PROJECT TITLE :
Algorithm and Architecture for a Low-Power Content-Addressable Memory Based on Sparse Clustered Networks
We propose a low-power content-addressable memory (CAM) employing a replacement algorithm for associativity between the input tag and therefore the corresponding address of the output knowledge. The proposed design is based on a recently developed sparse clustered network using binary connections that on-average eliminates most of the parallel comparisons performed throughout a probe. Therefore, the dynamic energy consumption of the proposed style is considerably lower compared with that of a typical low-power CAM style. Given an input tag, the proposed architecture computes a few prospects for the placement of the matched tag and performs the comparisons on them to locate a single valid match. TSMC sixty five-nm CMOS technology was used for simulation functions. Following a choice of style parameters, such as the number of CAM entries, the energy consumption and therefore the search delay of the proposed style are 8percent, and 26% of that of the standard NAND architecture, respectively, with a tenp.c space overhead. A design methodology primarily based on the silicon space and power budgets, and performance requirements is mentioned.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here