This Article 
 Bibliographic References 
 Add to: 
CAM2: A Highly-Parallel Two-Dimensional Cellular Automaton Architecture
July 1998 (vol. 47 no. 7)
pp. 788-801

Abstract—Cellular automaton (CA) is a promising computer paradigm that can break through the von Neumann bottleneck. Two-dimensional CA is especially suitable for application to pixel-level image processing. Although various architectures have been proposed for processing two-dimensional CA, there are no compact, practical computers. So, in spite of its great potential, CA is not widely used. This paper proposes a highly-parallel two-dimensional cellular automaton architecture called CAM2 and presents some evaluation results. CAM2 can attain pixel-order parallelism on a single board because it is composed of a CAM, which makes it possible to embed an enormous number processing elements (PEs), corresponding to CA cells, onto one VLSI chip. Multiple-zigzag mapping and dedicated CAM functions enable high-performance CA processing. The performance evaluation results show that 256k CA cells, which correspond to a 512 × 512 picture, can be processed by a CAM2 on a single board using deep submicron process technology. The processing speed is more than 10 billion CA cell updates per second. This means that more than a thousand CA-based image processing operations can be done on a 512 × 512 pixel image at video rates (33 msec). CAM2 will widen the potentiality of CA and make a significant contribution to the development of compact and high-performance systems.

[1] J. von Neumann, "The General Logical Theory of Automata," Cerebral Mechanisms in Behavior—The Hixon Symp., L.A. Jeffress, ed. New York: John Wiley&Sons, 1951.
[2] K. Preston Jr. et al., "Basics of Cellular Logic with Some Applications in Medical Image Processing," Proc. IEEE, vol. 67, no. 5, pp. 826-857, 1979.
[3] H. Harrer, "Multiple Layer Discrete-Time Cellular Neural Networks Using Time-Variant Templates," IEEE Trans. Circuits and Systems II, vol. 40, no. 3, pp. 191-199, 1993.
[4] H. Harrer, J.A. Nossek, T. Roska, and L.O. Chua, "A Current-Mode DTCNN Universal Chip," Proc. IEEE Int'l Symp. Circuits and Systems (ISCAS '94), vol. 4, pp. 135-138, 1994.
[5] J. Serra, Image Analysis and Mathematical Morphology.London: Academic Press, 1982.
[6] P. Maragos, "Tutorial on Advances in Morphological Image Processing and Analysis," Optical Eng., vol. 26, 1987.
[7] K. Preston Jr., "Cellular Logic Computers for Pattern Recognition," Computer, vol. 16, no. 1, pp. 36-47, Jan. 1983.
[8] M.J.B. Duff et al., "Review of the CLIP Image Processing System," Proc. Nat'l Computer Conf., pp. 1,055-1,060, 1978.
[9] K.E. Batcher, "Design of a Massively Parallel Processor," IEEE Trans. Computers, vol. 29, no. 9, pp. 836-840, Sept. 1980.
[10] T. Kondo et al., "Pseudo MIMD Array Processor-AAP2," Proc. 13th Symp. Computer Architecture Conf., pp. 330-337, 1986.
[11] Thinking Machines Corp., "Connection Machine Model CM-2 Technical Summary," v. 5.1, 1989.
[12] J. Nickolls, "The Design of the MasPar MP-1," Proc. 35th IEEE CS Int'l Conf., COMP-CON '90, pp. 25-28, 1990.
[13] S.R. Sternberg, "Biomedical Image Processing," Computer, vol. 16, no. 1, pp. 22-34, Jan. 1983.
[14] T. Toffoli and N. Margolus, Cellular Automata Machines, MIT Press, Cambridge, Mass., 1987.
[15] R. Etienne-Cummings et al., "A Foveated Visual Tracking Chip," Proc. IEEE Int'l Solid-State Circuits Conf. (ISSCC '97), pp. 38-39, 1997.
[16] K. Aizawa et al., "Implementations of on Sensor Image Compression and Comparisons Between Pixel and Column Parallel Architectures," Proc. IEEE Int'l Conf. Image Processing (ICIP-97), vol. 2, pp. 258-261, 1997.
[17] T. Komuro, I. Ishii, and M. Ishikawa, "Vision Chip Architecture Using General-Purpose Processing Elements for 1ms Vision System," Proc. Computer Architectures for Machine Perception (CAMP '97), pp. 276-279, 1997.
[18] G. Estrin and R.H. Fuller, "Some Applications for Content Addressable Memory," Proc. FJCC, pp. 495-508, 1963.
[19] T. Ogura, S. Yamada, and T. Nikaido, "A 4-kbit Associative Memory LSI," IEEE J. Solid-State Circuits, vol. 20, no. 6, pp. 1,277-1,282, 1985.
[20] H. Kadota, J. Miyake, Y. Nishimichi, H. Kudoh, and K. Kagawa, "An 8-kbit Content-Addressable and Reentrant Memory," IEEE J. Solid-State Circuits, vol. 20, no. 6, pp. 951-963, 1985.
[21] H. Yamada et al., "Real-Time String Search Engine LSI for 800-Mbit/sec LANs," Proc. IEEE Custom Integrated Circuits Conf. (CICC '88), pp. 21.6.1-21.6.4, 1988.
[22] T. Ogura, "A 20 K-B Associative Memory LSI for Artificial Intelligence Machines," IEEE J. Solid State Circuits, Vol. 24, Aug. 1990, pp. 1014-1020.
[23] T. Yamagata et al., "A 288-kb Fully Parallel Content Addressable Memory Using a Stacked-Capacitor Cell Structure," IEEE J. Solid-State Circuits, vol. 27, no. 12, pp. 1,927-1,933, 1992.
[24] S. Ushijima et al., "High-Performance Connectionless Server for Public ATM Networks and Its Application to Multiple Services Support in Heterogeneous Networking Environments," Proc. Second Int'l Symp. Interworking, 1994.
[25] T. Ogura, M. Nakanishi, T. Baba, Y. Nakabayashi, and R. Kasai, "A 336-kbit Content Addressable Memory for Highly Parallel Image Processing," Proc. IEEE Custom Integrated Circuits Conf. (CICC '96), vol. 13.4.1, pp. 273-276, 1996.
[26] Y. Fujino, T. Ogura, and T. Tsuchiya, "Facial Image Tracking System Architecture Utilizing Real-Time Labeling," Proc. SPIE Visual Comm. and Image Processing (VCIP '93), 1993.
[27] M. Nakanishi and T. Ogura, "A Real-Time CAM-Based Hough Transform Algorithm and Its Performance Evaluation," Proc. 13th Int'l Conf. Pattern Recognition (ICPR '96), vol. 2, pp. 516-521, 1996.
[28] M. Nakanishi and T. Ogura, "Real-Time Extraction Using a Highly Parallel Hough Transform Board," Proc. IEEE Int'l Conf. Image Processing (ICIP-97), vol. 2, pp. 582-585, 1997.
[29] M. Meribout, T. Ogura, and M. Nakanishi, "Real-Time Hough Transform Based Circular Shape Extraction," Proc. IAPR Workshop Machine Vision Applications (MVA '96), pp. 178-182, 1996.
[30] M. Meribout, M. Nakanishi, and T. Ogura, "Hough Transform Implementation on a Reconfigurable Highly Parallel Architecture," Proc. Computer Architectures for Machine Perception (CAMP '97), pp. 276-279, 1997.
[31] E. Hosoya, T. Ogura, and M. Nakanishi, "Real-Time 3D Feature Extraction Hardware Algorithm with Feature Point Matching Capability," Proc. IAPR Workshop Machine Vision Applications (MVA '96), pp. 430-433, 1996.
[32] T. Ogura and M. Nakanishi, "CAM-Based Highly-Parallel Image Processing Hardware," IEICE Trans. Electron, vol. E80-C, no. 7, pp. 868-874, 1997.
[33] E.R. Dougherty and P.A. Laplante, Real-Time Imaging. SPIE and IEEE Press, 1995.
[34] T. Ikenaga and T. Ogura, "CAM2: A Highly-Parallel 2D Cellular Automata Architecture for Real-Time and Palm-Top Pixel-Level Image Processing," Lecture Notes in Computer Scicence 1124: Proc. Euro-Par '96, vol. 2, pp. 203-666, 1996.
[35] T. Ikenaga and T. Ogura, "Discrete-Time Cellular Neural Networks Using HIghly-Parallel 2D Cellular Automata CAM2," Proc. Int'l Symp. Nonlinear Theory and Its Applications (NOLTA '96), pp. 221-224, 1996.
[36] T. Ikenaga and T. Ogura, "Real-Time Morphology Processing Using Highly Parallel 2D Cellular Automata CAM2," Proc. IEEE Int'l Conf. Image Processing (ICIP-97), vol. 2, pp. 562-565, 1997.
[37] E. Sternheim, R. Singh, R. Madhavan, and Y. Trivedi, Digital Design and Synthesis with Verilog HDL.San Jose, Calif.: Automata Publishing, 1993.

Index Terms:
Cellular automaton, content addressable memory, real-time image processing, SIMD, multiple-zigzag mapping.
Takeshi Ikenaga, Takeshi Ogura, "CAM2: A Highly-Parallel Two-Dimensional Cellular Automaton Architecture," IEEE Transactions on Computers, vol. 47, no. 7, pp. 788-801, July 1998, doi:10.1109/12.709379
Usage of this product signifies your acceptance of the Terms of Use.