Opportunities in physical computing driven by analog realization

Hasler, Jennifer

doi:10.1109/icrc.2016.7738680

Cited by 22 publications

(13 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analog architecture theory is practical only given analog programmable and configurable technologies demonstrations [6], minimizing issues with device mismatch [7], as well as a starting foundation for analog computation [2]. The broad potential of large-scale Field Programmable Analog Arrays (FPAA, e.g., [6], Figure 2) required an analog computation framework (Figure 1).…”

Section: Digital Computationmentioning

confidence: 99%

“…Analog computing requires infrastructure building to reach a similar level of usability. Traditionally, analog required a miracle to occur by an expert [2], but This approach is not a practical technique for solving a wide range of energy-efficient computing applications ( Figure 1). O(•) got occasionally used, such as for vector-matrix multiplication ( [3][4][5]), but no general theory developed.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Analog Architecture Complexity Theory Empowering Ultra-Low Power Configurable Analog and Mixed Mode SoC Systems

Hasler

2019

JLPEA

Self Cite

View full text Add to dashboard Cite

This discussion develops a theoretical analog architecture framework similar to the well developed digital architecture theory. Designing analog systems, whether small or large scale, must optimize their architectures for energy consumption. As in digital systems, a strong architecture theory, based on experimental results, is essential for these opportunities. The recent availability of programmable and configurable analog technologies, as well as the start of analog numerical analysis, makes considering scaling of analog computation more than a purely theoretical interest. Although some aspects nicely parallel digital architecture concepts, analog architecture theory requires revisiting some of the foundations of parallel digital architectures, particularly revisiting structures where communication and memory access, instead of processor operations, that dominates complexity. This discussion shows multiple system examples from Analog-to-Digital Converters (ADC) to Vector-Matrix Multiplication (VMM), adaptive filters, image processing, sorting, and other computing directions.

show abstract

Section: Digital Computationmentioning

confidence: 99%

mentioning

confidence: 99%

Analog Architecture Complexity Theory Empowering Ultra-Low Power Configurable Analog and Mixed Mode SoC Systems

Hasler

2019

JLPEA

Self Cite

View full text Add to dashboard Cite

show abstract

“…A digital system emulating an analog system requires digital simulation of at least ODEs, which we established is a challenging problem for digital systems. The potential higher computing level of analog systems (real values) compared with digital systems (countable values) further illustrates the numerical difficulty [13].…”

Section: Simulation Tool Impact Of Analog and Digital Numericsmentioning

confidence: 99%

“…A factor of 1000 improvement in energy efficiency is roughly equivalent to the improvement from the start of DSP (1978) [12] to the digital energy efficiency wall of 10 MMAC (/s)/mW (MMAC = Million Multiply Accumulate). The computational capability of analog computation compared to digital computation (1000×) lower energy/power, 100× lower area) could possibly open the next wave of computing [13].…”

Section: Why Analog Numerical Analysis?mentioning

confidence: 99%

Starting Framework for Analog Numerical Analysis for Energy-Efficient Computing

Hasler

2017

JLPEA

Self Cite

View full text Add to dashboard Cite

Abstract:The focus of this work is to develop a starting framework for analog numerical analysis and related algorithm questions. Digital computation is enabled by a framework developed over the last 80 years. Having an analog framework enables wider capability while giving the designer tools to make reasonable choices. Analog numerical analysis concerns computation on physical structures utilizing the real-valued representations of that physical system. This work starts the conversation of analog numerical analysis, including exploring the relevancy and need for this framework. A complexity framework based on computational strengths and weaknesses builds from addressing analog and digital numerical precision, as well as addresses analog and digital error propagation due to computation. The complimentary analog and digital computational techniques enable wider computational capabilities.

show abstract

“…As shown later, Dig-Ns [2][3][4] in an ANN offer a wide frequency of operation, but are not energy-efficient in lower frequencies due to static leakage currents of high number of transistors. On the other hand, the use of mixed-signal circuitry for computing has been a topic of debate for more than two decades [5][6], as the efficiency gained in terms of energy is often overshadowed by the effects of noise and variability. However, due to the presence of multiple distributed connections from input to output in an ANN, it offers inherent error-resiliency towards noise/variability and hence the low power consumption of MS-N can be properly leveraged.…”

Section: Introductionmentioning

confidence: 99%

An Energy-Efficient Mixed-Signal Neuron for Inherently Error-Resilient Neuromorphic Systems

Chatterjee¹,

Panda²,

Maity³

et al. 2017

2017 IEEE International Conference on Rebooting Computing (ICRC)

View full text Add to dashboard Cite

This work presents the design and analysis of a mixed-signal neuron (MS-N) for convolutional neural networks (CNN) and compares its performance with a digital neuron (Dig-N) in terms of operating frequency, power and noise. The circuitlevel implementation of the MS-N in 65 nm CMOS technology exhibits 2-3 orders of magnitude better energy-efficiency over Dig-N for neuromorphic computing applications -especially at low frequencies due to the high leakage currents from many transistors in Dig-N. The inherent error-resiliency of CNN is exploited to handle the thermal and flicker noise of MS-N. A system-level analysis using a cohesive circuit-algorithmic framework on MNIST and CIFAR-10 datasets demonstrate an increase of 3% in worst-case classification error for MNIST when the integrated noise power in the bandwidth is ~ 1 µV 2 .

show abstract

Opportunities in physical computing driven by analog realization

Cited by 22 publications

References 54 publications

Analog Architecture Complexity Theory Empowering Ultra-Low Power Configurable Analog and Mixed Mode SoC Systems

Analog Architecture Complexity Theory Empowering Ultra-Low Power Configurable Analog and Mixed Mode SoC Systems

Starting Framework for Analog Numerical Analysis for Energy-Efficient Computing

An Energy-Efficient Mixed-Signal Neuron for Inherently Error-Resilient Neuromorphic Systems

Contact Info

Product

Resources

About