Hosted at Trinity College, Dublin, Ireland
Schools of Engineering and Computer Science & Statistics
Linda Doyle - The future of communications and its computational landscape
Linda Doyle is the Director of Research and Professor of Engineering and The Arts in Trinity College Dublin. Prof. Doyle was also the Director of CONNECT. Her expertise is in the fields of wireless communications, cognitive radio, reconfigurable networks, spectrum management and creative arts practices. She has raised over €70 million in research funding in the past decade and has published widely in her field. Prof. Doyle has a reputation as an advocate for change in spectrum management practices and has played a role in spectrum policy at the national and international level. Currently she is a member of the National Broadband Steering Committee in Ireland, and is a member of the Ofcom Spectrum Advisory Board in the UK. Prof. Doyle is on the advisory board of Wireless@KTH in Sweden. She is a Fellow of Trinity College Dublin. She is on the Board of the Festival of Curiosity – a STEM outreach activity for children based on a city-centre yearly science festival. She is also a judge in the BT Young Scientist, Ireland’s premier science competition for school children. She is on the Boards of the Douglas Hyde Gallery and Pallas Studios. Prof. Doyle is a Director of Xcelerit and SRS, two CTVR/CONNECT spin-outs.
Brendan Farley - Implementing Software Defined Radios for 5G with Next Generation FPGA’s
In emerging 5G base station architectures, the radio bandwidth and channel count will expand rapidly and the performance requirements will vary widely. Any commercial solution must be delivered with lower power and smaller footprint and in a cost-effective manner. Recent advances in FPGA technology enable direct digitization and synthesis of RF carriers by the FPGA, allowing traditional RF functions such as custom analog mixers and local oscillators to be moved to the digital domain. This provides a flexible, software programmable digital-RF platform to address of the myriad of emerging 5G radio requirements. And by implementing these features in FinFET technology, the cost, power and footprint of the solution can be radically reduced.
Brendan Farley is Vice President of Engineering at US multinational technology corporation Xilinx Inc. where he is responsible for Analog and RF development including the recently announced RFSoC devices. Brendan previously held various R&D management roles at former Philips Research subsidiary, S3 Group, in the area of SOC development and high performance mixed signal IP licensing. He directed HDMI transceiver development in the high technology start-up, Redmere Technology and was Chief Technology Officer at automation company, Cylon Controls. He is a regular presenter at industry conferences and forums, most recently at the 2017 Hot Chips Symposium on High Performance Circuits and the 2017 Asian Solid State Circuits Conference. Brendan is a member of the Board of Microelectronics Competence Centre Ireland and holds a Bachelor of Science Degree in Electronic Engineering from Trinity College Dublin and a Master of Science Degree in Technology Management from NUI Galway.
Patrick Dorsey - SiP Integration of Reusable Chiplets
This talk will provide an overview of a trend to pursue SiP (System in Package) integration. SiP solutions support the disaggregation of IP blocks away from monolithic SoC structures and integration of board components to reduce latency and improve form factor. Disaggregation is driven by a desire to increase IP portability, harness the benefits of dissimilar technology nodes, address lithographic reticle size limitations and quickly create market targeted products. An ecosystem based on SiP integration of reusable chiplets is on the horizon. This ecosystem needs high density SiP technologies which provide scalable “monolithic like” integration capabilities. We will explore how technologies like Intel EMIB, Intel AIB and CoWoS can be employed to address these SiP trends and propose a solution to address the needs of this emerging ecosystem.
Patrick Dorsey is the Senior Director, Strategy & Planning, Intel Corporation. He is responsible for the Strategy Office for Intel’s Programmable Solutions Group. He guides teams researching new technologies, applications, and markets for FPGA-based platforms through collaboration with suppliers, customers and the ecosystem. Patrick Dorsey joined Intel PSG (Altera) in 2011 and was previously Sr. Director of Marketing at Intel PSG (Altera) responsible for product marketing worldwide. Previously, Patrick was Senior Director of Product Marketing at Xilinx. He has been involved in technology marketing and solutions development for more than 25 years including Director of Marketing, Technical Marketing, and Product Planning for tools and server products at Sun Microsystems; and sales/consulting roles at Texas Instruments and Deloitte Consulting. Patrick holds a bachelor’s degree in Computer Engineering and a masters degree in Business Administration both from the University of Michigan.
Vivienne Sze - Energy-Efficient Edge Computing for AI-driven Applications
Edge computing near the sensor is preferred over the cloud due to privacy or latency concerns for a wide range of applications including robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to throughput and accuracy requirements. In this talk, we will describe how joint algorithm and hardware design can be used to reduce energy consumption while delivering real-time and robust performance for applications including deep learning, computer vision, autonomous navigation and video/image processing. We will show how energy-efficient techniques that exploit correlation and sparsity to reduce compute, data movement and storage costs can be applied to various AI tasks including object detection, image classification, depth estimation, super-resolution, localization and mapping. Finally, we will discuss how to efficiently maintain flexibility when building energy efficient and high performance accelerators in the rapidly moving field of deep learning.
Vivienne Sze is an Associate Professor at MIT in the Electrical Engineering and Computer Science Department. Her research interests include energy-aware signal processing algorithms, and low-power circuit and system design for portable multimedia applications, including computer vision, deep learning, autonomous navigation, and video process/coding. Prior to joining MIT, she was a Member of Technical Staff in the R&D Center at TI, where she designed low-power algorithms and architectures for video coding. She also represented TI in the JCT-VC committee of ITU-T and ISO/IEC standards body during the development of High Efficiency Video Coding (HEVC), which received a Primetime Emmy Engineering Award. She is a co-editor of the book entitled “High Efficiency Video Coding (HEVC): Algorithms and Architectures” (Springer, 2014). Prof. Sze received the B.A.Sc. degree from the University of Toronto in 2004, and the S.M. and Ph.D. degree from MIT in 2006 and 2010, respectively. In 2011, she received the Jin-Au Kong Outstanding Doctoral Thesis Prize in Electrical Engineering at MIT. She is a recipient of the 2017 Qualcomm Faculty Award, the 2016 Google Faculty Research Award, the 2016 AFOSR Young Investigator Research Program (YIP) Award, the 2016 3M Non-Tenured Faculty Award, the 2014 DARPA Young Faculty Award, the 2007 DAC/ISSCC Student Design Contest Award, and a co-recipient of the 2016 IEEE Micro Top Picks Award and the 2008 A-SSCC Outstanding Design Award. For more information about research in the Energy-Efficient Multimedia Systems Group at MIT visit: http://www.rle.mit.edu/eems/
Dan Werthimer - Searching for E.T. with FPGAs
What is the possibility of other intelligent life in the universe? Can we detect radio, infrared, or visible light signals from alien civilizations? Current and future projects searching for such signals, including the new $100-million Breakthrough Prize Foundation Listen project, may provide an answer. Dan Werthimer will describe plans for future searches and show how new technologies, are revolutionizing the search for extraterrestrial intelligence (SETI). Dan will also describe Berkeley’s SETI@home project, which analyzes data from the world’s largest radio telescopes using desktop computers and cell phones from millions of volunteers, forming one of Earth’s most powerful supercomputers. Dan will discuss next generation radio telescopes, such as the Square Kilometer Array, that are composed of hundreds to thousands of smaller telescopes; these large arrays require peta-ops per second of real time processing to combine telescope signals, generate spectra-images, and search for radio signals from extraterresrial civilizations. Dan will describe these telescopes, their instrumentation, and the motivation for peta-op/sec FPGA systems. Open source hardware, software, libraries, tools, reference designs and video training are available at http://casper.berkeley.edu
Dan Werthimer is co-founder and chief scientist of the SETI@home project and directs other UC Berkeley SETI searches at radio, infrared and visible wavelengths, including the Search for Extra-Terrestrial Radio Emissions from Nearby Developed Intelligent Populations (SERENDIP). He is also the principal investigator for the worldwide Collaboration for Astronomy Signal Processing and Electronics Research (CASPER).
Marilyn Wolf - IoT Systems Caring Analytics for Long-Term Care of People with Special Needs
This talk describes our efforts to build cyber-physical systems to help care for people with special needs. The term “special needs” covers a wide range of cognitive and physical limitations. With a growing worldwide population of people with special needs, we need to find new ways to give these people meaningful lives. Because the special needs population covers such a wide range of conditions, the traditional, diagnosis-driven medical approach will not scale. IoT systems built from distributed sensors and data analytics. This talk will frame the long-term care problem, describe prototype IoT architectures, and present analysis algorithms to generate actionable information from sensor data.
Marilyn Wolf is Farmer Distinguished Chair in Embedded Computing Systems and GRA Eminent Scholar at the Georgia Institute of Technology. She received her BS, MS, and PhD in electrical engineering from Stanford University in 1980, 1981, and 1984. She was with AT&T Bell Laboratories from 1984 to 1989. She was on the faculty of Princeton University from 1989 to 2007. Her research interests include cyber-physical systems, embedded computing, embedded video and computer vision, and VLSI systems. She has received the ASEE Terman Award and IEEE Circuits and Systems Society Education Award. She is a Fellow of the IEEE and ACM.