大きなノイズマージンを有するハミング距離検索機能付き内容照合メモリ(CAM)の構成法とその照合特性(<特集>通信(コミュニケーション)工学特集)

概要

論文の詳細を見る
In content addressable memory (CAM), large amounts of stored data are compared with an input data in parallel, and the contents and/or the addresses of any matches are then output. Such lookup capability is useful in many applications, including cache tag tables, image pattern recognition, artificial intelligence, packet switching in communication networks and hardware date base accelerators. In this paper, we propose a Hamming distance search CAM with large noise margin. The CAM can compare stored date and an input date in parallel, and find stored date with Hamming distance within a certain range ("near match"). Also, the interrogation characteristics of the CAM are analyzed in detail. Furthermore, the results obtained from these analyses are fully confirmed by simulation using the circuit analysis program HSPICE.
東海大学の論文
2003-09-30