Abstract:
Content-addressable memory (CAM) is a hardware searchengine used for parallel lookup that assures high-speed match but at the cost of higher power consumption. Both low p...Show MoreMetadata
Abstract:
Content-addressable memory (CAM) is a hardware searchengine used for parallel lookup that assures high-speed match but at the cost of higher power consumption. Both low power NAND-type and highspeed NOR-type match-line (ML) schemes suffer from requirement of the precharge prior to the search. Recently, a precharge-free ML structure has been proposed but with inadequate search performance. In this brief, a self-controlled precharge-free CAM (SCPF-CAM) structure is proposed for high-speed applications. The proposed architecture is useful in applications where search time is very crucial to design larger word lengths. The proposed 128×32-bit SCPF-CAM structure has been implemented using predictive 45-nm CMOS process and simulated in SPECTRE at the supply voltage of 1 V. The ML delay using the proposed SCPF-CAM architecture has been reduced by 88% and 73% compared to the precharge-free and traditional NAND-type ML structure.
Published in: IEEE Transactions on Very Large Scale Integration (VLSI) Systems ( Volume: 25, Issue: 8, August 2017)