On-Chip Noise Sensor for Integrated Circuit Susceptibility Investigations

Dhia, Sonia Ben; Boyer, Alexandre; Vrignon, B.; Deobarro, M.; Dinh, Thanh Vinh

doi:10.1109/tim.2011.2172116

Cited by 33 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resolution of the measurement instrument is a critical consideration for a high-accurate measurement for the circuit, our experimental setup can provide a high-resolution thanks to its resolution of up to 100 uV per division. Noise reduction is another critical consideration in the field of measurement [ 29 , 30 , 31 , 32 , 33 ]. A clean target signal without significant noise interference can improve the measurement, thereby obtaining a reliable evaluation on the circuit.…”

Section: A Measurement-verified Perceptron Chipmentioning

confidence: 99%

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Geng

Sun

Nakatake

2020

Sensors

View full text Add to dashboard Cite

Perceptron is an essential element in neural network (NN)-based machine learning, however, the effectiveness of various implementations by circuits is rarely demonstrated from chip testing. This paper presents the measured silicon results for the analog perceptron circuits fabricated in a 0.6 μm/±2.5 V complementary metal oxide semiconductor (CMOS) process, which are comprised of digital-to-analog converter (DAC)-based multipliers and phase shifters. The results from the measurement convinces us that our implementation attains the correct function and good performance. Furthermore, we propose the multi-layer perceptron (MLP) by utilizing analog perceptron where the structure and neurons as well as weights can be flexibly configured. The example given is to design a 2-3-4 MLP circuit with rectified linear unit (ReLU) activation, which consists of 2 input neurons, 3 hidden neurons, and 4 output neurons. Its experimental case shows that the simulated performance achieves a power dissipation of 200 mW, a range of working frequency from 0 to 1 MHz, and an error ratio within 12.7%. Finally, to demonstrate the feasibility and effectiveness of our analog perceptron for configuring a MLP, seven more analog-based MLPs designed with the same approach are used to analyze the simulation results with respect to various specifications, in which two cases are used to compare to their digital counterparts with the same structures.

show abstract

Section: A Measurement-verified Perceptron Chipmentioning

confidence: 99%

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Geng

Sun

Nakatake

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…On-chip parametric sensing has been an important field of advancement, providing diverse and concrete support for feeding back the physical parameters needed by any runtime management scheme. In addition to detecting threshold crossing using voltage and thermal sensors to trigger simple actions such as throttling [26], it's also possible to sense a wider range of parameters including current/power [17], process variations [20], supply noise [4], voltage drop [23], transistor ageing [30] and electromagnetic induction [10]. More recently, reference-free sensing techniques have also been developed which would support better sensing under uncertain operating conditions, especially when no high-quality references can be had in terms of voltage, current or frequency [25].…”

Section: Introductionmentioning

confidence: 99%

Studying the Interplay of Concurrency, Performance, Energy and Reliability with ArchOn -- An Architecture-Open Resource-Driven Cross-Layer Modelling Framework

Rafiev

Iliasov

Romanovsky

et al. 2014

2014 14th International Conference on Application of Concurrency to System Design

View full text Add to dashboard Cite

The interplay between pairs of critical factors such as performance, energy and reliability within modern computing systems has always been an interesting topic of study. However, studying the interplay of all three factors together in a many-core, multi-layer design setting has been a relatively recent undertaking. This work explores the practical problems encountered in such studies and introduces the modelling framework ArchOn, which is based on a novel resource-driven graph representation. ArchOn facilitates the analysis and potentially design and synthesis of systems whose design domains are more conveniently organized into multiple layers or levels (e.g. application, OS, hardware, etc.) and potentially large scale and diverse types of concurrency. The layer-agnostic formalism helps designers reason about cross-layer issues and the resource-driven approach is advantageous for reasoning about such issues as energy and time. Example single-and multi-core case studies help explain and illustrate the method.

show abstract

“…However, current on-chip measurement techniques are not suitable for measuring the 2D on-chip EMI distribution in real time. Some techniques store the measured signals first and then read out them afterwards (1)(2)(3)(4)(5) (6).…”

Section: Introductionmentioning

confidence: 99%

Initial Designs of an on-Chip EMI Sensor Array

et al. 2014

View full text Add to dashboard Cite

The purpose of the on-chip EMI sensor array (OCEMISA) is to measure the 2-dimension profile of the EMI voltage in the on-chip power distribution network in real time. The feedback signal from a senser cell should reflect only its local EMI. Signals have to be grouped carefully. This paper presents two different designs of the OCEMISA. In the first design, sensor cell generates regular pulses as feedback. The time domain waveform is monitored. In the second design, the supply noise generated by the sensor cell is utilized as feedback. The spectrum is monitored. Designs are implemented with FPGA for validation check. Measurement results show that feedback signals faces synchronization and instability problems. Those problems come from the IC process variation and are influenced by the feedback scheme. With the presentation and analysis of those problems, the paper is intent to provide optimization directions to make OCEMISA practical.

show abstract

On-Chip Noise Sensor for Integrated Circuit Susceptibility Investigations

Cited by 33 publications

References 14 publications

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Studying the Interplay of Concurrency, Performance, Energy and Reliability with ArchOn -- An Architecture-Open Resource-Driven Cross-Layer Modelling Framework

Initial Designs of an on-Chip EMI Sensor Array

Contact Info

Product

Resources

About