论文信息 - Low-power word-parallel nearest-Hamming-distance search circuit based on frequency mapping

Low-power word-parallel nearest-Hamming-distance search circuit based on frequency mapping

Distance-frequency mapping with ring oscillators, adjustable in discrete steps, enables fast word-parallel nearest-Hamming-distance search with low power consumption. High robustness against fabrication-related variations of the MOSFET characteristics is achieved in addition. A test chip in 180 nm CMOS technology with 64 words, each consisting of 256 bits, consumes less than 36.5 mW and 307 μW at supply voltages of 1.8 and 0.7 V, respectively. In comparison to previous digital designs, power dissipation is 5 times smaller, while search speed from 50ns to 245ns for Hamming distances from 0 to 256 is approximately equal.

Akio Kawabata | Tetsushi Koide | Hans Jurgen Mattausch | Tania Ansari | Wataru Imafuku

[1] H.J. Mattausch,et al. Fully-parallel pattern-matching engine with dynamic adaptability to Hamming or Manhattan distance , 2002, 2002 Symposium on VLSI Circuits. Digest of Technical Papers (Cat. No.02CH37302).

[2] M. Ikeda,et al. A high-speed and low-voltage associative co-processor with exact Hamming/Manhattan-distance estimation using word-parallel and hierarchical search architecture , 2004, IEEE Journal of Solid-State Circuits.

[3] M. Ikeda,et al. Time–domain minimum–distance detector and its application to low power coding scheme on chip interface , 1998, Proceedings of the 24th European Solid-State Circuits Conference.

[4] Donald R. Tveter. The pattern recognition basis of artificial intelligence , 1998 .

[5] M. Miura-Mattausch,et al. Correlating Microscopic and Macroscopic Variation With Surface-Potential Compact Model , 2009, IEEE Electron Device Letters.

[6] S. Nakahara,et al. A design for a minimum Hamming-distance search using asynchronous digital techniques , 2005, IEEE Journal of Solid-State Circuits.

[7] H.J. Mattausch,et al. Developing a Reliable Learning Model for Cognitive Classification Tasks Using an Associative Memory , 2007, 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing.