Energy-Efficient Hybrid Analog/Digital Approximate Computation in Continuous Time

Ning Guo, Yipeng Huang, Tao Mai, Sharvil Patil, Chi Cao, Mingoo Seok, Simha Sethumadhavan, Yannis Tsividis

Research output: Contribution to journalArticlepeer-review

42 Scopus citations

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 μs to several hundred μs, 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.

Original languageEnglish (US)
Article number7463004
Pages (from-to)1514-1524
Number of pages11
JournalIEEE Journal of Solid-State Circuits
Volume51
Issue number7
DOIs
StatePublished - Jul 2016
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Keywords

  • Analog computation
  • continuous-time computation
  • continuous-time digital
  • energy-efficient computation
  • hybrid computation
  • low-energy computation
  • nonlinear function generation

Fingerprint

Dive into the research topics of 'Energy-Efficient Hybrid Analog/Digital Approximate Computation in Continuous Time'. Together they form a unique fingerprint.

Cite this