Schedule
16:30 – 19:00: Talks
From 19:00: Get-together
Talks
16:30
The Journey of Analog IC Design Automation
Jiang Hu, Department of ECE, Texas A&M University
Abstract: Analog integrated circuits (ICs) are integral components of nearly all electronic systems, and their designs demand tremendous time and effort from engineers with intensive training. Over the decades, there have been persistent endeavors to automate analog IC design, mirroring the successes achieved in digital circuitry. However, this journey has proven to be exceedingly challenging. In this presentation, I will provide a brief review of the history of analog IC design automation, emphasizing notable achievements in this field. Subsequently, I will offer insights regarding the key barriers encountered along this journey. Finally, I will conclude by envisioning potential future directions for advancement in this domain.
17:00
EDA Methods for Integrated Circuit Full Custom Design
Frank Schenkel
Abstract: Starting up a new business, keeping it alive, and growing it are an adventure, even more so if it is about EDA tools for analog/mixed-signal and circuit-level design. As part of the founder team of MunEDA GmbH, I will share some of the experiences that we have gained over the past years.
17:30
Optimization for AI / AI for Optimization
Wolfgang Utschick
Chair of Methods of Signal Processing, Technical University of Munich
Abstract: It is as well-known as it is evident that the art of optimizing the myriad weights of a deep neural network is the key to learning any AI. In this talk, we ask ourselves whether the art of AI is also the key to solving an optimization problem. We will approach the problem using some examples, but not purely with scientific rigor. The most complicated implications will be left for others…
18:00
Innovation, a Never Aging Relay Between Academia and Industry
Georg Georgakos, Infineon Technologies
Abstract: Collaboration between universities and industries is not running by itself. It brings overhead on both sides. There are gaps in what has to be done to bring practical problems into university research and solutions from the university back into industrial applications. From my long-term experience in the industry, I will contemplate a bit on the issues of industry and university collaboration, using practical examples.
18:30
AI/ML-infused IC Design Workflows on the Hybrid Cloud
Gi-Joon Nam, IBM T. J. Watson Research Center
Abstract: As the complexity of modern hardware systems explodes, fast and effective design space explorations for better integrated circuit (IC) implementations is becoming more and more difficult to achieve due to higher demands of computational resources. To address these problems, we have been working on AI/ML-infused IC design orchestration in order 1) to enable the IC design environment on hybrid cloud platform so that we can easily scale up/down the workloads accordingly to the computation demands; and 2) to produce higher quality of results (QoRs) in shorter total turnaround time (TAT). In this work, we will illustrate how we provide a scalable IC design workload execution that produces higher performance designs by utilizing some of AI/ML-driven techniques for IC design capabilities.
19:00
Laudatio
Ulf Schlichtmann, Ordinarius, Chair of Electronic Design Automation, Technical University of Munich
Speaker Bios
Jiang Hu is a professor in the Department of Electrical and Computer Engineering at Texas A&M University. His research interests include optimization and machine learning techniques for chip and AI hardware design automation, approximate computing and hardware security. He has co-authored more than 260 technical papers, co-invented 10 patents and co-edited a book. He received best paper awards at DAC 2001, ICCAD 2011, IEEE International Conference on Vehicular Electronics and Safety 2018, MICRO 2021 and ASPDAC 2023. He served as the technical program chair and general chair of the ACM International Symposium on Physical Design in 2011 and 2012, respectively. He was named an IEEE fellow in 2016. He was the technical program co-chair of the ACM/IEEE Workshop on Machine Learning for CAD 2023 and will be its general co-chair in 2024. Currently, he is the Editor-in-Chief of the ACM Transactions on Design Automation of Electronic Systems.
Frank Schenkel studied electrical engineering at the University of Stuttgart and the Technical University of Munich, respectively. After finishing his PhD at the Institute of Electronic Design Automation of the Technical University of Munich, he co-founded MunEDA, the leading supplier of tools for analysis, optimization, and migration of integrated full custom designs.
Wolfgang Utschick received a doctoral degree in electrical engineering from the Technical University of Munich (TUM). Before that, he completed several years of certified industrial training programs, then studied at TUM and conducted his diploma thesis work under the supervision of Claudia Latzel (née Wieser) and Helmut Gräb. He became an enthusiastic lecturer, scientist, and IEEE Fellow because of this experience! Since 2002, he has been an Extraordinarius (Associate Professor) and then Ordinarius (Full Professor) in Methods of Signal Processing at TUM. Since 2011, he has regularly taught courses in Singapore as a TUM Asia Faculty Member and as a guest professor at the Singapore Institute of Technology. In 2021, he became a core member of the newly founded Munich Data Science Institute. From 2017 to 2022, he served two terms of office as the elected Dean of the Department of Electrical and Computer Engineering, TUM. He also served on the Board of Deans for TUM's newly founded School of Communication, Information, and Technology. Wolfgang teaches courses on signal processing, stochastic processes, optimization theory, and machine learning in wireless communications, especially in the physical layer, where he is an active researcher, inventor, author, and lecturer.
Georg Georgakos received his Diploma in electrical engineering in 1987 from the University of Applied Sciences, Munich, Germany. From 1987 to 1993 he was involved in several research activities at Siemens and IBM R&D laboratories, including interconnect reliability, DUV lithography and basic analog circuits.
From 1994 until 2001 he was engaged in the development of embedded FLASH memories for automotive and smartcard applications. He started as a design engineer and took over project and program management. Since 2001 he is technical lead in Infineon’s Design Automation group responsible for Library Innovation covering standard cells, IOs and memories. His special interests are ionizing radiation effects and new methodologies in the field of Design for Reliability and IP Qualification. In numerous cooperation projects with universities he supervised Diploma, Master and PhD theses, most of them in the frame of funding projects. Furthermore he was German Project Coordinator of HONEY (BMBF /MEDEA+ funded project) and European Project Coordinator of RELY (BMBF /CATRENE funded project) which was honoured by the German edacentrum with the EDA-Achievement Award 2014. He is an author or co-author of over 40 publications in international journals and conference proceedings and holds more than 30 patents.
Gi-Joon Nam is currently a principal research scientist and the manager of the Design Automation Group in IBM’s T. J. Watson Research Center, USA. He has more than 25 years of professional experience in the semiconductor and EDA (Electronic Design Automation) industries and published over 100 technical publications and issued patents. To outreach the community further, Gi-Joon has been serving as an executive committee member of ACM SIGDA and IEEE CEDA. Also, Gi-Joon is the recipient of several IBM outstanding research awards and IBM corporate achievement awards.
Ulf Schlichtmann, see: https://www.ce.cit.tum.de/eda/personen/ulf-schlichtmann/