AbstractThe talk will first address the challenges the traditional computer architectures and device technologies are facing. Then, an overview of alternative computing notions based on different potential technologies will be given. Thereafter, computation-in-memory paradigm based on emerging memristive devices will be explored, starting from the basic concepts, logic operation, arithmetic operations, up to the architecture and its huge potential in realizing order of magnitude improvement as compared with the state-of-the art architectures, at least for some applications.
BiographyHamdioui is currently Chair Professor on Dependable and Emerging Computer Technologies and Head of the Computer Engineering Laboratory (CE-Lab) of the Delft University of Technology, the Netherlands. He received the MSEE and PhD degrees (both with honors) from TUDelft. Prior to joining TUDelft as a professor, Hamdioui spent about seven years within industry including Microprocessor Products Group at Intel Corporation (Califorina, USA), IP and Yield Group at Philips Semiconductors R&D (Crolles, France) and DSP design group at Philips/ NXP Semiconductors (Nijmegen, The Netherlands). His research focuses on two domains: Dependable CMOS nano-computing (including Reliability, Testability, Hardware Security) and emerging technologies and computing paradigms (including 3D stacked ICs, memristors for logic and storage, in-memory-computing for big-data applications).
AbstractThe innovation in the Automotive domain today is characterized by three major trends:
- the transition from combustion engines to Full Electric Vehicles,
- the introduction of highly complex and safety relevant ADAS assistant systems including first Autonomous Driving (AD) functions which demands fail-operational systems and
- the Connected Car – the introduction of large traffic management systems solutions.
Current EE-architectures with up to 100 dedicated ECUs are no longer capable to answer the demand towards increased compute performance, fail-operational, safety and security and real-time behavior (RT).
Therefore new vehicle EE-architectures based on only a few powerful ‘high performance’ compute platforms capable to calculate sensor data fusion like vision recognition in real time in are highly appreciated.
Automotive could be treated as the appropriate touchstone for the deployment of computation technology in a lot of further embedded domains like machinery, medical, avionics, trains and many more.
BiographyKnut Hufeld has been working for Infineon Technologies AG and the former Siemens Semiconductor Division since 1995. He received his diploma in electrical engineering/informatics (M.S. degree) from the Technical University of Ilmenau, Germany, in 1993. Knut Hufeld worked in several research departments on system process control, parallel processing and algorithmic characterisation of parasitic effects in circuit design at Siemens Corporate Research and later Infineon. Since 2001 he coordinates funded research programs on European and national scale for Infineon.
Knut Hufeld was active in the Artemis SRA discussion since the beginning and had become a member of the Artemis-IA Steering Board in 2012 and of the Artemis-IA Presidium in 2017. He is also representing Infineon in national and European expert groups as counterpart to the German and European PAs. As coordinator of funded research programs for Infineon Technologies AG, Knut Hufeld is personally involved in several H2020 and ECSEL projects – like Productive4.0 or EPI- the European Processor Initiative for Low power High Performance Computing. In 2017 Knut Hufeld became a member of the Advisory Board, the LIASE, of the ECSEL lighthouse initiative Industry4.E on Digital Industry. Knut Hufeld has a long term experience on PPP activities, representing the Infineon Technologies AG in several strategic research initiatives and organizations like eNova, the strategy platform for e-mobility and autonomous driving of the German Automotive Industry or as steering board member of ETP4HPC, the European Technology Platform for High Performance Computing.
Areas of expertise
- Semiconductor process technology
- Power semiconductors and modules
- Microcontroller – MultiCore
- Embedded Systems / Cyber Physical Systems
- High performance computing
University Program Manager EMEA, Cadence
AbstractCadence Academic Network plays a critical role in bridging the divide between industry and academia. For over 10 years, their work has been focused on addressing this need by improving resources provided to universities and research institutes and building relationships with professors across the globe. Creating this knowledge network enables the universities to take their classroom teaching and fundamental research to the next level. Relationships built between industry and academia creates an environment where both sides are able to benefit and create the technologies of tomorrow. As a global partner to academia, the Cadence Academic Network is proving to industry that academia matters.
Join Anton Klotz, University Program Lead EMEA, Cadence Design Systems, to learn more about the journey of the Cadence Academic Network.
BiographyAnton Klotz is managing Cadence Academic Network in EMEA region. Started 10 years ago Academic Network is standing on four pillars, which are providing academic licenses to universities and research institutes, either direct or through academic distributors, marketing activities with academia (organizing and sponsoring conferences, workshops, tutorials, contests), running internship program and looking out for collaborative research possibilities with academia. Prior to that Anton worked 10 years as application engineer at Cadence, where he was responsible for verification of large digital designs in advanced nodes. Anton received his diploma in technical computer sciences from Mannheim University, Germany.