全部论文

Papers 2008–2026

共 3875 篇 ISSCC 论文,按年份倒序排列

ISSCC 2020 Session 22 Memory
A 1.1V 16GB 640GB/s HBM2E DRAM with a Data-Bus Window-Extension Technique and a Synergetic On-Die ECC Scheme
Chi-Sung Oh, Ki Chul Chun, Young-Yong Byun, Yong-Ki Kim,
So-Young Kim, Yesin Ryu, Jaewon Park, Sinho Kim, Sanguhn Cha, Donghak Shin, Jungyu Lee, Jong-Pil Son, Byung-Kyu Ho, Seong-Jin Cho, Beomyong Kil, Sungoh Ahn, Baekmin Lim, Yongsik Park, Kijun Lee, Myung-Kyu Lee, Seungduk B
ISSCC 2020 Session 21 Digital Processors
A 5.69mm2 0.98nJ/Pixel Image-Processing SoC with 24b High-Dynamic-Range and Multiple Sensor Format Support for Automotive Applications
Chi-Cheng Ju, Tsu-Ming Liu, Yung-Chang Chang, Chih-Ming Wang,
Chang-Hung Tsai, Ying-Jui Chen, TH Wu, Hue-Min Lin, Han-Liang Chou, Abrams Chen, Andy-HB Wang, WC Gu, Wayne Hsieh, Jing-Ying Chang, Shou-Chun Liao, CT Ho, Larry Chu, Sokonisa Wei, CH Wang, Kevin Jou MediaTek, Hsinchu, Ta
ISSCC 2020 Session 21 Digital Processors
A 1.5µJ/Task Path-Planning Processor for 2D/3D Autonomous Navigation of Micro Robots
Chieh Chung, Chia-Hsiang Yang
Autonomous micro robots have been deployed for various applications, ranging from unmanned package delivery to smart aerial surveillance. These robots possess intelligence for perception, make decisions based on the coll
ISSCC 2020 Session 21 Digital Processors
A Fully Integrated Genetic Variant Discovery SoC for Next-Generation Sequencing
Yi-Chung Wu*1, Yen-Lung Chen*1, Chung-Hsuan Yang1, Chao-Hsi Lee2,
Chao-Yang Yu3, Nian-Shyang Chang3, Ling-Chien Chen3, Jia-Rong Chang3, Chun-Pin Lin3, Hung-Lieh Chen3, Chi-Shi Chen3, Jui-Hung Hung2, Chia-Hsiang Yang1 National Taiwan University, Taipei, Taiwan National Chiao Tung Univer
ISSCC 2020 Session 20 Power Management
3D Surgical Alignment with 100µm Resolution Using Magnetic-Field Gradient-Based Localization
Saransh Sharma, Grace Ding, Aditya Telikicherla, Fatemeh Aghlmand,
Arian Hashemi Talkhooncheh, Minwo Wang, Mikhail G. Shapiro, Azita Emami California Institute of Technology, Pasadena, CA Substantial advances in the field of surgery have taken place in recent years, which aim at decreas
ISSCC 2020 Session 20 Power Management
A 4.0×3.7×1.0mm3-MEMS CMOS Integrated E-Nose with
Embedded 4×Gas Sensors, a Temperature Sensor and, a Relative Humidity Sensor
Si Hoon Lee1, Kwangmin Park1, Jaeheung Lim1, Minchul Lee1, Jeongho Park1, Hyun Kim1, Young Ok Lee2, Hyun Su Ahn2, Eunseok Shin1, Hyungjong Ko1, Seoungjae Yoo1, Hyunsurk Ryu1, Yongin Park1, Joonseok Kim1, Long Yan1 Samsun
ISSCC 2020 Session 20 Power Management
A 57nW Software-Defined Always-On Wake-Up Chip for IoT Devices with Asynchronous Pipelined Event-Driven Architecture and Time-Shielding Level-Crossing ADC
Zhixuan Wang1, Le Ye1,2, Hao Zhang1, Jiayoon Ru3, Haitao Fan2,
China 1 2 IoT devices usually operate in random-sparse-event scenarios (Fig. 20.2.1). To avoid missing events, traditionally a periodic-wake-up frequency [1] must be orders of magnitude higher than the average event rate
ISSCC 2020 Session 20 Power Management
A 28µW IoT Tag That Can Communicate with Commodity WiFi Transceivers via a Single-Side-Band QPSK Backscatter Communication Technique
Po-Han Peter Wang1,2, Chi Zhang1, Hongsen Yang1, Dinesh Bharadia1, Patrick P. Mercier1
San Diego, CA 1 2 Nearly all IoT devices require wireless connectivity, and to keep costs down and deployment opportunities up, communication should ideally occur with widely deployed commodity hardware such as WiFi. How
ISSCC 2020 Session 2 Digital Processors
IBM z15: A 12-Core 5.2GHz Microprocessor
Christopher Berry1, Brian Bell2, Adam Jatkowski1, Jesse Surprise1,
John Isakson3, Ofer Geva1, Brian Deskin4, Mark Cichanowski3, Dina Hamid1, Chris Cavitt1, Gregory Fredeman1, Anthony Saporito1, Ashutosh Mishra5, Alper Buyuktosunoglu6, Tobias Webel7, Preetham Lobo5, Pradeep Parashurama5,
ISSCC 2020 Session 2 Digital Processors
A 16nm 3.5B+ Transistor >14TOPS 2-to-10W Multicore SoC Platform for Automotive and Embedded
Applications with Integrated Safety MCU, 512b Vector
VLIW DSP, Embedded Vision and Imaging Acceleration Rama Venkatasubramanian1, Don Steiss1, Greg Shurtz2, Tim Anderson1, Kai Chirca1, Raghavendra Santhanagopal1, Niraj Nandan1, Anish Reghunath1, Hetul Sanghvi1, Daniel Wu1,
ISSCC 2020 Session 2 Digital Processors
A 7nm FinFET 2.5GHz/2.0GHz Dual-Gear Octa-Core CPU Subsystem with Power/Performance Enhancements for a Fully Integrated 5G Smartphone SoC.
Hugh Mair1, Ericbill Wang2, Ashish Nayak1, Rolf Lagerquist1, Loda Chou2,
Gordon Gammie1, Hsinchen Chen1, Lee-Kee Yong1, Manzur Rahman1, Jenny Wiedemeier1, Ramu Madhavaram1, Alex Chiou2, Blundt Li2, Vincent Lin2, Rory Huang2, Michael Yang2, Achuta Thippana1, Osric Su2, SA Huang2 MediaTek, Aust
ISSCC 2020 Session 2 Digital Processors
A 7nm High-Performance and Energy-Efficient Mobile Application Processor with Tri-Cluster CPUs and a Sparsity-Aware NPU
Young Duk Kim, Wookyeong Jeong, Lakkyung Jung, Dongsuk Shin,
Jae Geun Song, Jinook Song, Hyeokman Kwon, Jaeyoung Lee, Jaesu Jung, Myungjin Kang, Jaehun Jeong, Yoonjoo Kwon, Nak Hee Seong Samsung Electronics, Hwaseong, Korea Mobile application processors (APs) must be extremely pow
ISSCC 2020 Session 2 Digital Processors
A 220GOPS 96-Core Processor with 6 Chiplets 3D-Stacked on an Active Interposer Offering 0.6ns/mm
Latency, 3Tb/s/mm2 Inter-Chiplet Interconnects and, 156mW/mm2 @ 82%-Peak-Efficiency DC-DC Converters
which is finally delivered to the chiplet through a micro-bump face-to-face power grid (Fig. 2.3.7). The SCVR input voltage (up to 2.5V) reduces total input current and the required number of power IOs in the package. Ea
ISSCC 2020 Session 2 Digital Processors
AMD Chiplet Architecture for High-Performance Server and Desktop Products
Samuel Naffziger1, Kevin Lepak2, Milam Paraschou1, Mahesh Subramony2
AMD, Austin, TX 1 2 AMD’s “Rome” and “Matisse” are second-generation AMD Infinity Fabric-based SoCs using 3 unique hybrid process technology chiplets to achieve leading performance, performance/$ and performance/W, targe
ISSCC 2020 Session 2 Digital Processors
Zen 2: The AMD 7nm Energy-Efficient High-Performance x86-64 Microprocessor Core
Teja Singh1, Sundar Rangarajan1, Deepesh John1, Russell Schreiber1,
design, fabricated in an energy-efficient TSMC 7nm FinFET process. Similar to AMD’s prior-generation core, codenamed “Zen” [1], the Core Complex Unit (CCX) with 4 cores in this version (Fig. 2.1.1) is used across a wide
ISSCC 2020 Session 19 Quantum & Photonics
A 200dB FoM 4-to-5GHz Cryogenic Oscillator with an Automatic Common-Mode Resonance Calibration for Quantum Computing Applications
Jiang Gong1, Yue Chen1, Fabio Sebastiano1, Edoardo Charbon2,3, Masoud Babaie1
generation is required for the control electronics of quantum computers. To avoid limiting the performance of quantum bits, the frequency noise of a PLL should be <1.9kHzrms [1]. However, it is challenging for RF oscilla
ISSCC 2020 Session 19 Quantum & Photonics
A 110mK 295µW 28nm FDSOI CMOS Quantum Integrated Circuit with a 2.8GHz Excitation and nA Current Sensing of an On-Chip Double Quantum Dot
Loïck Le Guevel1,2, Gérard Billiot1, Xavier Jehl2, Silvano De Franceschi2,
Marcos Zurita1, Yvain Thonnart1, Maud Vinet1, Marc Sanquer2, Romain Maurand2, Aloysius G. M. Jansen2, Gaël Pillonnet1 CEA-LETI-MINATEC, Grenoble, France CEA-IRIG, Grenoble, France 1 2 To reach quantum supremacy, quantum
ISSCC 2020 Session 19 Quantum & Photonics
A Scalable Cryo-CMOS 2-to-20GHz Digitally Intensive Controller for 4×32 Frequency Multiplexed Spin Qubits/Transmons in 22nm FinFET Technology for Quantum Computers
Bishnu Patra*1, Jeroen P. G. van Dijk*1, Sushil Subramanian2,
Andrea Corna1, Xiao Xue1, Charles Jeon2, Farhana Sheikh2, Esdras Juarez-Hernandez3, Brando Perez Esparza3, Huzaifa Rampurawala2, Brent Carlton2, Nodar Samkharadze4, Surej Ravikumar2, Carlos Nieva2, Sungwon Kim2, Hyung-Ji
ISSCC 2020 Session 18 AI / ML
A Fully-Generic-Process Galvanic Isolator for Gate Driver with 123mW 23% Power Transfer and Full-Triplex 21/14/0.5Mb/s Bidirectional Communication Utilizing Reference-Free Dual-Modulation FSK DATA2 is transferred in the same manner as DATA1 through another transformer. Almost all the circuits excluding the DATA1 driver and I/O buffer operate at 1.5V supply to support sufficiently high operating speed. The driver operates with 5.5V supply to transfer power by the same transformer, and the rectifier placed in parallel with the DATA1 receiver extracts the received power.
Hiroaki Ishihara, Kohei Onizuka, Figure 18.8.3 explains the operation of the error-tolerant DATA1 demodulator.
Thanks to the VCO synchronization, demodulation can be realized by a delaybased digital frequency counting normalized by the oscillation period (tVCO). But there is a challenge in that the received signal edge is not per
ISSCC 2020 Session 18 Power Management
A DC to 35MHz Fully Integrated Single-Power-Supply Isolation Amplifier for Current- and Voltage-Sensing Front-Ends of Power Electronics
Satoshi Takaya, Hiroaki Ishihara, Kohei Onizuka
Increased switching frequency of power devices for power electronics allows for compact and lightweight circuit implementations for variety of applications, including power factor corrections, DC/DC converters, and motor
ISSCC 2020 Session 18 Power Management
A 92.8%-Peak-Efficiency 60A 48V-to-1V 3-Level Half-Bridge DC-DC Converter with Balanced Voltage on a Flying Capacitor
Minho Choi1,2, Deog-Kyoon Jeong1
Samsung Electronics, Hwaseong, Korea 1 2 Demand for DC-DC voltage conversion from a 48V input has been on the rise due to proliferation of server and automotive applications with a 48V intermediate bus and 48V batteries,
ISSCC 2020 Session 18 Power Management
ZVS Flyback-Converter ICs Optimizing USB Power Delivery for Fast-Charging Mobile Devices to Achieve 93.5% Efficiency
Wei-Hsu Chang, Kun-Yu Lin, Chun-Ching Lee, Li-Di Lo, Jenn-Yu Lin, Ta-Yung Yang
standard as a charging solution for mobile devices [1]. Moreover, the extended specification includes programmable power supply (PPS) which is suitable for fast charging mobile devices by allowing the power source to dyn
ISSCC 2020 Session 18 Power Management
An 11MHz Fully Integrated 5kV Isolated DC-DC Converter Without Cross-Isolation-Barrier Feedback
Lisong Li1, Xiangming Fang1, Rongxiang Wu2
University of Electronic Science and Technology of China, Chengdu, China 1 2 Galvanic isolation greatly enhances system safety and reliability in applications such as medical devices and sensor interfaces. In these appli
ISSCC 2020 Session 18 Power Management
A 120mA Non-Isolated Capacitor-Drop AC/DC Power Supply
Yogesh Ramadass*1, Andres Blanco*2, Boqiang Xiao*3, John Cummings3, *Equally-Credited Authors (ECAs)
meters, appliances, smoke alarms to ground fault detectors require a non-isolated DC supply that is powered directly from the AC mains. These applications typically require the ability to handle up to 305VAC,rms at the i
ISSCC 2020 Session 18 Power Management
A Monolithic E-Mode GaN 15W 400V Offline Self-Supplied Hysteretic Buck Converter with 95.6% Efficiency
Maik Kaufmann1, Michael Lueders2, Cetin Kaya3, Bernhard Wicht1
Texas Instruments, Freising, Germany, 3 Texas Instruments, Dallas, TX 1 2 Due to superior figures-of-merit (FoMs), gallium nitride (GaN) high-electron mobility transistors (HEMTs) offer a huge potential for high-voltage
ISSCC 2020 Session 18 Power Management
A Self-Health-Learning GaN Power Converter Using OnDie Logarithm-Based Analog SGD Supervised Learning and Online TJ-Independent Precursor Measurement
Yuanqing Huang, Yingping Chen, D. Brian Ma
As GaN technology proliferates in modern power electronics, reliability of GaNbased circuits has become the biggest hurdle for commercialization. Sustaining largest voltage and current stresses in power circuits, power d
ISSCC 2020 Session 17 Clocking & PLLs
A 9mW 54.9-to-63.5GHz Current-Reuse LO Generator with a 186.7dBc/Hz FoM by Unifying a 20GHz
3rd-Harmonic-Rich Current-Output VCO, a Harmonic-Current Filter and a 60GHz TIA
Chao Fan , Jun Yin , Chee-Cheow Lim , Pui-In Mak , Rui P. Martins 1 1 1 1 1,2 University of Macau, Macau, China University of Lisboa, Lisbon, Portugal 1 2 Low-power mm-wave sensors using an FMCW radar technology are open
ISSCC 2020 Session 17 Clocking & PLLs
A 12mW 10GHz FMCW PLL Based on an Integrating DAC with 90kHz rms Frequency Error for 23MHz/µs Slope and 1.2GHz Chirp Bandwidth
Pratap Tumkur Renukaswamy1,2, Nereo Markulic1, Sehoon Park1,2,
continuous-wave (FMCW) radars are a viable solution for high-resolution indoor localization and tracking applications. The fast saw-tooth FMCW chirp needs to be synthesized with a short ramp time, large chirp bandwidth (
ISSCC 2020 Session 17 Clocking & PLLs
A 21.7-to-26.5GHz Charge-Sharing Locking Quadrature PLL with Implicit Digital Frequency-Tracking Loop Achieving 75fs Jitter and -250dB FoM
Yizhe Hu1, Xi Chen1, Teerachot Siriburanon1, Jianglin Du1, Zhong Gao1,
Ireland 1 2 Sub-sampling (SS) and injection-locking (IL) techniques are becoming increasingly popular for 5G millimeter-wave (mmW) frequency generation [1,2] due to their ability to achieve ultra-low jitter (<100fs). How
ISSCC 2020 Session 17 Clocking & PLLs
A 12.5GHz Fractional-N Type-I Sampling PLL Achieving 58fs Integrated Jitter
Mario Mercandelli1, Alessio Santiccioli1, Angelo Parisi1, Luca Bertulessi1,
oscillators for 5G wireless transceivers require rms integrated jitter below 100fs to enable spectrally efficient modulation schemes, such as high-order quadrature amplitude modulation (QAM), at millimeter-wave carrier f
ISSCC 2020 Session 17 Clocking & PLLs
A 18.6-to-40.1GHz 201.7dBc/Hz FoMT Multi-Core Oscillator Using E-M Mixed-Coupling Resonance Boosting
Yiyang Shu, Huizhen Jenny Qian, Xun Luo
The development of millimeter-wave (mmW) multiple-band systems for the 5G wireless and point-to-point backhaul communication requires ultra-wideband signal sources with low phase noise. However, with increasing parasitic
ISSCC 2020 Session 17 Clocking & PLLs
A 66fsrms Jitter 12.8-to-15.2GHz Fractional-N Bang-Bang PLL with Digital Frequency-Error Recovery for Fast Locking
Alessio Santiccioli1, Mario Mercandelli1, Luca Bertulessi1, Angelo Parisi1,
substantial increase in mobile data-rates, enabled by the 5G standard, calls for significantly lower integrated jitter of the local oscillator with respect to previous generations, with requirements below 90fs rms for mi
ISSCC 2020 Session 16 Data Converters
A 40MHz-BW 76.2dB/78.0dB SNDR/DR Noise-Shaping Nonuniform Sampling ADC with Single Phase-Domain Level Crossing and Embedded Nonuniform Digital Signal Processor in 28nm CMOS
Tzu-Fan Wu, Mike Shuo-Wei Chen
A low-power, wide-bandwidth, and high-dynamic-range (DR) ADC is one of the critical building blocks in a wireless receiver design, in which a continuous-time delta-sigma modulator (CT DSM) has become a popular choice. Ho
ISSCC 2020 Session 16 Data Converters
An 800MHz-BW VCO-Based Continuous-Time Pipelined ADC with Inherent Anti-Aliasing and On-Chip Digital Reconstruction Filter
Hajime Shibata1, Gerry Taylor2, Bob Schell3, Victor Kozlov1, Sharvil Patil1,
Donald Paterson4, Asha Ganesan1, Yunzhi Dong4, Wenhua Yang4, Yue"Yin1, Zhao Li1, Prawal Shrestha4, Athreya Gopal5, Aathreya Bhat4, Shanthi Pavan6 Analog Devices, Toronto, Canada, 2Analog Devices, San Diego, CA Analog Dev
ISSCC 2020 Session 16 Data Converters
A 13b 0.005mm2 40MS/s SAR ADC with kT/C Noise Cancellation
Jiaxin Liu1, Xiyuan Tang2, Wenda Zhao2, Linxiao Shen2, Nan Sun2
University of Texas, Austin, TX 1 2 As with any ADC with a front-end S/H, the SAR ADC suffers from a fundamental SNR challenge: its sampling kT/C noise. To satisfy the SNR requirement, the input capacitor has to be suffi
ISSCC 2020 Session 16 Data Converters
A Calibration-Free 71.7dB SNDR 100MS/s 0.7mW Weighted-Averaging Correlated Level Shifting Pipelined SAR ADC with Speed-Enhancement Scheme
Tsung-Chih Hung, Jia-Ching Wang, Tai-Haur Kuo
With the increasing demand for next-generation communication, the trend of developing wide-bandwidth, high-resolution ADCs has emerged, where pipelined SAR (PIPE-SAR) ADCs [1-2] have become popular owing to their excelle
ISSCC 2020 Session 16 Data Converters
A Single-Channel 5.5mW 3.3GS/s 6b Fully Dynamic Pipelined ADC with Post-Amplification Residue Generation
Zihao Zheng1,2, Lai Wei1,2, Jorge Lagos2, Ewout Martens2, Yan Zhu1,
Chi-Hang Chan1, Jan Craninckx2, Rui P. Martins1,3 University of Macau, Macau, China imec, Leuven, Belgium 3 University of Lisboa, Lisbon, Portugal 1 2 Multi-GS/s ADCs are key blocks for ADC-based serial links and mm-wave
ISSCC 2020 Session 16 Data Converters
A 4× Interleaved 10GS/s 8b Time-Domain ADC with 16× Interpolation-Based Inter-Stage Gain Achieving >37.5dB SNDR at 18GHz Input
Minglei Zhang1, Yan Zhu1, Chi-Hang Chan1, Rui P. Martins1,2
University of Lisboa, Lisbon, Portugal 1 2 The ever-increasing data traffic in wireline communication systems has led to the demand for high-speed ADCs with a large input BW. Time-interleaved SAR ADCs with a large interl
ISSCC 2020 Session 16 Data Converters
A 12b 18GS/s RF Sampling ADC with an Integrated Wideband Track-and-Hold Amplifier and Background Calibration
Ahmed M. A. Ali, Huseyin Dinc, Paritosh Bhoraskar, Scott Bardsley,
consumption enable direct RF sampling, more integration, flexibility and lower cost for communication, instrumentation and other applications. The state of the art of interleaved RF converters enables up to 10GS/s with 1
ISSCC 2020 Session 15 AI / ML
A 28nm 64Kb 6T SRAM Computing-in-Memory Macro with 8b MAC Operation for AI Edge Chips multiplication results (PL"="IN[1:0]"⋅ W) to HGBLB.
Xin Si , Yung-Ning Tu , Wei-Hsing Huang , Jian-Wei Su , Pei-Jung Lu ,
Jing-Hong Wang1, Ta-Wei Liu1, Ssu-Yen Wu1, Ruhui Liu1, Yen-Chi Chou1, Zhixiao Zhang1, Syuan-Hao Sie1, Wei-Chen Wei1, Yun-Chen Lo1, Tai-Hsing Wen1, Tzu-Hsiang Hsu1, Yen-Kai Chen1, William Shih1, Chung-Chuan Lo1, Ren-Shuo
ISSCC 2020 Session 15 AI / ML
A 22nm 2Mb ReRAM Compute-in-Memory Macro with 121-28TOPS/W for Multibit MAC Computing for Tiny AI Edge Devices
Cheng-Xin Xue, Tsung-Yuan Huang, Je-Syu Liu, Ting-Wei Chang,
Hui-Yao Kao, Jing-Hong Wang, Ta-Wei Liu, Shih-Ying Wei, Sheng-Po Huang, Wei-Chen Wei, Yi-Ren Chen, Tzu-Hsiang Hsu, Yen-Kai Chen, Yun-Chen Lo, Tai-Hsing Wen, Chung-Chuan Lo, Ren-Shuo Liu, Chih-Cheng Hsieh, Kea-Tiong Tang,
ISSCC 2020 Session 15 AI / ML
A 351TOPS/W and 372.4GOPS Compute-in-Memory SRAM Macro in 7nm FinFET CMOS for Machine-Learning Applications
Qing Dong1, Mahmut E. Sinangil1, Burak Erbagci1, Dar Sun2,
computations and reduces off-chip weight access to reduce energy consumption and latency, specifically for AI edge devices. Prior CIM approaches demonstrated tradeoffs for area, noise margin, process variation and weight
ISSCC 2020 Session 15 AI / ML
A 28nm 64Kb Inference-Training Two-Way Transpose Multibit 6T SRAM Compute-in-Memory Macro for AI Edge Chips
Jian-Wei Su1,2, Xin Si1, Yen-Chi Chou1, Ting-Wei Chang1,
Wei-Hsing Huang1, Yung-Ning Tu1, Ruhui Liu1, Pei-Jung Lu1, Ta-Wei Liu1, Jing-Hong Wang1, Zhixiao Zhang1, Hongwu Jiang3, Shanshi Huang3, Chung-Chuan Lo1, Ren-Shuo Liu1, Chih-Cheng Hsieh1, Kea-Tiong Tang1, Shyh-Shyuan Sheu
ISSCC 2020 Session 15 AI / ML
A 5nm 135Mb SRAM in EUV and High-Mobility-Channel FinFET Technology with Metal Coupling and ChargeSharing Write-Assist Circuitry Schemes for High-Density and Low-VMIN Applications
Jonathan Chang, Yen-Huei Chen, Gary Chan, Hank Cheng,
Po-Sheng Wang, Yangsyu Lin, Hidehiro Fujiwara, Robin Lee, Hung-Jen Liao, Ping-Wei Wang, Geoffrey Yeap, Quincy Li TSMC, Hsinchu, Taiwan Despite recent advances, low-voltage operation remains one of the key approaches for
ISSCC 2020 Session 14 AI / ML
A 65nm Computing-in-Memory-Based CNN Processor with 2.9-to-35.8TOPS/W System Energy Efficiency Using Dynamic-Sparsity Performance-Scaling Architecture and Energy-Efficient Inter/Intra-Macro Data Reuse
Jinshan Yue1,2, Zhe Yuan1,2, Xiaoyu Feng1, Yifan He1, Zhixiao Zhang3,
University, Hsinchu, Taiwan 1 2 Computing-in-Memory (CIM) is a promising solution for energy-efficient neural network (NN) processors. Previous CIM chips [1-4] mainly focus on the memory macro itself, lacking insight on
ISSCC 2020 Session 14 AI / ML
A 65nm 24.7µJ/Frame 12.3mW Activation-SimilarityAware Convolutional Neural Network Video Processor
Using Hybrid Precision, Inter-Frame Data Reuse and, Mixed-Bit-Width Difference-Frame Data Codec
Zhe Yuan1,2, Yixiong Yang1, Jinshan Yue1,2, Ruoyang Liu1, Xiaoyu Feng1, Zhiting Lin3, Xiulong Wu3, Xueqing Li1, Huazhong Yang1, Yongpan Liu1 Tsinghua University, Beijing, China Pi2star Technology, Beijing, China 3 Anhui
ISSCC 2020 Session 14 AI / ML
A 510nW 0.41V Low-Memory Low-Computation Keyword-Spotting Chip Using Serial FFT-Based MFCC and Binarized Depthwise Separable Convolutional Neural Network in 28nm CMOS
Weiwei Shan1, Minhao Yang2, Jiaming Xu1, Yicheng Lu1, Shuai Zhang1,
is a strong requirement for always-on speech interfaces in wearable and mobile devices, such as Voice Activity Detection (VAD) and Keyword Spotting (KWS) [1-5]. A KWS system is used to detect specific wake-up words by sp
ISSCC 2020 Session 13 Memory
A 128Gb 1b/Cell 96-Word-Line-Layer 3D Flash Memory to Improve Random Read Latency with tPROG=75µs and tR=4µs
Toshiyuki Kouchi1, Noriyasu Kumazaki1, Masashi Yamaoka1,
Sanad Bushnaq1, Takuyo Kodama1, Yuki Ishizaki1, Yoko Deguchi1, Akio Sugahara1, Akihiro Imamoto1, Norichika Asaoka1, Ryosuke Isomura1, Takaya Handa1, Junichi Sato2, Hiromitsu Komai1, Atsushi Okuyama1, Naoaki Kanagawa1, Ya
ISSCC 2020 Session 13 Memory
A 22nm 1Mb 1024b-Read and Near-Memory-Computing Dual-Mode STT-MRAM Macro with 42.6GB/s Read Bandwidth for Security-Aware Mobile Devices
Tung-Cheng Chang, Yen-Cheng Chiu, Chun-Ying Lee, Je-Min Hung,
Kuang-Tang Chang, Cheng-Xin Xue, Ssu-Yen Wu, Hui-Yao Kao, Peng Chen, Hsiao-Yu Huang, Shih-Hsih Teng, Meng-Fan Chang National Tsing Hua University, Hsinchu, Taiwan Many security-aware mobile devices, using the secure hash
ISSCC 2020 Session 13 Memory
A 22nm 32Mb Embedded STT-MRAM with 10ns Read
Speed, 1M Cycle Write Endurance, 10 Years Retention, at 150°C and High Immunity to Magnetic Field
Interference Yu-Der Chih, Yi-Chun Shih, Chia-Fu Lee, Yen-An Chang, Po-Hao Lee, Hon-Jarn Lin, Yu-Lin Chen, Chieh-Pu Lo, Meng-Chun Shih, Kuei-Hung Shen, Harry Chuang, Tsung-Yung Jonathan Chang TSMC, Hsinchu, Taiwan STT-MRA