scholarly journals A Low-Voltage, Low-Power Reconfigurable Current-Mode Softmax Circuit for Analog Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1004
Author(s):  
Massimo Vatalaro ◽  
Marco Lanuzza ◽  
Felice Crupi ◽  
Tatiana Moposita ◽  
Lionel Trojman ◽  
...  
Keyword(s):  
Low Power ◽  
Modular Design ◽  
Low Voltage ◽  
Supply Voltage ◽  
Current Mode ◽  
Cmos Technology ◽  
Chip Area ◽  
Analog Implementation ◽  
Efficient Option ◽  
P Type

This paper presents a novel low-power low-voltage analog implementation of the softmax function, with electrically adjustable amplitude and slope parameters. We propose a modular design, which can be scaled by the number of inputs (and of corresponding outputs). It is composed of input current–voltage linear converter stages (1st stages), MOSFETs operating in a subthreshold regime implementing the exponential functions (2nd stages), and analog divider stages (3rd stages). Each stage is only composed of p-type MOSFET transistors. Designed in a 0.18 µm CMOS technology (TSMC), the proposed softmax circuit can be operated at a supply voltage of 500 mV. A ten-input/ten-output realization occupies a chip area of 2570 µm2 and consumes only 3 µW of power, representing a very compact and energy-efficient option compared to the corresponding digital implementations.

An Ultra-Low-Voltage Low-Power Current-Mode True RMS-to-DC Converter

2016 ◽  
Vol 25 (06) ◽  
pp. 1650066 ◽  
Author(s):  
Pantre Kompitaya ◽  
Khanittha Kaewdang
Keyword(s):  
Integrated Circuits ◽  
Low Power ◽  
High Performance ◽  
Dynamic Range ◽  
Low Voltage ◽  
Supply Voltage ◽  
Circuit Complexity ◽  
Current Mode ◽  
Cmos Technology ◽  
Low Supply Voltage

A current-mode CMOS true RMS-to-DC (RMS: root-mean-square) converter with very low voltage and low power is proposed in this paper. The design techniques are based on the implicit computation and translinear principle by using CMOS transistors that operate in the weak inversion region. The circuit can operate for two-quadrant input current with wide input dynamic range (0.4–500[Formula: see text]nA) with an error of less than 1%. Furthermore, its features are very low supply voltage (0.8[Formula: see text]V), very low power consumption ([Formula: see text]0.2[Formula: see text]nW) and low circuit complexity that is suitable for integrated circuits (ICs). The proposed circuit is designed using standard 0.18[Formula: see text][Formula: see text]m CMOS technology and the HSPICE simulation results show the high performance of the circuit and confirm the validity of the proposed design technique.

scholarly journals Investigation of PVT-Aware STT-MRAM Sensing Circuits for Low-VDD Scenario

Micromachines ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 551
Author(s):  
Zhongjian Bian ◽  
Xiaofeng Hong ◽  
Yanan Guo ◽  
Lirida Naviner ◽  
Wei Ge ◽  
...  
Keyword(s):  
Nonvolatile Memory ◽  
High Speed ◽  
Low Voltage ◽  
Supply Voltage ◽  
Random Access ◽  
Magnetic Tunnel Junction ◽  
Complementary Metal Oxide Semiconductor ◽  
Current Mode ◽  
Cmos Technology ◽  
Oxide Semiconductor

Spintronic based embedded magnetic random access memory (eMRAM) is becoming a foundry validated solution for the next-generation nonvolatile memory applications. The hybrid complementary metal-oxide-semiconductor (CMOS)/magnetic tunnel junction (MTJ) integration has been selected as a proper candidate for energy harvesting, area-constraint and energy-efficiency Internet of Things (IoT) systems-on-chips. Multi-VDD (low supply voltage) techniques were adopted to minimize energy dissipation in MRAM, at the cost of reduced writing/sensing speed and margin. Meanwhile, yield can be severely affected due to variations in process parameters. In this work, we conduct a thorough analysis of MRAM sensing margin and yield. We propose a current-mode sensing amplifier (CSA) named 1D high-sensing 1D margin, high 1D speed and 1D stability (HMSS-SA) with reconfigured reference path and pre-charge transistor. Process-voltage-temperature (PVT) aware analysis is performed based on an MTJ compact model and an industrial 28 nm CMOS technology, explicitly considering low-voltage (0.7 V), low tunneling magnetoresistance (TMR) (50%) and high temperature (85 °C) scenario as the worst sensing case. A case study takes a brief look at sensing circuits, which is applied to in-memory bit-wise computing. Simulation results indicate that the proposed high-sensing margin, high speed and stability sensing-sensing amplifier (HMSS-SA) achieves remarkable performance up to 2.5 GHz sensing frequency. At 0.65 V supply voltage, it can achieve 1 GHz operation frequency with only 0.3% failure rate.

A CMOS Automatic Gain Control Circuit for Biomedical Applications

2015 ◽  
Vol 645-646 ◽  
pp. 1308-1313
Author(s):  
Zhi Qiang Gao ◽  
Fu Xiang Huang ◽  
Jing Li ◽  
Liang Yin ◽  
Xiao Wei Liu
Keyword(s):  
Exponential Function ◽  
Biomedical Applications ◽  
Low Voltage ◽  
Supply Voltage ◽  
Automatic Gain Control ◽  
Gain Control ◽  
Cmos Technology ◽  
Chip Area ◽  
Gain Variation ◽  
Linearity Error

In this paper, a low-voltage automatic gain control (AGC) circuits is presented. The proposed circuit uses a novel approximated exponential function to increase the dB-linear output range. The three-stage AGC is fabricated in 0.18μm CMOS technology and shows the maximum gain variation of more than 100dB and a 67dB linear range with linearity error of less than ±1dB. The range of gain variation can be controlled from 34 to 101dB. The AGC dissipates less than 2.3mA under 1.8V supply voltage while occupying 0.4mm2 of chip area.

A LOW POWER CRYOGENIC CMOS ROIC DESIGN FOR 512 × 512 IRFPA

2013 ◽  
Vol 22 (10) ◽  
pp. 1340033 ◽  
Author(s):  
HONGLIANG ZHAO ◽  
YIQIANG ZHAO ◽  
YIWEI SONG ◽  
JUN LIAO ◽  
JUNFENG GENG
Keyword(s):  
Power Consumption ◽  
Low Power ◽  
Integrated Circuit ◽  
High Performance ◽  
Supply Voltage ◽  
Cmos Technology ◽  
High Gain ◽  
Readout Integrated Circuit ◽  
Chip Area ◽  
Operating Modes

A low power readout integrated circuit (ROIC) for 512 × 512 cooled infrared focal plane array (IRFPA) is presented. A capacitive trans-impedance amplifier (CTIA) with high gain cascode amplifier and inherent correlated double sampling (CDS) configuration is employed to achieve a high performance readout interface for the IRFPA with a pixel size of 30 × 30 μm2. By optimizing column readout timing and using two operating modes in column amplifiers, the power consumption is significantly reduced. The readout chip is implemented in a standard 0.35 μm 2P4M CMOS technology. The measurement results show the proposed ROIC achieves a readout rate of 10 MHz with 70 mW power consumption under 3.3 V supply voltage from 77 K to 150 K operating temperature. And it occupies a chip area of 18.4 × 17.5 mm2.

scholarly journals A New Low-Voltage Low-Power Dual-Mode VCII-Based SIMO Universal Filter

Electronics ◽  
2019 ◽  
Vol 8 (7) ◽  
pp. 765 ◽  
Author(s):  
Leila Safari ◽  
Gianluca Barile ◽  
Giuseppe Ferri ◽  
Vincenzo Stornelli
Keyword(s):  
Low Power ◽  
Transfer Functions ◽  
Low Voltage ◽  
Supply Voltage ◽  
Building Blocks ◽  
Cmos Technology ◽  
Universal Filter ◽  
Dual Mode ◽  
Input Multiple Output ◽  
Low Pass

In this paper, a new low-voltage low-power dual-mode universal filter is presented. The proposed circuit is implemented using inverting current buffer (I-CB) and second-generation voltage conveyors (VCIIs) as active building blocks and five resistors and three capacitors as passive elements. The circuit is in single-input multiple-output (SIMO) structure and can produce second-order high-pass (HP), band-pass (BP), low-pass (LP), all-pass (AP), and band-stop (BS) transfer functions. The outputs are available as voltage signals at low impedance Z ports of the VCII. The HP, BP, AP, and BS outputs are also produced in the form of current signals at high impedance X ports of the VCIIs. In addition, the AP and BS outputs are also available in inverting type. The proposed circuit enjoys a dual-mode operation and, based on the application, the input signal can be either current or voltage. It is worth mentioning that the proposed filter does not require any component matching constraint and all sensitivities are low, moreover it can be easily cascadable. The simulation results using 0.18 μm CMOS technology parameters at a supply voltage of ±0.9 V are provided to support the presented theory.

LOW VOLTAGE, LOW POWER CHEBYSHEV FILTER IN 0.18 μm CMOS TECHNOLOGY

2013 ◽  
Vol 22 (07) ◽  
pp. 1350053 ◽  
Author(s):  
S. REKHA ◽  
T. LAXMINIDHI
Keyword(s):  
Low Power ◽  
Dynamic Range ◽  
Low Voltage ◽  
Supply Voltage ◽  
Cmos Technology ◽  
Transconductance Amplifier ◽  
Low Pass ◽  
Unity Gain ◽  
Design Centering ◽  
Low Supply Voltage

This paper presents an active-RC continuous time filter in 0.18 μm standard CMOS technology intended to operate on a very low supply voltage of 0.5 V. The filter designed, has a 5th order Chebyshev low pass response with a bandwidth of 477 kHz and 1-dB passband ripple. A low-power operational transconductance amplifier (OTA) is designed which makes the filter realizable. The OTA uses bulk-driven input transistors and feed-forward compensation in order to increase the Dynamic Range and Unity Gain Bandwidth, respectively. The paper also presents an equivalent circuit of the OTA and explains how the filter can be modeled using descriptor state-space equations which will be used for design centering the filter in the presence of parasitics. The designed filter offers a dynamic range of 51.3 dB while consuming a power of 237 μW.

A Novel CNFET Technology Based 3 Bit Flash ADC for Low-Voltage High Speed SoC Application

2015 ◽  
Vol 19 ◽  
pp. 19-36 ◽  
Author(s):  
P.A. Gowri Sankar ◽  
G. Sathiyabama
Keyword(s):  
Power Consumption ◽  
Low Power ◽  
Circuit Design ◽  
Field Effect ◽  
High Speed ◽  
Low Voltage ◽  
Supply Voltage ◽  
Cmos Technology ◽  
Flash Adc ◽  
Simulation Results

The continuous scaling down of metal-oxide-semiconductor field effect transistors (MOSFETs) led to the considerable impact in the analog-digital mixed signal integrated circuit design for system-on-chips (SoCs) application. SoCs trends force ADCs to be integrated on the chip with other digital circuits. These trends present new challenges in ADC circuit design based on existing CMOS technology. In this paper, we have designed and analyzed a 3-bit high speed, low-voltage and low-power flash ADC at 32nm CNFET technology for SoC applications. The proposed ADC utilizes the Threshold Inverter Quantization (TIQ) technique that uses two cascaded carbon nanotube field effect transistor (CNFET) inverters as a comparator. The TIQ technique proposed has been developed for better implementation in SoC applications. The performance of the proposed ADC is studied using two different types of encoders such as ROM and Fat tree encoders. The proposed ADCs circuits are simulated using Synopsys HSPICE with standard 32nm CNFET model at 0.9 input supply voltage. The simulation results show that the proposed 3 bit TIQ technique based flash ADC with fat tree encoder operates up to 8 giga samples per second (GSPS) with 35.88µW power consumption. From the simulation results, we observed that the proposed TIQ flash ADC achieves high speed, small size, low power consumption, and low voltage operation compared to other low power CMOS technology based flash ADCs. The proposed method is sensitive to process, temperature and power supply voltage variations and their impact on the ADC performance is also investigated.

scholarly journals 1.5-V CMOS Current Multiplier/Divider

2018 ◽  
Vol 8 (3) ◽  
pp. 1478 ◽  
Author(s):  
Jetsdaporn Satansup ◽  
Worapong Tangsrirat
Keyword(s):  
Low Voltage ◽  
Supply Voltage ◽  
Current Mode ◽  
Cmos Technology ◽  
Signal Frequency ◽  
Total Power ◽  
Total Power Consumption ◽  
Linearity Error ◽  
Low Supply Voltage ◽  
Circuit Technique

A circuit technique for designing a compact low-voltage current-mode multiplier/divider circuit in CMOS technology is presented.  It is based on the use of a compact current quadratic cell able to operate at low supply voltage.  The proposed circuit is designed and simulated for implementing in TSMC 0.25-m CMOS technology with a single supply voltage of 1.5 V.  Simulation results using PSPICE, accurately agreement with theoretical ones, have been provided, and also demonstrate a maximum linearity error of 1.5%, a THD less than 2% at 100 MHz, a total power consumption of 508 W, and -3dB small-signal frequency of about 245 MHz.

Design of Low Voltage Low Power ADC for WSN Node

2013 ◽  
Vol 760-762 ◽  
pp. 561-566
Author(s):  
Si Kui Ren ◽  
Zhi Qun Li
Keyword(s):  
Low Power ◽  
Figure Of Merit ◽  
Dynamic Range ◽  
Low Voltage ◽  
Cmos Technology ◽  
Total Power ◽  
Chip Area ◽  
Analog To Digital ◽  
Spurious Free Dynamic Range ◽  
Free Dynamic

This paper presents a low power low voltage 7bit 16MS/s SAR ADC (successive approximation register analog-to-digital converter) for the application of ZigBee receiver. The proposed 7-bit ADC is designed and simulated in 180nm RF CMOS technology. Post simulation results show that at 1.0-V supply and 16 MS/s, the ADC achieves a SNDR (signal-to-noise-and-distortion ratio) and SFDR (Spurious Free Dynamic Range) are 43.6dB, 57.4dB respectively. The total power dissipation is 228μW, and it occupies a chip area of 0.525 mm2. It results in a figure-of-merit (FOM) of 0.11pJ/step.

Sign in / Sign up

Export Citation Format

Share Document