面向图像转置和分块处理的一种高效内存访问策略  被引量:3

An Efficient Memory Access Strategy for Transposition and Block Operation in Image Processing

在线阅读下载全文

作  者:沈煌辉[1,2] 王贞松[1] 郑为民[3] 

机构地区:[1]中国科学院计算技术研究所,北京100190 [2]中国科学院大学,北京100049 [3]广州中国科学院先进技术研究所,广州511458

出  处:《计算机研究与发展》2013年第1期188-196,共9页Journal of Computer Research and Development

摘  要:图像转置和图像分块处理在目前图像处理过程中是经常用到的两种操作.对于实时图像处理,图像转置和图像分块的效率直接影响到实时性,而图像转置和图像分块的效率和内存访问效率密切相关.而访存效率与计算机体系结构、存储器结构和实际操作策略有直接的关系.根据存储器的读写特性提出一种分段存储的高效内存访问策略,通过理论分析得出合理的分段长度,即图像转置时分段长度的选择与DDR2 SDRAM的型号有关;而图像分块时分段长度的选择则与数据块的大小有关.结合工程实际应用还推导了普适的总线地址与存储器物理地址之间的映射,同时给出了一种硬件实现方式,针对不同的应用,仅需要替换地址映射模块,具有一定的通用性和扩展性.分段存储方法已经在SAR实时成像压缩系统中得到有效的验证.Image transposition and image block processing are common operations in image processing. The efficiencies of image transposition and image block processing, which are closely related to memory access efficiency, directly affect the real-time of image processing, while memory access efficiency has direct relationship with computer architecture, memory structure and operational strategy. A segmented storage strategy for efficient memory accessing is proposed in this paper. The segmented storage is based on the read/write characteristics of memory, and the proper segmented length is calculated by theoretic analysis. When the image is transposed, the segmented length is related to the type of DDR2 SDRAM. When the image is partitioned, the segmented length is related to the size of image block. Combined with engineering application, universal mapping between bus address and memory address is deduced in this paper. Meanwhile, a hardware module is given to implement DDR2 SDRAM controller. It is only necessary to update address mapping module for different applications. So the segmented storage strategy has certain universality and expansibility, and is verified in the SAR real-time image process system.

关 键 词:图像转置 图像分块 内存访问 分段存储 地址映射 

分 类 号:TP333[自动化与计算机技术—计算机系统结构]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象