Paper Info
Title
Energy-Efficient Hybrid Analog/Digital Approximate Computation in Continuous Time.
Abstract
We present a unit that performs continuous-time hybrid approximate computation, in which both analog and digital signals are functions of continuous time. Our 65 nm CMOS prototype system is capable of solving nonlinear differential equations up to 4th order, and is scalable to higher orders. Nonlinear functions are generated by a programmable, clockless, continuous-time 8-bit hybrid architecture (ADC + SRAM + DAC). Digitally assisted calibration is used in all analog/mixed-signal blocks. Compared to the prior art, our chip makes possible arbitrary nonlinearities and achieves 16× lower power dissipation, thanks to technology scaling and extensive use of class-AB analog blocks. Typically, the unit achieves a computational accuracy of about 0.5% to 5% RMS, solution times from a fraction of 1 s to several hundred s, and total computational energy from a fraction of 1 nJ to hundreds of nJ, depending on equation details. Very significant advantages are observed in computational speed and energy (over two orders of magnitude and over one order of magnitude, respectively) compared to those obtained with a modern microcontroller for the same RMS error.
Year
DOI
Venue
2016
10.1109/JSSC.2016.2543729
J. Solid-State Circuits
Keywords
Field
DocType
Analog computation,continuous-time computation,continuous-time digital,energy-efficient computation,hybrid computation,low-energy computation,nonlinear function generation
Nonlinear system,Analog device,Analog multiplier,Hybrid computer,Computer science,Digital signal,CMOS,Electronic engineering,Analog computer,Analog signal processing
Journal
Volume
Issue
ISSN
51
7
0018-9200
Citations 
PageRank 
References 
11
0.73
6
Authors
8
Name
Order
Citations
PageRank
Ning Guo1151.23
Yipeng Huang2110.73
Tao Mai3151.91
Sharvil Patil4284.73
Chi Cao5110.73
Mingoo Seok660180.71
Simha Sethumadhavan792554.24
Yannis P. Tsividis833373.63