec技术的小波变换优化算法,实验结果表明此算法是行之有效的。The Wavelet Transform overcomes the disadvantage of the traditional Fourier Transform and has very good time-frequency localization performance, which brings the Wavelet Theory into the image processing fields. PowerPC G4＇s and higher families extend the SIMD instruction set in CPU, which is named as AhiVec. With these instructions we can improve the efficiency of the software dealing with a large amount of data. This paper proposes an optimized algorithm based on AhiVec technology for wavelet transform, and the experiment result indicates that it works well.

关 键 词：多分辨分析 小波变换 POWERPC Altivec 

分 类 号：TN911.7[电子电信—通信与信息系统]