首页 | 本学科首页   官方微博 | 高级检索  
     

基于多个 DSP 的图像处理 SIMD 并行结构
引用本文:陈益新,陈思培,李雯,张桂林. 基于多个 DSP 的图像处理 SIMD 并行结构[J]. 华中科技大学学报(自然科学版), 1997, 0(Z1)
作者姓名:陈益新  陈思培  李雯  张桂林
作者单位:Chen Yixin Inst. of Image Recognition & AI,HUST,Wuhan 430074,China. Chen Sipei Li Wen Zhang Guilin
摘    要:通过分析低层图像处理算法特点,指出标准SIMD结构不能完成某些低层图像处理算法的数据综合任务,提出的改进型SIMD结构增加了多指令控制、共享存储器单元,能执行更多种类图像处理算法,讨论了图像在SIMD结构计算机上的一维、二维分块方法,结果表明一维图像分块在互连网络硬件量、算法执行速度两方面更具优越性.

关 键 词:图像处理;单指令多数据流计算机;互连网络;共享存储器

An Improved SIMD Image Processing Computer Architecture
Chen Yixin Inst. of Image Recognition , AI,HUST,Wuhan ,China. Chen Sipei Li Wen Zhang Guilin. An Improved SIMD Image Processing Computer Architecture[J]. JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE, 1997, 0(Z1)
Authors:Chen Yixin Inst. of Image Recognition & AI  HUST  Wuhan   China. Chen Sipei Li Wen Zhang Guilin
Affiliation:Chen Yixin Inst. of Image Recognition & AI,HUST,Wuhan 430074,China. Chen Sipei Li Wen Zhang Guilin
Abstract:Based on an analysis of the specific features of a low level image processing algorithm, it is suggested by the authors that the standard SIMD is incapable of accomplishing the data synthesizing tasks required. An improved SIMD architecture with multiple instruction control and a sharing memory is presented, which will be able to implement many kinds of image processing algorithms. The 1 D and 2 D image blocking schemes are discussed. The results show that 1 D image blocking is better in terms of the amount of hard ware in the interconnection network and the implementation speed for some algorithms. with the LUT technique, a flexible and simple arbitrating circuit for the sharing memory is designed. The speed up ratio and programmable ability of the architecture proposed for the image processing algorithms are briefly discussed.
Keywords:image processing  SIMD computer  interconnection network  sharing memory
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号