Next Issue
Previous Issue

Table of Contents

J. Low Power Electron. Appl., Volume 8, Issue 4 (December 2018)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
View options order results:
result details:
Displaying articles 1-18
Export citation of selected articles as:
Open AccessArticle Design and Evaluation of an Electrical Bioimpedance Device Based on DIBS for Myography during Isotonic Exercises
J. Low Power Electron. Appl. 2018, 8(4), 50; https://doi.org/10.3390/jlpea8040050
Received: 7 November 2018 / Revised: 11 December 2018 / Accepted: 12 December 2018 / Published: 15 December 2018
Viewed by 270 | PDF Full-text (6403 KB) | HTML Full-text | XML Full-text
Abstract
Electrical Bioimpedance Spectroscopy (EIS) is a technique used to assess passive electrical properties of biological materials. EIS detects physiological and pathological conditions in animal tissues. Recently, the introduction of broadband excitation signals has reduced the measuring time for application techniques such as Electrical
[...] Read more.
Electrical Bioimpedance Spectroscopy (EIS) is a technique used to assess passive electrical properties of biological materials. EIS detects physiological and pathological conditions in animal tissues. Recently, the introduction of broadband excitation signals has reduced the measuring time for application techniques such as Electrical Bioimpedance Myography. Therefore, this work is aimed at proposing a prototype by using discrete interval binary sequences (DIBS), which is based on a system that holds a current source, impedance acquisition system, microcontroller and graphical user interface. Measurements between 5 Ω to 5 kΩ had impedance acquisition and phase angle errors of aproximately 2% and were lower than 3 degrees, respectively. Based on a proposed circuit, bioimpedance of the chest muscle (Pectoralis Major) was measured during isotonic exercise (push-up). As a result, our analyses have detected tiredness and fatigue. We have explored and proposed new parameters which assess such conditions, as both the maximum magnitude and tiredness coefficient. These parameters decrease exponentially with consecutive push-ups and were convergent in the majority of the sixteen days of measurement. Full article
Figures

Figure 1

Open AccessArticle Enhancing Reliability of Tactical MANETs by Improving Routing Decisions
J. Low Power Electron. Appl. 2018, 8(4), 49; https://doi.org/10.3390/jlpea8040049
Received: 25 October 2018 / Revised: 19 November 2018 / Accepted: 23 November 2018 / Published: 28 November 2018
Viewed by 216 | PDF Full-text (2790 KB) | HTML Full-text | XML Full-text
Abstract
Mobile ad-hoc networks (MANETs) have been primarily designed to enhance tactical communications in a battlefield. They provide dynamic connectivity without requiring any pre-existing infrastructure. Their multi-hop capabilities can improve radio coverage significantly. The nature of tactical MANET operations requires more specialized routing protocols
[...] Read more.
Mobile ad-hoc networks (MANETs) have been primarily designed to enhance tactical communications in a battlefield. They provide dynamic connectivity without requiring any pre-existing infrastructure. Their multi-hop capabilities can improve radio coverage significantly. The nature of tactical MANET operations requires more specialized routing protocols compared to the ones which are used in commercial MANET. Routing decisions in MANETs are usually conditioned on signal-to-interference-plus-noise ratio (SINR) measurements. In order to improve routing decisions for use in highly dynamic tactical MANETs, this paper proposes to combine two different metrics to achieve reliable multicast in multi-hop ad hoc networks. The resulting protocol combining received signal strength (RSS) with SINR to make routing decisions is referred to as Link Quality Aware Ad-hoc On-Demand Distance Vector (LQA-AODV) routing. The proposed routing protocol can quickly adapt to dynamic changes in network topology and link quality variations often encountered in tactical field operations. Using computer simulations, the performance of proposed protocol is shown to outperform other widely used reactive routing protocols assuming several performance metrics. Full article
Figures

Figure 1

Open AccessArticle Towards Energy-Efficient and Secure Computing Systems
J. Low Power Electron. Appl. 2018, 8(4), 48; https://doi.org/10.3390/jlpea8040048
Received: 30 October 2018 / Revised: 19 November 2018 / Accepted: 21 November 2018 / Published: 27 November 2018
Viewed by 249 | PDF Full-text (1748 KB) | HTML Full-text | XML Full-text
Abstract
Countermeasures against diverse security threats typically incur noticeable hardware cost and power overhead, which may become the obstacle for those countermeasures to be applicable in energy-efficient computing systems. This work presents a summary of energy-efficiency techniques that have been applied in security primitives
[...] Read more.
Countermeasures against diverse security threats typically incur noticeable hardware cost and power overhead, which may become the obstacle for those countermeasures to be applicable in energy-efficient computing systems. This work presents a summary of energy-efficiency techniques that have been applied in security primitives or mechanisms to ensure computing systems’ resilience against various security threats on hardware. This work also uses examples to discuss practical methods for securing the hardware for computing systems to achieve energy efficiency. Full article
(This article belongs to the Special Issue Emerging Interconnection Networks Across Scales)
Figures

Figure 1

Open AccessArticle Enabling Energy-Efficient Physical Computing through Analog Abstraction and IP Reuse
J. Low Power Electron. Appl. 2018, 8(4), 47; https://doi.org/10.3390/jlpea8040047
Received: 1 October 2018 / Revised: 12 November 2018 / Accepted: 16 November 2018 / Published: 24 November 2018
Viewed by 330 | PDF Full-text (1141 KB) | HTML Full-text | XML Full-text
Abstract
This paper shows the first step in analog (and mixed signal) abstraction utilized in large-scale Field Programmable Analog Arrays (FPAA), encoded in the open-source SciLab/Xcos based toolset. Having any opportunity of a wide-scale utilization of ultra-low power technology both requires programmability/reconfigurability as well
[...] Read more.
This paper shows the first step in analog (and mixed signal) abstraction utilized in large-scale Field Programmable Analog Arrays (FPAA), encoded in the open-source SciLab/Xcos based toolset. Having any opportunity of a wide-scale utilization of ultra-low power technology both requires programmability/reconfigurability as well as abstractable tools. Abstraction is essential both make systems rapidly, as well as reduce the barrier for a number of users to use ultra-low power physical computing techniques. Analog devices, circuits, and systems are abstractable and retain their energy efficient opportunities compared with custom digital hardware. We will present the analog (and mixed signal) abstraction developed for the open-source toolkit used for the SoC FPAAs. Abstraction of Blocks in the FPAA block library makes the SoC FPAA ecosystem accessible to system-level designers while still enabling circuit designers the freedom to build at a low level. Multiple working test cases of various levels of complexity illustrate the analog abstraction capability. The FPAA block library provides a starting point for discussing the fundamental block concepts of analog computational approaches. Full article
Figures

Figure 1

Open AccessArticle Low-Complexity Loeffler DCT Approximations for Image and Video Coding
J. Low Power Electron. Appl. 2018, 8(4), 46; https://doi.org/10.3390/jlpea8040046
Received: 9 October 2018 / Revised: 12 November 2018 / Accepted: 16 November 2018 / Published: 22 November 2018
Viewed by 288 | PDF Full-text (2327 KB) | HTML Full-text | XML Full-text
Abstract
This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of 8-point DCT approximations was proposed, capable of unifying the mathematical formalism of several 8-point DCT approximations archived in the literature.
[...] Read more.
This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of 8-point DCT approximations was proposed, capable of unifying the mathematical formalism of several 8-point DCT approximations archived in the literature. Pareto-efficient DCT approximations are obtained through multicriteria optimization, where computational complexity, proximity, and coding performance are considered. Efficient approximations and their scaled 16- and 32-point versions are embedded into image and video encoders, including a JPEG-like codec and H.264/AVC and H.265/HEVC standards. Results are compared to the unmodified standard codecs. Efficient approximations are mapped and implemented on a Xilinx VLX240T FPGA and evaluated for area, speed, and power consumption. Full article
Figures

Figure 1

Open AccessCommunication Including Liquid Metal into Porous Elastomeric Films for Flexible and Enzyme-Free Glucose Fuel Cells: A Preliminary Evaluation
J. Low Power Electron. Appl. 2018, 8(4), 45; https://doi.org/10.3390/jlpea8040045
Received: 18 October 2018 / Revised: 8 November 2018 / Accepted: 14 November 2018 / Published: 22 November 2018
Viewed by 293 | PDF Full-text (3068 KB) | HTML Full-text | XML Full-text
Abstract
This communication introduces a new flexible elastomeric composite film, which can directly convert the chemical energy of glucose into electricity. The fabrication process is simple, and no specific equipment is required. Notably, the liquid metal Galinstan is exploited with a two-fold objective: (i)
[...] Read more.
This communication introduces a new flexible elastomeric composite film, which can directly convert the chemical energy of glucose into electricity. The fabrication process is simple, and no specific equipment is required. Notably, the liquid metal Galinstan is exploited with a two-fold objective: (i) Galinstan particles are mixed with polydimethylsiloxane to obtain a highly conductive porous thick film scaffold; (ii) the presence of Galinstan in the composite film enables the direct growth of highly catalytic gold structures. As a first proof of concept, we demonstrate that when immersed in a 20 mM glucose solution, a 5 mm-long, 5 mm-wide and 2 mm-thick sample can generate a volumetric power density up to 3.6 mW·cm 3 at 7 mA·cm 3 and 0.51 V without using any enzymes. Full article
(This article belongs to the Special Issue Flexible Electronics and Self-Powered Systems)
Figures

Figure 1

Open AccessReview A Recent Progress of Spintronics Devices for Integrated Circuit Applications
J. Low Power Electron. Appl. 2018, 8(4), 44; https://doi.org/10.3390/jlpea8040044
Received: 28 October 2018 / Revised: 9 November 2018 / Accepted: 9 November 2018 / Published: 13 November 2018
Viewed by 390 | PDF Full-text (3748 KB) | HTML Full-text | XML Full-text
Abstract
Nonvolatile (NV) memory is a key element for future high-performance and low-power microelectronics. Among the proposed NV memories, spintronics-based ones are particularly attractive for applications, owing to their low-voltage and high-speed operation capability in addition to their high-endurance feature. There are three types
[...] Read more.
Nonvolatile (NV) memory is a key element for future high-performance and low-power microelectronics. Among the proposed NV memories, spintronics-based ones are particularly attractive for applications, owing to their low-voltage and high-speed operation capability in addition to their high-endurance feature. There are three types of spintronics devices with different writing schemes: spin-transfer torque (STT), spin-orbit torque (SOT), and electric field (E-field) effect on magnetic anisotropy. The NV memories using STT have been studied and developed most actively and are about to enter into the market by major semiconductor foundry companies. On the other hand, a development of the NV memories using other writing schemes are now underway. In this review article, first, the recent advancement of the spintronics device using STT and the NV memories using them are reviewed. Next, spintronics devices using the other two writing schemes (SOT and E-field) are briefly reviewed, including issues to be addressed for the NV memories application. Full article
(This article belongs to the Special Issue Spin-Orbit Torque/Voltage-Controlled MRAM and Low Power Application)
Figures

Figure 1

Open AccessArticle Low-Cost Low-Power Acceleration of a Microwave Imaging Algorithm for Brain Stroke Monitoring
J. Low Power Electron. Appl. 2018, 8(4), 43; https://doi.org/10.3390/jlpea8040043
Received: 26 September 2018 / Revised: 27 October 2018 / Accepted: 31 October 2018 / Published: 1 November 2018
Viewed by 381 | PDF Full-text (902 KB) | HTML Full-text | XML Full-text
Abstract
Microwave imaging can effectively image the evolution of a hemorrhagic stroke thanks to the dielectric contrast between the blood and the surrounding brain tissues. To keep low both the form factor and the power consumption in a bedside device, we propose implementing a
[...] Read more.
Microwave imaging can effectively image the evolution of a hemorrhagic stroke thanks to the dielectric contrast between the blood and the surrounding brain tissues. To keep low both the form factor and the power consumption in a bedside device, we propose implementing a microwave imaging algorithm for stroke monitoring in a programmable system-on-chip, in which a simple ARM-based CPU offloads to an FPGA the heavy part of the computation. Compared to a full-software implementation in the ARM CPU, we obtain a 5× speed increase with hardware acceleration without loss in accuracy and precision. Full article
Figures

Figure 1

Open AccessArticle A 0.7 V, Ultra-Wideband Common Gate LNA with Feedback Body Bias Topology for Wireless Applications
J. Low Power Electron. Appl. 2018, 8(4), 42; https://doi.org/10.3390/jlpea8040042
Received: 18 September 2018 / Revised: 20 October 2018 / Accepted: 22 October 2018 / Published: 26 October 2018
Viewed by 309 | PDF Full-text (4287 KB) | HTML Full-text | XML Full-text
Abstract
An ultra-wideband (UWB) low noise amplifier (LNA) for 3.3–13.0 GHz wireless applications using 90 nm CMOS is proposed in this paper. The proposed LNA uses an improved common-gate (CG) topology utilizing feedback body biasing (FBB), which improves noise figure (NF) by a considerable
[...] Read more.
An ultra-wideband (UWB) low noise amplifier (LNA) for 3.3–13.0 GHz wireless applications using 90 nm CMOS is proposed in this paper. The proposed LNA uses an improved common-gate (CG) topology utilizing feedback body biasing (FBB), which improves noise figure (NF) by a considerable amount. Parallel-series tuned LC network was used between the common-gate first stage and the cascoded common-source (CS) stage to achieve the maximum signal flow from CG to CS stage. Improved CS topology with a series inductor at the drain terminal in the second stage connected and cascoded CS third stage provides high power gain (S21) and bandwidth enhancement throughout the complete UWB. A common-drain buffer stage at the output provides high output reflection coefficient (S22). It achieves an average power gain (S21) of 14.7 ± 0.5 dB with a noise figure (NF) of 3.0–3.7 dB. It has an input reflection coefficient (S11) less than −11.7 dB for 3.3–13.0 GHz frequency and output reflection coefficient (S22) of less than −10.6 dB with a very high reversion isolation (S12) of less than −72.4 dB. It consumes only 5.2 mW from a 0.7 V power supply. Full article
Figures

Figure 1

Open AccessArticle A Novel Approach to Design SRAM Cells for Low Leakage and Improved Stability
J. Low Power Electron. Appl. 2018, 8(4), 41; https://doi.org/10.3390/jlpea8040041
Received: 8 September 2018 / Revised: 9 October 2018 / Accepted: 12 October 2018 / Published: 24 October 2018
Viewed by 356 | PDF Full-text (6401 KB) | HTML Full-text | XML Full-text
Abstract
The semiconductor electronic industry is advancing at a very fast pace. The size of portable and handheld devices are shrinking day by day and the demand for longer battery backup is also increasing. With these requirements, the leakage power in stand-by mode becomes
[...] Read more.
The semiconductor electronic industry is advancing at a very fast pace. The size of portable and handheld devices are shrinking day by day and the demand for longer battery backup is also increasing. With these requirements, the leakage power in stand-by mode becomes a critical concern for researchers. In most of these devices, memory is an integral part and its size also scales down as the device size is reduced. So, low power and high speed memory design is a prime concern. Another crucial factor is the stability of static random-access memory (SRAM) cells. This paper combines multi threshold and fingering techniques to propose a modified 6T SRAM cell which has high speed, improved stability and low leakage current in stand-by mode of the memory cell. The simulations are done using the Cadence Virtuoso tool on UMC 55 nm technology. Full article
Figures

Figure 1

Open AccessEditorial Editorial for the Special Issue on “Quantum-Dot Cellular Automata (QCA) and Low Power Application”
J. Low Power Electron. Appl. 2018, 8(4), 40; https://doi.org/10.3390/jlpea8040040
Received: 22 October 2018 / Accepted: 22 October 2018 / Published: 23 October 2018
Viewed by 291 | PDF Full-text (132 KB) | HTML Full-text | XML Full-text
Abstract
Challenges created by the trend of increasingly reducing the size of transistors have made necessary innovative technologies to limit undesirable impacts on the performance speed and power consumption of future designs. [...] Full article
Open AccessArticle Ray Tracing Modeling of Electromagnetic Propagation for On-Chip Wireless Optical Communications
J. Low Power Electron. Appl. 2018, 8(4), 39; https://doi.org/10.3390/jlpea8040039
Received: 13 September 2018 / Revised: 11 October 2018 / Accepted: 12 October 2018 / Published: 17 October 2018
Viewed by 374 | PDF Full-text (4190 KB) | HTML Full-text | XML Full-text
Abstract
Multi-core processors are likely to be a point of no return to meet the unending demand for increasing computational power. Nevertheless, the physical interconnection of many cores might currently represent the bottleneck toward kilo-core architectures. Optical wireless networks on-chip are therefore being considered
[...] Read more.
Multi-core processors are likely to be a point of no return to meet the unending demand for increasing computational power. Nevertheless, the physical interconnection of many cores might currently represent the bottleneck toward kilo-core architectures. Optical wireless networks on-chip are therefore being considered as promising solutions to overcome the technological limits of wired interconnects. In this work, the spatial properties of the on-chip wireless channel are investigated through a ray tracing approach applied to a layered representation of the chip structure, highlighting the relationship between path loss, antenna positions and radiation properties. Full article
(This article belongs to the Special Issue Emerging Interconnection Networks Across Scales)
Figures

Figure 1

Open AccessArticle MB-CNN: Memristive Binary Convolutional Neural Networks for Embedded Mobile Devices
J. Low Power Electron. Appl. 2018, 8(4), 38; https://doi.org/10.3390/jlpea8040038
Received: 1 May 2018 / Revised: 11 October 2018 / Accepted: 11 October 2018 / Published: 13 October 2018
Viewed by 475 | PDF Full-text (1744 KB) | HTML Full-text | XML Full-text
Abstract
Applications of neural networks have gained significant importance in embedded mobile devices and Internet of Things (IoT) nodes. In particular, convolutional neural networks have emerged as one of the most powerful techniques in computer vision, speech recognition, and AI applications that can improve
[...] Read more.
Applications of neural networks have gained significant importance in embedded mobile devices and Internet of Things (IoT) nodes. In particular, convolutional neural networks have emerged as one of the most powerful techniques in computer vision, speech recognition, and AI applications that can improve the mobile user experience. However, satisfying all power and performance requirements of such low power devices is a significant challenge. Recent work has shown that binarizing a neural network can significantly improve the memory requirements of mobile devices at the cost of minor loss in accuracy. This paper proposes MB-CNN, a memristive accelerator for binary convolutional neural networks that perform XNOR convolution in-situ novel 2R memristive data blocks to improve power, performance, and memory requirements of embedded mobile devices. The proposed accelerator achieves at least 13.26 × , 5.91 × , and 3.18 × improvements in the system energy efficiency (computed by energy × delay) over the state-of-the-art software, GPU, and PIM architectures, respectively. The solution architecture which integrates CPU, GPU and MB-CNN outperforms every other configuration in terms of system energy and execution time. Full article
(This article belongs to the Special Issue Energy-Aware Neuromorphic Hardware)
Figures

Figure 1

Open AccessArticle Physical Simulations of High Speed and Low Power NanoMagnet Logic Circuits
J. Low Power Electron. Appl. 2018, 8(4), 37; https://doi.org/10.3390/jlpea8040037
Received: 29 June 2018 / Revised: 1 October 2018 / Accepted: 1 October 2018 / Published: 8 October 2018
Cited by 1 | Viewed by 380 | PDF Full-text (4643 KB) | HTML Full-text | XML Full-text
Abstract
Among all “beyond CMOS” solutions currently under investigation, nanomagnetic logic (NML) technology is considered to be one of the most promising. In this technology, nanoscale magnets are rectangularly shaped and are characterized by the intrinsic capability of enabling logic and memory functions in
[...] Read more.
Among all “beyond CMOS” solutions currently under investigation, nanomagnetic logic (NML) technology is considered to be one of the most promising. In this technology, nanoscale magnets are rectangularly shaped and are characterized by the intrinsic capability of enabling logic and memory functions in the same device. The design of logic architectures is accomplished by the use of a clocking mechanism that is needed to properly propagate information. Previous works demonstrated that the magneto-elastic effect can be exploited to implement the clocking mechanism by altering the magnetization of magnets. With this paper, we present a novel clocking mechanism enabling the independent control of each single nanodevice exploiting the magneto-elastic effect and enabling high-speed NML circuits. We prove the effectiveness of this approach by performing several micromagnetic simulations. We characterized a chain of nanomagnets in different conditions (e.g., different distance among cells, different electrical fields, and different magnet geometries). This solution improves NML, the reliability of circuits, the fabrication process, and the operating frequency of circuits while keeping the energy consumption at an extremely low level. Full article
(This article belongs to the Special Issue Quantum-Dot Cellular Automata (QCA) and Low Power Application)
Figures

Figure 1

Open AccessArticle An Experimental Characterization for Injection Quantity of a High-pressure Injector in GDI Engines
J. Low Power Electron. Appl. 2018, 8(4), 36; https://doi.org/10.3390/jlpea8040036
Received: 28 August 2018 / Revised: 20 September 2018 / Accepted: 27 September 2018 / Published: 3 October 2018
Viewed by 503 | PDF Full-text (8267 KB) | HTML Full-text | XML Full-text
Abstract
The high-pressure (HP) injector is a highly dynamic component requiring careful voltage and pressure input modulation to achieve the required fuel injection quantities of gasoline direct injection (GDI) engines. Accurate fuel injection curves are a key influence for this technology, and therefore, will
[...] Read more.
The high-pressure (HP) injector is a highly dynamic component requiring careful voltage and pressure input modulation to achieve the required fuel injection quantities of gasoline direct injection (GDI) engines. Accurate fuel injection curves are a key influence for this technology, and therefore, will require an accurate estimation of fuel flow rate to be realized. In order to be driven to rapid response with respect to solenoid valve coils, HP injectors typically require to be designed to be capable of rapid response in GDI engines. In this paper, the design and analysis of the proposed injector drive circuit are presented. Next, the effects of total pulse width, injector supply voltage, fuel system pressure, and pulse width modulation (PWM) operation on fuel injection quantities of an HP injector are measured for achieving robust performance and stability in the presence of bounded errors of the GDI injectors due to total pulse width, injector’s supply voltage, fuel pressure and PWM operation. Additionally, the fuel injection quantities of the HP injector are measured by tuning the parameters of the injector drive circuit with the PWM operation. These are defined as the fuel injection curves. Finally, experimental results are provided for verification of the proposed injector drive circuit. Full article
Figures

Figure 1

Open AccessArticle Path Planning for Highly Automated Driving on Embedded GPUs
J. Low Power Electron. Appl. 2018, 8(4), 35; https://doi.org/10.3390/jlpea8040035
Received: 24 August 2018 / Revised: 21 September 2018 / Accepted: 28 September 2018 / Published: 2 October 2018
Viewed by 435 | PDF Full-text (952 KB) | HTML Full-text | XML Full-text
Abstract
The sector of autonomous driving gains more and more importance for the car makers. A key enabler of such systems is the planning of the path the vehicle should take, but it can be very computationally burdensome finding a good one. Here, new
[...] Read more.
The sector of autonomous driving gains more and more importance for the car makers. A key enabler of such systems is the planning of the path the vehicle should take, but it can be very computationally burdensome finding a good one. Here, new architectures in Electronic Control Units (ECUs) are required, such as Graphics Processing Units (GPUs), because standard processors struggle to provide enough computing power. In this work, we present a novel parallelization of a path planning algorithm. We show how many paths can be reasonably planned under real-time requirements and how they can be rated. As an evaluation platform, an Nvidia Jetson board equipped with a Tegra K1 System-on-Chip (SoC) was used, whose GPU is also employed in the zFAS ECU of the AUDI AG. Full article
(This article belongs to the Special Issue Automotive Low Power Technologies)
Figures

Figure 1

Open AccessReview Towards Neuromorphic Learning Machines Using Emerging Memory Devices with Brain-Like Energy Efficiency
J. Low Power Electron. Appl. 2018, 8(4), 34; https://doi.org/10.3390/jlpea8040034
Received: 31 August 2018 / Revised: 28 September 2018 / Accepted: 29 September 2018 / Published: 2 October 2018
Viewed by 543 | PDF Full-text (2283 KB) | HTML Full-text | XML Full-text
Abstract
The ongoing revolution in Deep Learning is redefining the nature of computing that is driven by the increasing amount of pattern classification and cognitive tasks. Specialized digital hardware for deep learning still holds its predominance due to the flexibility offered by the software
[...] Read more.
The ongoing revolution in Deep Learning is redefining the nature of computing that is driven by the increasing amount of pattern classification and cognitive tasks. Specialized digital hardware for deep learning still holds its predominance due to the flexibility offered by the software implementation and maturity of algorithms. However, it is being increasingly desired that cognitive computing occurs at the edge, i.e., on hand-held devices that are energy constrained, which is energy prohibitive when employing digital von Neumann architectures. Recent explorations in digital neuromorphic hardware have shown promise, but offer low neurosynaptic density needed for scaling to applications such as intelligent cognitive assistants (ICA). Large-scale integration of nanoscale emerging memory devices with Complementary Metal Oxide Semiconductor (CMOS) mixed-signal integrated circuits can herald a new generation of Neuromorphic computers that will transcend the von Neumann bottleneck for cognitive computing tasks. Such hybrid Neuromorphic System-on-a-chip (NeuSoC) architectures promise machine learning capability at chip-scale form factor, and several orders of magnitude improvement in energy efficiency. Practical demonstration of such architectures has been limited as performance of emerging memory devices falls short of the expected behavior from the idealized memristor-based analog synapses, or weights, and novel machine learning algorithms are needed to take advantage of the device behavior. In this article, we review the challenges involved and present a pathway to realize large-scale mixed-signal NeuSoCs, from device arrays and circuits to spike-based deep learning algorithms with ‘brain-like’ energy-efficiency. Full article
(This article belongs to the Special Issue CMOS Low Power Design)
Figures

Figure 1

Open AccessArticle An Improved CMOS Design of Op-Amp Comparator with Gain Boosting Technique for Data Converter Circuits
J. Low Power Electron. Appl. 2018, 8(4), 33; https://doi.org/10.3390/jlpea8040033
Received: 16 August 2018 / Revised: 13 September 2018 / Accepted: 18 September 2018 / Published: 25 September 2018
Viewed by 430 | PDF Full-text (4403 KB) | HTML Full-text | XML Full-text
Abstract
A modified architecture of a comparator to achieve high slew rate and boosted gain with an improvement in gain design error is introduced and investigated in this manuscript. It employs the conventional architecture of common-mode current feedback with the modified gain booster topology
[...] Read more.
A modified architecture of a comparator to achieve high slew rate and boosted gain with an improvement in gain design error is introduced and investigated in this manuscript. It employs the conventional architecture of common-mode current feedback with the modified gain booster topology to increase gain, slew rate, and reduced gain error from the conventional structure. Observation from the simulation results concludes that the modified structure using 24 transistors shows power dissipation of 362.29 μW in 90 nm CMOS technology by deploying a supply voltage of 0.7 V, which is a 70% reduction as compared to the usual common mode feedback (CMFD) structure. The symmetric slew rate of 839.99 V/µs for both charging and discharging is obtained, which is 173% more than the standard CMFD structure. A reduction of 0.61% in gain error is achieved through this architecture. A SPICE simulation tool based on 90 nm CMOS technology is employed for executing the Monte Carlo simulations. A brief comparison with earlier CMFD structures shows improved performance parameters in terms of power consumption and slew rate with the reduction in gain error. Full article
Figures

Figure 1

J. Low Power Electron. Appl. EISSN 2079-9268 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top