PHYSIOLOGICAL-READOUT

SESSION 14
Tuesday February 7 th , 1:30 PM
Deep-Learning Processors
Session Chair: Takashi Hashimoto, Panasonic, Osaka, Japan
Associate Chair: Mahesh Mehendale, Texas Instruments, Bangalore, India
1:30 PM
14.1 A 2.9TOPS/W Deep Convolutional Neural Network SoC in FD-SOI 28nm
DS2 for Intelligent Embedded Systems
G. Desoli 1 , N. Chawla 2 , T. Boesch 3 , S-P. Singh 2 , E. Guidetti 1 , F. De Ambroggi 4 , T. Majo 1 ,
P. Zambotti 4 , M. Ayodhyawasi 2 , H. Singh 2 , N. Aggarwal 2
1
STMicroelectronics, Cornaredo, Italy; 2 STMicroelectronics, Greater Noida, India
3
STMicroelectronics, Geneva, Switzerland; 4 STMicroelectronics, Agrate Brianza, Italy
2:00 PM
14.2 DNPU: An 8.1TOPS/W Reconfigurable CNN-RNN Processor for General-
Purpose Deep Neural Networks
D. Shin, J. Lee, J. Lee, H-J. Yoo, KAIST, Daejeon, Korea
2:30 PM
14.3 A 28nm SoC with a 1.2GHz 568nJ/Prediction Sparse Deep-Neural-
Network Engine with >0.1 Timing Error Rate Tolerance for IoT
Applications
P. N. Whatmough, S. K. Lee, H. Lee, S. Rama, D. Brooks, G-Y. Wei
Harvard University, Cambridge, MA
Break 3:00 PM
3:15 PM
14.4 A Scalable Speech Recognizer with Deep-Neural-Network Acoustic
Models and Voice-Activated Power Gating
M. Price, J. Glass, A. Chandrakasan
Massachusetts Institute of Technology, Cambridge, MA
3:45 PM
14.5 ENVISION: A 0.26-to-10TOPS/W Subword-Parallel Dynamic-Voltage-
Accuracy-Frequency-Scalable Convolutional Neural Network Processor
in 28nm FDSOI
B. Moons, R. Uytterhoeven, W. Dehaene, M. Verhelst, KU Leuven, Leuven, Belgium
4:15 PM
14.6 A 0.62mW Ultra-Low-Power Convolutional-Neural-Network Face-
DS2 Recognition Processor and a CIS Integrated with Always-On Haar-Like
Face Detector
K. Bong, S. Choi, C. Kim, S. Kang, Y. Kim, H-J. Yoo, KAIST, Daejeon, Korea
4:45 PM
14.7 A 288µW Programmable Deep-Learning Processor with 270KB On-Chip
Weight Storage Using Non-Uniform Memory Hierarchy for Mobile
Intelligence
S. Bang 1 , J. Wang 1 , Z. Li 1 , C. Gao 1 , Y. Kim 1,2 , Q. Dong 1 , Y-P. Chen 1 , L. Fick 1 , X. Sun 1 ,
R. Dreslinski 1 , T. Mudge 1 , H. S. Kim 1 , D. Blaauw 1 , D. Sylvester 1
1
University of Michigan, Ann Arbor, MI; 2 CubeWorks, Ann Arbor, MI
5:00 PM
14.8 A 135mW Fully Integrated Data Processor for Next-Generation
Sequencing
Y-C. Wu 1 , J-H. Hung 2 , C-H. Yang 1,2 , 1 National Taiwan University, Taipei, Taiwan
2
National Chiao Tung University, Hsinchu, Taiwan
Conclusion 5:15 PM
28