High Performance Pre-computation based Self-Controlled Precharge-Free Content-Addressable Memory

Abstract

Content-addressable memory (CAM) is a special type of memory used in networking
applications for very-high-speed searching operation. It compares input search data with the
table of stored data, and returns the address of matching data in a parallel search method.
Also the use of parallel comparison results in reduced search time, it also significantly
increases power consumption when compared to precharge based CAM. The low-power
NAND-type and high-speed NOR-type CAM methods require the precharge prior to the
search. This PF phase leads to increase the settling time of the output and also reduce the
speed of the search operation. In this paper, a High performance Pre-computation Based
Self-Controlled Precharge-Free CAM (PB-SCPF CAM) structure is proposed for high-speed
applications which reduce the settling time as well as improve the speed of the search. Where
search time is very important for designing larger word lengths, SCPF architecture is
efficacious in applications. The experimental results show that PB-SCPF approach can attain
on average 32% in power reduction and 80% in delay reduction. The most important
contribution of this project is that it offers theoretical and practical proofs to verify that our
suggested PB-SCPF CAM system can achieve greater power reduction without the
requirement of special CAM cell design. This shows that the approach which we have used is
more flexible and adaptive for general designs and high speed applications.