Abstract: A CAM compares input search data in parallel against a table of stored data and returns the address of the matching data. A BCAM stores and searches only “0”s and “1”s. A TCAM can store and search an additional state, called “don’t care” so that a TCAM can perform partial matching. CAM offers high search speed in a single clock cycle, so CAMs are much faster than other search systems. Therefore CAMs are used in a wide variety of applications. Due to its parallel ML comparison 46% of power is consumed by the ML sensing structure, so TCAM is power hungry. This work proposes a Pai-Sigma ML scheme to reduce the compare power of a TCAM. The proposed ML does not incur the issues of charge sharing and short circuit current. Moreover, the switching activity of the search lines of a TCAM with the proposed MLs is low. A 3x3-bit Hybrid-type TCAM with the Parallel Pai-Sigma MLs is implemented to demonstrate the low-power feature. Results show that the compare power of the Hybrid-type TCAM can achieve 60% energy reduction compared with the conventional NOR-type TCAM. Also, the power consumption of the Hybrid-type TCAM is only 9.3962 µW.
Keywords: Ternary Content Addressable Memory (TCAM), Binary Content addressable Memory (BCAM), Random Access Memory, NOR-type TCAM, NAND-type TCAM, Hybrid-type TCAM, Match-line (ML), Search-line (SL), Bit-line (BL).
Title: Design and Implementation of Low Power Hybrid-Type Ternary Content Addressable Memory Using Pai-Sigma Match-Line Sensing Scheme
Author: Yashaswini H G, Aswatha Kumar M, B N Shobha
International Journal of Electrical and Electronics Research
ISSN 2348-6988 (online)
Research Publish Journals
