Yukoh Matsumoto
TOPS Systems, Japan
Challenges on Designing Parallel Processing for realizing Real-Time Applications
Download SlidesAbstract
TOPS Systems has been working on diverse of applications to accelerate for Real-Time processing, such as on-line learning, 3D Rendering, 5G, Automotive Network System, etc. Efficient parallel processing of algorithms in applications is a common issue. In this talk, challenges and innovative solutions on parallel processing design of both software and hardware for acceleration, especially based on time based quantitative design methodologies, will be discussed.
Biography
Dr. Yukoh Matsumoto is Chief Architect and CEO of TOPS Systems. His current interest is "efficient design of parallel processing" in algorithm as well as architecture. He has been proposing an efficient programming model for parallel processing, DeepPN. In his 33 years of carrier, he has architected and designed more than 10 advanced microprocessors such as SMYLEdeep for AI, Manycore for Ray Tracing, Superscalar x86 processor, etc. Prior to TOPS Systems, he worked for TI in US and Japan. He received the Dr. of Information Sciences (the Ph.D.) degree from the Graduate School of Tohoku University in 2007. He has participated in the MOT (Management of Technology) program at the Graduate School of Engineering in Tokyo University.