Name
Title | ||
|---|---|---|
A 305mV-850mV 400μW 45GSamples/J reconfigurable compressive sensing engine with early-termination for ultra-low energy target detection in 14nm tri-gate CMOS |
Abstract | ||
|---|---|---|
A reconfigurable compressive sensing engine for on-die acceleration of target threshold detection, feature extraction and depth perception is fabricated in 14nm Tri-Gate CMOS, and occupies 0.022mm
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
. Compressed-domain processing with sort-assisted thresholding, opportunistic early-termination using 3-stop checkpointing and in-line bound estimation enable 305mV-850mV operation with peak energy-efficiency of 45GSamples/J, measured at near-threshold operation of 340mV, resulting in 73× higher efficiency over conventional Nyquist-rate sensor digital front-ends. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/ASSCC.2016.7844183 | 2016 IEEE Asian Solid-State Circuits Conference (A-SSCC) |
Keywords | Field | DocType |
compressive sensing,target detection,thresholding,checkpointing,bound estimation | Object detection,Efficient energy use,Computer science,Electronic engineering,Real-time computing,Feature extraction,CMOS,Acceleration,Thresholding,Throughput,Compressed sensing | Conference |
ISBN | Citations | PageRank |
978-1-5090-3701-8 | 0 | 0.34 |
References | Authors | |
5 | 10 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sudhir Satpathy | 1 | 269 | 19.69 |
| S. Mathew | 2 | 462 | 76.59 |
| Vikram B. Suresh | 3 | 31 | 10.23 |
| Mark A. Anders | 4 | 185 | 17.43 |
| Gregory K. Chen | 5 | 298 | 32.96 |
| Himanshu Kaul | 6 | 456 | 51.07 |
| Amit Agarwal | 7 | 693 | 72.95 |
| S. K. Hsu | 8 | 521 | 52.06 |
| Ram Krishnamurthy | 9 | 650 | 74.63 |
| Vivek De | 10 | 3024 | 577.83 |