2014

UMTEC, Macao, China, 3 Instituto Superior Tecnico, Lisbon, Portugal 1 2 The latest passive-mixer-first wideband receiver (RX) [1] has managed to squeeze the power (10 to 12mW) via resonant multi-phase LO and current-reus

Tung Huei Ke1, Soeren Steudel1, Koji Obata3, Marko Marinkovic4, Duy-Vu Pham4, Arne Hoppe4, Aashini Gulati5, Francisco Gonzalez Rodriguez5, Brian Cobb5, Gerwin H. Gelinck5, Jan Genoe1,2, Wim Dehaene1,2, Paul Heremans1,2 i

Direct processing of raw high-dimensional data such as images and video by machine learning systems is impractical both due to prohibitive power consumption and the “curse of dimensionality,” which makes learning tasks e

Manoj Nag1, Soeren Steudel1, Sarah Schols1, Joris Maas4, Ashutosh Tripathi4, Jan-Laurens van der Steen4, Tim Ellis4, Gerwin H. Gelinck4, Paul Heremans1,2,4 imec, Leuven, Belgium, 2KU Leuven, Leuven, Belgium, Panasonic, O

the reference RC oscillator 1 is 10Hz, RC oscillator 2 (= Sensor 1) is not oscillating, which corresponds to “Dry” (= no urination), and RC oscillator 3 (= Sensor 2) is 5Hz, which corresponds to “Wet” (= urination). Figu

University of Technology, Eindhoven, The Netherlands, 4 CEA-LITEN, Grenoble, France 1 3 In the last several years, organic electronics have gained increasing consideration as a cost-effective alternative to silicon, espe

power and frequency by bidirectional switches has been expected to be an ultimate AC-to-AC converter because it eliminates limited-lifetime capacitors and achieves high efficiency power conversion even without PFC (Power

Masao Taguchi, Hiroki Ishikuro, Tadahiro Kuroda and negative pulses are received for each bit due to Manchester encoding, error propagation can be limited within two bits. Therefore, FEC techniques can be applied. If the

Jia Hao Cheong1, Peng Li1, Jun Zhou1, Wei Da Toh1, Xin Zhang1, Yuan Gao1, Kuang Wei Cheng2, Xin Liu1, Minkyu Je1 Institute of Microelectronics, Singapore, Singapore, National Cheng Kung University, Tainan, Taiwan 1 2 Wea

Thomas C. Oh4, James F. Buckwalter2 Qualcomm, San Diego, CA, University of California, San Diego, La Jolla, CA, 3 Peregrine Semiconductor, San Diego, CA, 4 HRL Laboratories, Malibu, CA 1 2 High-speed track-and-hold ampli

Munehiro Kozuma1, Takeshi Osada1, Yoshiyuki Kurokawa1, Takayuki Ikeda1, Naoto Yamade1, Yutaka Okazaki1, Hidekazu Miyairi1, Masahiro Fujita2, Jun Koyama1, Shunpei Yamazaki1 Semiconductor Energy Laboratory, Kanagawa, Japan

wide range of load current, especially for today’s multicore SoCs, which usually have a wide range of current profile. Active-phase-count (APC) control, as proposed in [1-3], is the key technique that offers the wide loa

In recent years, the clock frequency, the number of cores, and the power dissipation of application processors (APs) for portable electronics have dramatically increased. As a result, peak processor currents have reached

Improving battery longevity in portable devices usually requires the use of different voltage levels with a wide range of load capability for various functional blocks. Since a single-inductor-multiple-output (SIMO) conv

Dynamic voltage scaling (DVS) is an effective strategy in reducing the power consumption of a processor through adjusting its supply voltage at runtime. The power converter that drives the processor should have a wide ou

There is an increasing need for fully integrated power converters to reduce form factor in mobile devices and provide high-density point-of-load power delivery in performance computing applications [1]. While the number

The growing demand for both performance and battery life in portable consumer electronics requires SoCs and power management circuits to be small, efficient, and dynamically powerful. Dynamic voltage scaling (DVS) can he

Thomas Toifl2, Christian Menolfi2, Lukas Kull2, Thomas Morf2, Marcel Kossel2, Matthias Brändli2, Peter Buchmann2, Pier Andrea Francese2 ETH, Zurich, Switzerland, 2IBM Research, Rüschlikon, Switzerland 1 For an on-chip or

In this paper, a 3-phase switched-capacitor (SC) boost converter that uses 2 external floating capacitors to provide 16V output from a 3.3V input is presented. It achieves an efficiency of 70.3% at 7mA load current while

Gregory Still3, Christopher Gonzalez2, Allen Hall1, David Hogenmiller1, Frank Malgioglio4, Ryan Nett1, Jose Paredes1, Juergen Pille5, Donald Plass4, Ruchir Puri2, Phillip Restle2, David Shan1, Kevin Stawiasz2, Zeynep Top

Gregory Still3, Ryan Kruse4, Seongwon Kim1, David Boerstler4, Tilman Gloekler5, Raphael Robertazzi1, Kevin Stawiasz1, Timothy Diemoz2, George English2, David Hui2, Paul Muench2, Joshua Friedrich4 IBM, Yorktown Heights, N

4IBM STG, Williston, VT, 5IBM STG, Raleigh, NC 1 3 A resonant-clock design for the IBM POWER8 processor core was implemented with 2 resonant modes (and a non-resonant mode), saving clock power over a wide frequency range

dual-threaded 64b Ivybridge cores [1] and 37.5MB shared L3 cache. The system interface includes two on-chip memory controllers, each with two memory channels and supports multiple system topologies. The processor has 4.3

Stephen Kosonocky2, Robert S. Orefice1, Donald A. Priore1, Jonathan White1, Kathryn Wilcox1 AMD, Boxborough, MA, 2AMD, Fort Collins, CO, 3AMD, Austin, TX 1 The AMD two-core x86-64 CPU module, codenamed “Steamroller”, con

In high-performance microprocessor cores, the on-die supply voltage seen by the transistors is non-ideal and exhibits significant fluctuations. These supply fluctuations are caused by sudden changes in the current consum

Carlos Tokunaga, Joseph F. Ryan, Charles Augustine, Jaydeep P. Kulkarni, Yi-Chun Shih, Stephen T. Kim, Rinkle Jain, Keith Bowman, Arijit Raychowdhury, Muhammad M. Khellah, James W. Tschanz, Vivek De Intel, Hillsboro, OR

John Ngai, Russ Homer, Matthew Ashcraft, Greg Favor Applied Micro, Sunnyvale, CA Potenza is a first generation 64b ARM v8 processor and memory sub-system of the X-GeneTM server platform [1]. The Potenza processor module

Thomas P. Thomas, Christopher Mozak, Brent Boswell, Manoj Lal, Anant Deval, Jonathan Douglas, Mahmoud Elassal, Ankireddy Nalamalpu, Timothy M. Wilson, Matthew Merten, Srinivas Chennupaty, Wilfred Gomes, Rajesh Kumar Inte

and limited by the Random Transaction Rate (RTR) of the memory system. Networking line cards to date are ≤200Gb/s and were able to use memories optimized for latency (SRAM) and bandwidth (SDRAM) designed for computing sy

The future penetration of long-term-evolution mobile phone services and various data cloud services will continuously accelerate the present traffic evolution. Figure 6.2.1 shows the commercial system capacity evolution

Aidan Keady1, John McGrath1, Edward Cullen1, Daire Breathnach1, Denis Keane1, Patrick Lynch1, Marites De La Torre1, Ronnie De La Torre1, Peng Lim1, Anthony Collins1, Brendan Farley1, Liam Madden2 Xilinx, Dublin, Ireland,

Bumsuk Kim, Hongki Kim, Jongeun Park, Taesub Jung, Wonje Park, Taeheon Lee, Eunkyung Park, Sangjun Choi, Gyehun Choi, Haeyong Park, Yujung Choi, Seungwook Lee, Yunkyung Kim, Y. Jay Jung, Donghyuk Park, Seungjoo Nah, Youn

Miniaturized low-power artificial compound eyes in a small form factor and a low payload can be a promising approach to provide wide-field information for micro-air-vehicle (MAV) applications. Recently, research efforts

that integrates an image sensor and parallel image processors on a single silicon die. Nowadays, high-speed vision chips with powerful recognition capabilities are greatly demanded in applications such as: industrial aut

have a wide range of applications, such as 3D mice, gesture-based remote controllers, amusement, robots, security systems, and automobiles. Numerous ToF range imager developments have been reported [1-4]. Recent developm

combination with 3D printers. One of the common technologies in contactless 3D scanners is the light-section method, which has advantages in term of accuracy. The method, however, requires a long base line between a came

Cyrus S. Bamji, Dane Snow, Hideaki Oshima, Larry Prather, Mike Fenton, Lou Kordus, Pat O’Connor, Rich McCauley, Sheethal Nayak, Sunil Acharya, Swati Mehta, Tamer Elkhatib, Thomas Meyer, Tod O’Dwyer, Travis Perry, Vei-Han

medium-reach optical links due to its cost effectiveness. However, DMLs are not appropriate for use in fiber links longer than 20km at 6Gb/s or equivalent, because the SNR penalty increases abruptly due to excessive chro

The aggregate bandwidth required between two processors, for example, is expected to extend into the terabit-per-second range or higher [1]. Bandwidth is typically the bottleneck in such situations. Optical interconnect

cost-effective fiber for high-speed LANs. Modal dispersion leads to optical-energy spreading over several symbol periods, drastically limiting distance and data-rate. Compared with copper channels, equalization is challe

high-performance computing systems require high-bandwidth serial links to transport high-speed data streams among computational blocks. Optical links have recently attracted attention due to their low channel loss at hig

Erol Arslan, Jiansong Wan, Qiongna Zhang, Sijia Wang, Frank M.L. van der Goes, Klaas Bult Broadcom, Bunnik, The Netherlands The IEEE802.3an 10GBASE-T standard describes full-duplex 10Gb/s Ethernet transmission over four

standalone PHY chips with hundreds of millions of ports shipped every year. Transceiver design has recently focused on power reduction driven by the need for higher port density and throughput with minimum energy and the

Broadcom, Irvine, CA 1 2 As an alternative to the conventional dual-loop architecture, reference-less CDR architectures have become more popular in industry because of their simplicity and flexibility [1-5]. However, the

high-performance computing systems and data centers are currently being developed. The transmission range of conventional electrical interconnections is limited due to the bandwidth of electrical channels. VCSEL-based op

Eng Chuan Low1, Dan Ping Li1, Liming Jin1, Huajiang Zhang1, Chin Heng Leow1, Soong Lin Chew1, Uday Dasgupta1, Chee Hong Yong1, Tian Bao Gao1, Geok Teng Ong1, Wee Guan Tan1, Weimin Shu1, Chee Lee Heng1, Osama Shana’A1,2 M

medical equipment has not been rapidly developed. For wireless medical applications, lossless connection and noninvasive transmission are important factors. Moreover, in medical imaging applications such as 4D ultrasound

constraints on the wireless links where the ear-to-ear link enables signal processing of sound for both ears to enhance speech intelligence and the ear-to-device link provides an audio channel to commercial electronics s

UMTEC, Macao, China, 3 Instituto Superior Tecnico, Lisbon, Portugal 1 2 The rapid proliferation of Internet of Things has urged the development of ultralow-power (ULP) radios at the lowest possible cost, while being univ

4GHz RX for short-range wireless personal and body-area networks. In such applications, the RF transceiver consumes up to 90% of the total battery energy in a remote sensor node. In order to extend the operation lifetime