Name
Abstract | ||
|---|---|---|
In this work we present a programmable and reconfigurable single instruction multiple data (SIMD) visual processor based on the S-CNN architecture, namely, the Simplicial CNN Digital Visual Processor (SCDVP), oriented to high-performance low-level image processing. The cells in the array have a selectable neighborhood configuration and several registers, which provide the chip with extended spatial and temporal processing capabilities, in particular optical flow. A prototype 64 × 64 cell chip with two program memories and a column adder was fabricated in a 90 nm technology, which running at 133 MHz delivers 105.5 GOPS. The calculation at the cell level is performed with time coded signals and the program memory is located outside the array. This produces a very efficient realization in terms of area: 53.8 GOPS per mm2, which outperforms all results reported so far. We show that even after normalization, to account for technology scaling, the proposed architecture is the most efficient among all reported digital processors. Computation performance to power ratio also exceeds all previous results with 817.8 GOPS/W. Experimental results of the working chip are reported. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TCSI.2013.2295959 | Circuits and Systems I: Regular Papers, IEEE Transactions |
Keywords | Field | DocType |
cellular neural nets,digital signal processing chips,image sequences,neural chips,neural net architecture,S-CNN architecture,SCDVP,SIMD,cellular neural networks,column adder,extended spatial processing capability,frequency 133 MHz,high-performance low-level image processing,optical flow,program memory,programmable single instruction multiple data visual processor,reconfigurable single instruction multiple data visual processor,simplicial CNN digital visual processor,size 90 nm,temporal processing capability,time coded signals,ASIC,Cellular neural networks (CNN),image processing,piecewise linear,pixel level processing,simplicial computation,vision chip | Normalization (statistics),Adder,Power ratio,Computer science,Image processing,SIMD,Electronic engineering,Chip,Optical flow,Computation | Journal |
Volume | Issue | ISSN |
61 | 7 | 1549-8328 |
Citations | PageRank | References |
4 | 0.45 | 8 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Martin Di Federico | 1 | 16 | 1.99 |
| P Julian | 2 | 140 | 27.51 |
| Pablo Sergio Mandolesi | 3 | 22 | 8.49 |
| Di Federico, M. | 4 | 5 | 0.84 |