Heterogeneous Technology Alliance Neuromorphic circuits for low-power Digital Signal Processing.

Slides:



Advertisements
Similar presentations
Mixed Signal Chip Design Lab CMOS Analog Addition/Subtraction Jaehyun Lim, Kyusun Choi Department of Computer Science and Engineering The Pennsylvania.
Advertisements

TI Information – Selective Disclosure IEEE Santa Clara ComSoc/CAS Weekend Workshop – Event-based analog sensing Theodore Yu Texas Instruments.
DIGITALLY ASSISTED ANALOG CIRCUITS PRESENTATION By Sohaib Saadat Afridi MS (EE) SEECS NUST 1.
In God We Trust Class presentation for the course: “Custom Implementation of DSP systems” Presented by: Mohammad Haji Seyed Javadi May 2013 Instructor:
Neural Cross Correlation For Radio Astronomy Chipo N Ngongoni Supervisor: Professor J Tapson Department of Electrical Engineering, University of Cape Town.
Neurmorphic Architectures Kenneth Rice and Tarek Taha Clemson University.
9/21/04ELEC / Class Projects 1 ELEC / /Fall 2004 Advanced Topics in Electrical Engineering Designing VLSI for Low-Power and.
Design Automation for VLSI, MS-SOCs & Nanotechnologies Dr. Malgorzata Chrzanowska-Jeske Mixed-Signal System-on-Chip (supported.
Challenges in Implementation of FPAA/FPGA Mixed-signal Technology
Determining the Optimal Process Technology for Performance- Constrained Circuits Michael Boyer & Sudeep Ghosh ECE 563: Introduction to VLSI December 5.
ACCESS IC LAB Graduate Institute of Electronics Engineering, NTU Fault-tolerant Multicore System on Network-on-Chip Presenter: Parhelia.
Hardware implement 涂正中. 2010:Convolutional Networks and Applications in Vision ( Overview ) Chip: first : , Bell Labs’ ANNA chip. ConvNet chip.
Floating Point vs. Fixed Point for FPGA 1. Applications Digital Signal Processing -Encoders/Decoders -Compression -Encryption Control -Automotive/Aerospace.
Transformer Based Oscillators
An Efficient Algorithm for Dual-Voltage Design Without Need for Level-Conversion SSST 2012 Mridula Allani Intel Corporation, Austin, TX (Formerly.
Variation Aware Application Scheduling in Multi-core Systems Lavanya Subramanian, Aman Kumar Carnegie Mellon University {lsubrama,
Dong Hyuk Woo Nak Hee Seong Hsien-Hsin S. Lee
Neural Cross-Correlation For Radio Astronomy Chipo N Ngongoni Supervisor: Professor J Tapson Department of Electrical Engineering, University of Cape Town.
Heterogeneous Technology Alliance Template HTA General Assembly November 12 – 13, 2013.
Heterogeneous Technology Alliance Design of ultra-low-power µ-controler in near-threshold voltage.
Implementation of Infomax ICA Algorithm with Low-Power Analog CMOS Circuits Ki-Seok Cho and Soo-Young Lee Brain Science Research Center and Department.
VADA Lab.SungKyunKwan Univ. 1 L40: Lower Power Equalizer J. W. Kim and J.D.Cho 성균관대학교
A 1-V 2.4-GHz Low-Power Fractional-N Frequency Synthesizer with Sigma-Delta Modulator Controller 指導教授 : 林志明 教授 學生 : 黃世一 Shuenn-Yuh Lee; Chung-Han Cheng;
ACCESS IC LAB Graduate Institute of Electronics Engineering, NTU Under-project Meeting Network-on-Chip Group 2007/3/07 TA: 林書彥 黃群翔.
RF network in SoC1 SoC Test Architecture with RF/Wireless Connectivity 1. D. Zhao, S. Upadhyaya, M. Margala, “A new SoC test architecture with RF/wireless.
Heterogeneous Technology Alliance mmW Radio: Multi band architecture for analog and digital processing of aggregated traffic in mmW backhaul and access.
Heterogeneous Technology Alliance SIS Facility Reloaded HTA General Assembly November 12 – 13, 2013.
Aim of neuromorphic engineering: o Design and construct physical models of biological neural networks that replicate:  robust computation  adaptability.
COARSE GRAINED RECONFIGURABLE ARCHITECTURES 04/18/2014 Aditi Sharma Dhiraj Chaudhary Pruthvi Gowda Rachana Raj Sunku DAY
Heterogeneous Technology Alliance Photonic on Silicon : Electro-optical links for massively parallel multiprocessors systems- in-package.
Prof. Dr. Martin Brooke Bortecene Terlemez
Automatic Evaluation of the Accuracy of Fixed-point Algorithms Daniel MENARD 1, Olivier SENTIEYS 1,2 1 LASTI, University of Rennes 1 Lannion, FRANCE 2.
Electrode compensation of single-electrode recordings Emulation of double-electrode recordings with a single electrode Romain Brette UNIC.
Kirchhoff Institute for Physics Johannes Schemmel Ruprecht-Karls-Universität Heidelberg 1 Accelerated Neuromorphic Hardware : Hybrid Plasticity - The Next.
ICACT 2012 Performance Study on SNMP and SIP over SCTP in Wireless Sensor Networks Advisor: Quincy Wu Speaker: Chia-Wen Lu (Sally) National Chi Nan University.
Computer Architecture Lecture 26 Past and Future Ralph Grishman November 2015 NYU.
Scheduling Issues on a Heterogeneous Single ISA Multicore IRISA, France Robert Guziolowski, André Seznec. Contact: 1. M. Becchi and P.
DEFENSE EXAMINATION GEORGIA TECH ECE P. 1 Fully Parallel Learning Neural Network Chip for Real-time Control Jin Liu Advisor: Dr. Martin Brooke Dissertation.
Low Power, High-Throughput AD Converters
Heterogeneous Technology Alliance Heterogeneous multi-core.
Low Power, High-Throughput AD Converters
Eleuterio SpiritiILC Vertex Workshop, April On pixel sparsification architecture in 130nm STM technology ILC Vertex Workshop April 2008 Villa.
Cache Miss-Aware Dynamic Stack Allocation Authors: S. Jang. et al. Conference: International Symposium on Circuits and Systems (ISCAS), 2007 Presenter:
11/15/05ELEC / Lecture 191 ELEC / (Fall 2005) Special Topics in Electrical Engineering Low-Power Design of Electronic Circuits.
EDA Challenges in Neuromorphic Computing
EU-Russia Call Dr. Panagiotis Tsarchopoulos Computing Systems ICT Programme European Commission.
IJCNN, July 27, 2004 Extending SpikeProp Benjamin Schrauwen Jan Van Campenhout Ghent University Belgium.
CONTENTS: 1.Abstract. 2.Objective. 3.Block diagram. 4.Methodology. 5.Advantages and Disadvantages. 6.Applications. 7.Conclusion.
Philipp Gysel ECE Department University of California, Davis
Inexact and Approximate Circuits for Error Tolerant Applications IcySoc RTD 2013 Jérémy Schlachter, Vincent Camus, Christian Enz Ecole polytechnique fédérale.
LOW POWER DESIGN METHODS
M V Ganeswara Rao Associate Professor Dept. of ECE Shri Vishnu Engineering College for Women Bhimavaram Hardware Architecture of Low-Power ALU using Clock.
Heterogeneous Processing KYLE ADAMSKI. Overview What is heterogeneous processing? Why it is necessary Issues with heterogeneity CPU’s vs. GPU’s Heterogeneous.
AACD’17 Workshop Report: Advanced-node Analog Circuit Design
INFN Pavia and University of Bergamo
SW Series The SW series are fast, non-latching MEMS switches available both for single mode and multimode fibers. They are available in configurations.
IEEE Council on Electronic Design Automation Sani R
Neural Cross-Correlation For Radio Astronomy
J. W. Kim and J.D.Cho 성균관대학교 Lower Power Equalizer J. W. Kim and J.D.Cho 성균관대학교 SungKyunKwan Univ.
Introducing Embedded Systems and the Microcontrollers
Georg Oberholzer, Philipp Sommer, Roger Wattenhofer
Georg Oberholzer, Philipp Sommer, Roger Wattenhofer
Paper discussed in class: H. Zhang, V. Prabhu, V. George, M. Wan, M
ITRS Design.
Design for Simple Spiking Neuron Model
Demonstration of STDP based Neural Networks on an FPGA
Design for Simple Spiking Neuron Model
A Low-Power Analog Bus for On-Chip Digital Communication
Funded by the Horizon 2020 Framework Programme of the European Union
R. Denz, TE-MPE-EP Acknowledgements: J. Steckert
Presentation transcript:

Heterogeneous Technology Alliance Neuromorphic circuits for low-power Digital Signal Processing.

The Heterogeneous Technology Alliance HTA Neuromorphic circuits for low-power Digital Signal Processing. On going projects REPTILE (2011) 65 nm 1 mm² mixed-signal design 32 Analog neurons Results 40 pJ/spike (best state-of-the-art) X30 power efficiency (digital signal processing, estimation) SPIDER (2013) Full range architecture 25x32 neurons On-going results [1] A. Joubert, et al, "Hardware spiking neurons design: Analog or digital?", in Proceedings of the 2012 Annual International Joint Conference on Neural Networks (IJCNN), June 2012 [2] A. Joubert, et al, "Capacitance of TSVs in 3-D stacked chips a problem? Not for neuromorphic systems!", in Proceedings of the 49th Annual Design Automation Conference (DAC), June 2012 [3] B. Belhadj, et al, "Configurable conduction delay circuits for high spiking rates", in Proceedings of the 2012 IEEE International Symposium on Circuits and Systems (ISCAS), May 2012

The Heterogeneous Technology Alliance HTA Project Idea: Neuromorphic circuits for low-power Digital Signal Processing EU call: Project Idea short description: Neuromorphic circuits for low-power Digital Signal Processing. Short Description: Designing a family of neuromorphic accelerators for fast/low-power signal processing Replacement of classical DSP with breakthrough power gains (30x) Potential Applications: Co-processors in multi-core of µcontroller systems Competences needed: Mix analog / digital design Network-on-Chip specific design Neuromorphic architectures programming Contact: Hubs Network infra Nodes