© The Institution of Engineering and Technology
This Letter presents the architecture implementation and testing of an single instruction multiple data (SIMD) processor for energy aware embedded morphological visual processing using the simplicial piece-wise linear approximation. The architecture comprises a linear array of 48 × 48 processing elements, each connected to an eight-neighbour clique operating on binary input and state data. The architecture is synthesised from a custom designed ultra low-voltage CMOS library and fabricated in a 55 nm CMOS technology. The chip is capable of dynamic voltage/frequency scaling with power supplies between 0.5 and 1.2 V. The fabricated chip achieves an overall performance of 293 TOPS/W with dynamic energy dissipation efficiency of 3.4 fJ per output operation at 0.6 V.
References
-
-
1)
-
1. Bojarski, M., Del Testa, D., Dworakowski, D., et al: ‘End to end learning for self-driving cars’, , April 2016.
-
2)
-
9. Ojala, T., Pietikäinen, M., Harwood, D.: ‘A comparative study of texture measures with classification based on feature distributions’, Pattern Recognit., 1996, 29, (1), pp. 51–59 (doi: 10.1016/0031-3203(95)00067-4).
-
3)
-
5. Serra, J.: ‘Online course on mathematical morphology’. 2017, .
-
4)
-
7. David, F.N., Kendall, M.G., Barton, D.E.: ‘Symmetric function and allied tables’ (Cambridge University Press, Cambridge, UK, 1968).
-
5)
-
4. Maragos, P.: ‘Tutorial on advances in morphological image processing and analysis’, Opt. Eng., 1987, 707, pp. 64–74.
-
6)
-
6. Atzori, L., Iera, A., Morabito, G.: ‘The internet of things: a survey’, Comput. Netw., 2010, 54, (15), pp. 2787–2805 (doi: 10.1016/j.comnet.2010.05.010).
-
7)
-
6. Julian, P., Dogaru, R., Chua, L.O.: ‘A piecewise-linear simplicial coupling cell for CNN gray-level image processing’, Trans. Circuits Syst. I Fundam. Theory Appl., 2002, 49, (7), pp. 904–913 (doi: 10.1109/TCSI.2002.800464).
-
8)
-
9. Di Federico, M., Mandolesi, P.S., Julian, P., et al: ‘Experimental results of simplicial CNN digital pixel processor’, Electron. Lett., 2008, 44, (1), pp. 27–29 (doi: 10.1049/el:20082097).
-
9)
-
10. Mandolesi, P.S., Julian, P., Andreou, A.G.: ‘A scalable and programmable simplicial CNN digital pixel processor architecture’, Trans. Circuits Syst. I Regul.Pap., 2004, 51, (5), pp. 988–996 (doi: 10.1109/TCSI.2004.827626).
-
10)
-
2. Andreou, A.G., Figliolia, T., Sanni, K., et al: ‘Bio-inspired system architecture for energy efficient, BIGDATA computing with application to wide area motion imagery’. Proc. 2016 IEEE LASCAS, 2016, pp. 1–6.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2017.4738
Related content
content/journals/10.1049/el.2017.4738
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Correspondence
This article has following corresponding article(s):
in brief