In the conventional content-addressable memory (CAM), equal power is consumed to determine if a stored word is matched to a search word or mismatched, independent of the number of mismatched bits. This paper presents a match-line (ML) sensing scheme that allocates less power to match decisions involving a larger number of mismatched bits. Since the majority of CAM words are mismatched, this scheme results in a significant CAM power reduction. The proposed ML sensing scheme is implemented in a 256 144-bit ternary CAM for a 0.13-m 1.2-V CMOS logic process. For a 2-ns search time on a 144-bit word, the proposed scheme saves 60% of the power consumed by the conventional sensing scheme.Index Terms-Associative memory, content-addressable memory (CAM), current sensing, high speed, low power, match-line sensing, mismatch dependent, neural network, pattern matching, string matching.