A word-parallel digital associative engine with wide search range based on Manhattan distance
A word-parallel digital associative engine with wide search range based on Manhattan distance
复制标题
基于曼哈顿距离的宽搜索范围的词并行数字联想引擎
DOI：
10.1109/cicc.2004.1358803
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
K. Asada
中科院分区：
文献类型：
--
作者：
Y. Oike;M. Ikeda;K. Asada
提出了一种具有精确和宽范围曼哈顿距离计算的字并行数字联想引擎。它执行连续搜索操作，不仅检测最近匹配的数据，而且检测按精确曼哈顿距离排序的所有数据。使用分层搜索路径的字并行数字实现提供了具有完美精度的高速搜索操作、低电压操作模式以及无限数据容量的潜在能力。字并行距离计算电路使用加权搜索时钟自动计算曼哈顿距离，以检测最接近的匹配数据。采用0.18/spl mu/m CMOS工艺制造了具有8位/spl次/32个元素的64个字的关联引擎，并成功进行了测试。在电源电压为 1.8 V 时，所有数据排序的最坏情况搜索时间为 5.85 /spl mu/s。
A word-parallel digital associative engine with accurate and wide-range Manhattan-distance computation is presented. It performs a continuous search operation to detect not only the nearest-match data but also all data in the sorted order of the exact Manhattan distance. The word-parallel digital implementation using a hierarchical search path provides a high-speed search operation with faultless precision, a low-voltage operation mode, and a potential capability of unlimited data capacity. Word-parallel distance calculation circuits autonomously count the Manhattan distance using a weighted search clock to detect the nearest-match data. An associative engine, with 64 words of 8 bit/spl times/32 element, has been fabricated using a 0.18 /spl mu/m CMOS process and successfully tested. The worst-case search time of all data sorting takes 5.85 /spl mu/s at a supply voltage of 1.8 V.
与基于神经关联处理器的硬件识别系统兼容的图像表示算法，
DOI：
--
发表时间：
2003
期刊：
IEEE Trans.Neural Networks Vol.14,No.4
影响因子：
--
作者：
Masakazu Yagi;Tadashi Shibata
通讯作者：
Tadashi Shibata