2021 International Conference On
Computer Aided Design
The Premier Conference Devoted to Technical Innovations in
Electronic Design Automation
Virtual Technical Program:
November 1-4, 2021 Networking In-Person:
November 5, 2021
HOME» CONFERENCE» KEYNOTES
Virtual Technical Program
7:00 - 8:00 am
Massachusetts Institute of Technology (MIT)
Efficient Computing for AI and Robotics: From Hardware Accelerators to Algorithm Design
The compute demands of AI and robotics continue to rise due to the rapidly growing volume of data to be processed; the increasingly
complex algorithms for higher quality of results; and the demands for energy efficiency and real-time performance. In this talk,
we will discuss the design of efficient hardware accelerators and the co-design of algorithms and hardware that reduce the energy
consumption while delivering real-time and robust performance for applications including deep neural networks and autonomous navigation.
We will also highlight important design principles, methodologies, and tools that can facilitate an effective design process.
Vivienne Sze (http://sze.mit.edu/) is an associate professor in MIT’s Department of Electrical Engineering and Computer Science and
leads the Research Lab of Electronics’ Energy-Efficient Multimedia Systems research group. Her group works on computing systems that
enable energy-efficient machine learning, computer vision, and video compression/processing for a wide range of applications,
including autonomous navigation, digital health, and the internet of things. She is widely recognized for her leading work in
these areas and has received many awards, including faculty awards from Google, Facebook, and Qualcomm, the Symposium on VLSI
Circuits Best Student Paper Award, the IEEE Custom Integrated Circuits Conference Outstanding Invited Paper Award, and the IEEE
Micro Top Picks Award. As a member of the Joint Collaborative Team on Video Coding, she received the Primetime Engineering Emmy
Award for the development of the High-Efficiency Video Coding video compression standard. She is a co-author of the book
entitled “Efficient Processing of Deep Neural Networks”.
7:00 - 8:00 am
Ecole Polytechnique Fédérale de Lausanne (EPFL)
Challenges and opportunities in GaN power electronics
Electricity is the fastest growing form of end-use energy, however a considerable portion of the electricity consumed worldwide is
wasted in power conversion, especially in power semiconductor devices. The outstanding properties of Gallium Nitride and other
wideband gap semiconductors for power electronic devices can enable significantly more efficient and compact future power converters.
These devices are currently becoming ubiquitous in power electronic circuits, however due to their different physical process
compared to common power electronic devices, there is a lack of proper compact modeling tools that correctly represent their
behavior under different conditions as well as computer-aided design and optimization approaches to automatically optimize the
device design. This talk will present the principles, state-of-the-art and challenges of GaN power devices for efficient power
conversion, aiming to open opportunities for device modeling and automation in the field of power electronics.
Elison Matioli is a professor in the institute of electrical engineering at Ecole Polytechnique Fédérale de Lausanne (EPFL), since
2015. He received a B.Sc. degree in applied physics and applied mathematics from Ecole Polytechnique (Palaiseau, France), followed
by a Ph.D. degree from the Materials Department at the University of California, Santa Barbara (UCSB) in 2010. He was a post-doctoral
fellow in the EECS department at the Massachusetts Institute of Technology (MIT) until 2014. He has received the UCSB Outstanding
Graduate Student - Scientific Achievement Award for his Ph.D. work, the 2013 IEEE George Smith Award, the 2015 ERC Starting Grant
Award, the 2016 SNSF Assistant Professor Energy Grant Award and the 2020 University Latsis Prize.
7:00 - 8:00 am
University of California, Berkeley
RISC-V Is Inevitable
This talk reviews the history, current state, and future directions of RISC-V ("RISC Five"), an open instruction set architecture
that is growing in commercial significance. It covers:
Novel features of the recent instruction set extensions, such as vector and bit manipulation;
Compares their efficiency to conventional proprietary instruction sets; and
Gives examples of advances in computer security due to the open instruction set by allowing anyone to test their ideas end-to-end
via red team attacks over the Internet on full scale hardware/software systems based on novel architecture features implemented via
FPGAs that can be iterated weekly.
David Patterson is a UC Berkeley professor, Google distinguished engineer, RISC-V International Vice-Chair, and RISC-V International
Open Source Laboratory Director. His best known projects are RISC and RAID. He co-authored seven books, including Computer Architecture:
A Quantitative Approach, and shared the 2017 ACM A.M Turing Award shared with his co-author John Hennessy.
10:00 - 11:00 am
Robert Bosch GmbH
Designing Reliable Distributed Systems
Software is disrupting one industry after the other. Currently, the automotive industry is feeling the pinch to innovate in the
software business. New, innovative approaches to vehicles and their HW/SW architectures are needed and are currently subsumed under
the term SW-defined Vehicle. This trend however does not stop at vehicle boundaries but includes off-board communication with edge
and cloud services. Thinking it further, this results in a disruptive technology we call Reliable Distributed Systems (RDS),
enabling the operation of vehicles, where parts, such as sensing and compute are no longer bound to the vehicle, but can be
performed in an edge-cloud continuum. Reliable Distributed Systems are not limited to automotive use cases. By making compute
and sensing ubiquitously available, as well as offering transparent communications, applications in several domains are possible:
from industrial automation, over building automation to consumer robotics. However, designing Reliable Distributed Systems
raises several questions and poses new challenges for electronic design automation.
Dirk Ziegenbein is chief expert for open context systems engineering and leads a research group developing methods and technologies
for software systems engineering at Bosch Corporate Research in Stuttgart, Germany. He held several positions in R&D (software
component technology, scheduling analysis and software architectures for multi-cores) and product management (embedded software
engineering tools). Dirk is an initiator of the DATE Special Initiative on Autonomous Systems Design.