Mismatch-Induced Trade-Offs and Scalability of Analog Preprocessing Visual Microprocessor Chips

This paper explores trade-offs associated with the scaling of the interaction circuits (synaptic transconductance multipliers) in visual microprocessor chips. These trade-offs are related to the necessity of maintaining analog accuracy of these circuits while taking advantage of the possibility of reducing power consumption, increasing operational speed, and reducing the area occupation, as technologies scale down into the deep submicron range.The paper does not aim to forecast the evolution of the design of general analog and mixed-signal integrated circuits in submicron technologies. It focuses on a very specific aspect of a particular type of systems. Hence, although the conclusions of the paper might appear somewhat pessimistic, deep submicron technologies define scenarios, not covered in this paper, where analog and mixed-signal circuits can take significant advantages from technology scaling. Even for the systems targeted in this paper, improvements in terms of power consumption and overall operational speed can be achieved through the use of newer architectures and circuit techniques.

[1]  Carver Mead.  Scaling of MOS technology to submicrometer feature sizes , 1994, J. VLSI Signal Process..

[2]  Ángel Rodríguez-Vázquez,et al.  ACE4k: An analog I/O 64×64 visual microprocessor chip with 7-bit analog accuracy , 2002, Int. J. Circuit Theory Appl..

[3]  Tamás Roska,et al.  Towards the Visual Microprocessor , 2000 .

[4]  Chenming Hu,et al.  Future CMOS scaling and reliability , 1993, Proc. IEEE.

[5]  Michiel Steyaert,et al.  Impact of transistor mismatch on the speed-accuracy-power trade-off of analog CMOS circuits , 1996, Proceedings of Custom Integrated Circuits Conference.

[6]  Ángel Rodríguez-Vázquez,et al.  ACE4k: An analog I/O 64×64 visual microprocessor chip with 7-bit analog accuracy: Research Articles , 2002 .

[7]  A. Rodriguez-Vazquez,et al.  Four-quadrant one-transistor-synapse for high-density CNN implementations , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[8]  Alireza Moini,et al.  Vision Chips , 1999 .

[9]  Ángel Rodríguez-Vázquez,et al.  A 0.8-μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage , 1997, IEEE J. Solid State Circuits.

[10]  S. Espejo,et al.  Architectural and Basic Circuit Considerations for a Flexible 128 × 128 Mixed-Signal SIMD Vision Chip , 2002 .

[11]  F. Werblin,et al.  Vertical interactions across ten parallel, stacked representations in the mammalian retina , 2001, Nature.

[12]  Michel Steyaert,et al.  Speed-Power-Accuracy Trade-off in High-Speed Analog-to-Digital Converters; Now and in the future.. , 2000 .

[13]  P. Kinget,et al.  An analog parallel array processor for real-time sensor signal processing , 1996, 1996 IEEE International Solid-State Circuits Conference. Digest of TEchnical Papers, ISSCC.

[14]  M.J.M. Pelgrom,et al.  Matching properties of MOS transistors , 1989 .