2012

1.0 Introduction In the past two decades Flash memory grew from a novelty technology to a powerful disruptor that has profoundly transformed consumer electronics and mobile computing. This was made possible through relen

1.0 Introduction Minimizing global consumption of electrical energy is undoubtedly one of the most important challenges facing the world today. According to Exxon Mobil Energy Outlook 2010, economic growth and technologi

Society is going green! Increasingly, people are committing to choose equipment with lower energy demands. Historically, the growth of green has been repeatedly motivated by various economic upheavals, such as the 1973 o

1.0 Introduction Moore’s Law will continue to hold throughout the decade, allowing us to double transistor integration capacity while reducing power, thus providing an abundance of transistors needed to realize novel arc

maximizing high-performance microprocessor vector datapath utilization in multimedia, graphics, and signal processing workloads [1-3]. A wide SIMD vector permutation engine is required to achieve high-throughput data rea

an ever increasing number of cores in modern MPSoCs, power reduction and meeting on-chip bandwidth requirements are pressing concerns. Energy efficiency can be increased by percore dynamic voltage and frequency scaling (

blocks of 3D graphics, signal processing and high-performance computing workloads [1,2]. Higher floating-point precisions offer improved accuracy at the expense of performance and energy efficiency, with variable-precisi

rendering realistic images in high-throughput 3D graphics pipelines. It is the most performance and power-critical operation in programmable vertex and pixel shaders due to the large number of complex floating-point (FP)

IBM Systems and Technology Group, Fishkill, NY 1 2 3D integration (3DI) holds promise for improved performance of integrated systems by increasing interconnect bandwidth [1]. A processor stacked with cache memory is one

Mohammad Hossain1, Moongon Jung1, Ilya Khorosh1, Gokul Kumar1, Young-Joon Lee1, Dean Lewis1, Tzu-Wei Lin1, Chang Liu1, Shreepad Panth1, Mohit Pathak1, Minzhen Ren1, Guanhao Shen1, Taigon Song1, Dong Hyuk Woo1, Xin Zhao1,

Sangwon Seo, Matthew Fojtik, Sudhir Satpathy, Yoonmyung Lee, Daeyeon Kim, Nurrachman Liu, Michael Wieckowski, Gregory Chen, Trevor Mudge, Dennis Sylvester, David Blaauw University of Michigan, Ann Arbor, MI Recent high p

Tatsumi Nakada1, Ken Seki1, Toshiyuki Shimizu1, Naoki Shinjo1, Fumiyoshi Shoji2, Atsuya Uno2, Motoyoshi Kurokawa2 Fujitsu, Kanagawa, Japan RIKEN, Hyogo, Japan 1 2 Many high-performance CPUs employ a multicore architectur

Robert Bosch, Palo Alto, CA 1 2 Precision accelerometers are used in a variety of automotive applications, navigation systems, and low-level vibration-monitoring systems. Currently, these sensors are factory-calibrated t

In precision mechatronic systems, such as wafer steppers, the position of critical mechanical components must be dynamically stabilized with sub-nanometer precision. This can be achieved by a servo loop consisting of a d

compliant membrane and the rigid backplate is proportional to the air (acoustic) pressure. If the charge Q at the plates remains constant, there is a linear relationship between the voltage across the plates and the dist

increasingly harsh environments such as acid containing gases in vehicle exhausts or exhaust gas recirculation. State-of-the-art gel protection for sensing elements and their electronics is reaching its limit. A circuit’

National Semiconductor, Santa Clara, CA 1 2 Despite the increasing use of ICs at very high temperatures (>150°C) in automotive and industrial applications, sensing such temperatures is still mostly done with discrete the

Shouvik Mukherjee2, Carl Arft2, Jin-Tae Kim2, Niveditha Arumugam2, Pavan Gupta2, Sassan Tabatabaei2, Sudhakar Pamarti4, Haechang Lee2, Fari Assaderaghi2 Masdar Institute of Science and Technology, Abu Dhabi, United Arab

This paper describes an energy-efficient CMOS temperature sensor intended for use in RFID tags. The sensor achieves an inaccuracy of ±0.15°C (3σ) over the military temperature range (-55 to 125°C) and dissipates only 27n

Thermal sensors are used in modern microprocessors to provide information for: 1) throttling at the maximum temperature of operation, and 2) fan regulation at temperatures down to 50°C. Today’s microprocessors are therma

Dongsik Cho, Junghun Heo, Sunghoon Cho, Youngmin Shin, Sunghee Yun, Euiseok Kim, Ukrae Cho, Edward Pyo, Man Hyuk Park, Jae Cheol Son, Chinhyun Kim, Jeongnam Youn, Youngki Chung, Sungho Park, Seung Ho Hwang Samsung Electr

Emil Matûs1, Gerhard Fettweis1, Holger Eisenreich1, Georg Ellguth1, Sebastian Höppner1, Stefan Scholze1, René Schüffny1, Tomoyoshi Kobori2 Technical University Dresden, Dresden, Germany NEC, Tokyo, Japan 1 2 In current a

Masashi Shinagawa2, Hiroki Asada1, Ryo Minami1, Tatsuya Yamaguchi1, Ahmed Musa1, Yuuki Tsukui1, Yasuo Asakura2, Shinya Tamonoki2, Hiroyuki Yamagishi2, Yasufumi Hino2, Takahiro Sato1, Hironori Sakaguchi1, Naoki Shimasaki1

unmanned aerial vehicles (UAVs) and mobile augmented reality that require robust and fast recognition in the presence of dynamic camera noise. Devices in such applications suffer from severe motion/camera blur noise in l

popular recently in a variety of industries such as automotive, surveillance, and others. SoCs for such image recognition applications are required to be powerful enough to support real-time multiple object recognition,

Shanghai Jiao Tong University, Shanghai, China 1 2 8K×4K Super Hi-Vision (SHV) offers a significantly enhanced visual experience relative to 1080p, and is on its way to being the next digital TV standard. In addition, ad

reduced power consumption, which motivates the pursuit of high-performance at reduced operating voltages. Random and systematic device variations pose significant challenges to SRAM VMIN and low-voltage performance as te

Semiconductor Technology Academic Research Center, Yokohama, Japan 1 2 Decreasing operating margins due to random variations is a key issue for voltage scaling in SRAM technology. It is particularly severe for half-selec

embedded memory arrays used as register files and low-level caches that typically share the same supply voltage as the core [1]. The desire for wide voltage range operation to optimize power and performance dictates the

growth in the market for mobile information terminals such as smart phones and tablets, the performance of image processing engines (e.g., operation speed, accuracy in digital images) has improved remarkably. In these pr

clock and timing generators are in high demand to avoid complex analog operations and to meet stringent phase noise requirements. There have been several approaches to convert analog systems to their digital counterparts

implemented using digital phase-locked loops (DPLLs), are evolving as the preferred means for synthesizing on-chip clocks. Their main benefits include small area, reduced sensitivity to analog circuit imperfections, and

synchronization in high performance digital systems. The design of analog DLLs has become a challenge due to the trends associated with CMOS scaling, namely, high leakage current, low supply voltage, etc. Consequently, m

Mobile SoC designs demand a low-power clocking system to maximize battery life. The host PLL is critical since it must remain enabled to support always-on, always-connected operation. In addition, the host PLL should off

control gain, KVCO, increases the phase noise contribution arising from the charge pump and loop filter. To resolve this problem, dual-tuning PLLs (DT-PLLs) have been studied [1-4]. The DT-PLL structure adds a narrow-ban

shield surrounding each pixel. This layout symmetry enabled a wide-band radially symmetric antenna pattern. The silicon die (15Ω-cm resistivity) was thinned down to 150µm and active layers were selectively blocked to min

Millimeter-Wave (MMW) phased-array receivers are used not only to overcome the large path loss and thus to relax the link budget but also to electrically steer the beam direction to suppress unwanted signals. Each elemen

sub-millimeter-wave imaging using solid-state circuits is gaining attention for security and medical applications. To lower cost and increase integration, MOSFETs in CMOS are being investigated for implementing broadband

Up until recently, the terahertz frequency range (0.3 to 3THz) has been mostly addressed by high-mobility custom III-V processes, bulky and expensive nonlinear optics, or cryogenically cooled quantum cascade lasers. A lo

Sub-mm-Wave and terahertz frequencies have many applications such as medical imaging, spectroscopy and communication systems. CMOS signal generation at this frequency range is a major challenge due to the limited cut-off

For a highly integrated wireless system including on-chip antennas, high-outputpower power amplifiers (PA) are required to cover the desired transmission range. In order to achieve the output power level, power-combining

Institute of Microelectronics, Singapore, Singapore 3 MicroArray Technologies, Chengdu, China 1 2 High-data-rate short-range communication and image systems beyond 100GHz impose crucial requirements on signal sources, de

Z. Xu3, Y. Wu4, M. Zhu1, Mau-Chung Frank Chang1 University of California, Los Angeles, Los Angeles, CA 2 University of Florida, Gainsville, FL 3 HRL, Malibu, CA 4 Northrop Grumman Aerospace Systems, Los Angeles, CA 1 Mil

Tong Wang, Yuta Tsubouchi, Ryoichi Tachibana, Akihide Sai, Yuka Kobayashi, Daisuke Kurose, Tomohiko Ito, Koichiro Ban, Tomoya Tandai, Takeshi Tomizawa Toshiba, Kawasaki, Japan High-speed and energy-efficient wireless com

Viki Szortyka1,2, Kristof Vaesen1, Wim Van Thillo1, Bertrand Parvais1, Mike Libois1, Steven Thijs1, John R. Long3, Charlotte Soens1, Piet Wambacq1,2 imec, Heverlee, Belgium Vrije Universiteit Brussel, Brussel, Belgium 3

For minimizing the power consumption in portable devices, efficient DC-DC converters with a wide range of regulated voltages and currents are needed. Considering the required footprint area, cost, and chip count, integra

JDA, Daejeon, Korea 1 2 Several types of DC-DC converters for active-matrix organic LED (AMOLED) displays have been introduced to date [1-4]. Single-inductor multiple-output (SIMO) converters with current-mode control ha

terms of efficiency and lower fabrication cost. However, some areas such as bar-typed fluorescent lamp retrofit applications still require a solution with isolation. Even for replacement of the incandescent and compact f

Several emerging portable applications require high-efficiency LED drivers [1-4]. An LED driver is basically a current source that forces the current required for achieving the desired light emission into the LED. In ord

The traditional inductor-based buck converter has been the dominant design for step-down switched-mode voltage regulators for decades. Switched-capacitor (SC) DC-DC converters, on the other hand, have traditionally been