Bio:
Takao Iwaki received his B.Sc. and M.Sc. degrees in Physics from the University of Tokyo, Japan, in 1995 and 1997, respectively, and a Ph.D. degree in Engineering from the University of Warwick, U.K., in 2008.
He has been with DENSO CORPORATION since 1997, where he has primarily engaged in the research and development of MEMS (Micro Electro Mechanical Systems)-based automotive sensors, working both in business units and research laboratories. Since 2020, he has been seconded to MIRISE Technologies Corporation, an automotive semiconductor R&D company jointly funded by Toyota and DENSO. At MIRISE, he has led the research and development of automotive SoCs (Systems on Chip), initially as Director of the Planning and Administration Division and currently as Director of the SoC R&D Division. In 2023, he began working concurrently with ASRA (Advanced SoC Research for Automotive), focusing on chiplet-based SoC technologies for automotive applications.
Abstract:
In advanced driver assistance systems and autonomous driving, sophisticated AI technologies are employed for functions such as object recognition, self-localization, and trajectory planning. Since the required AI performance varies depending on vehicle type, a wide range of SoCs (Systems on Chip) is needed—from a few TOPS to over 1,000 TOPS per generation. Developing each of these individually is impractical, which is why chiplet technology—where multiple chips are modularly combined like LEGO blocks—is attracting growing interest.
For automotive applications, key technical challenges include ensuring package reliability under harsh environmental conditions and maintaining stable, high-bandwidth communication between chiplets. Addressing these issues is essential for the successful deployment of chiplet-based SoCs in vehicles. This presentation will explore the challenges and potential solutions surrounding chiplet integration in the automotive domain.