Performance analysis of certain memory techniques on TCAM using memristor

Abstract

Storage and computer systems call for continuous advances in both data latency and energy efficiency. However, the main advantages of CMOS technologies, such as high packing density and processing speed, are desensitized mainly because of the increasingly prohibitive power density. For next generation storage and computer systems to be able to exhibit high performance data applications, it is necessary to continue innovations in the creation of new systems, circuits and architectures, as well as the search for new materials. The memristor, a memory resistance abbreviation, is a passive two-terminal device whose resistance is controlled by external electrical signals and has a non-volatile memory function. Highly productive associative search functions are widely implemented in Content Addressable Memories (CAMs). Content Addressable Memory accesses a stored data word based on its content, compares it with a search word and returns the address of the adapted word. This comparison and search operations are performed in the memory cell, without the aid of Arithmetic and Logic Unit. Due to this search-based memory, CAM can be a crucial circuit element in high speed search engines, database engines, artificial neural network for neuromorphic computing and other applications for the Internet of Things. newline