858. The Future of Computing:

Domain-Specific Accelerators

■연사: Bill Dally, NVIDIA Chief Scientist and Stanford University Professor

■일시: 2018년 11월 28일(수), 16:30 ~ 18:00

■장소: 서울대학교 제2공학관(302동) 105호

Abstract:

Scaling of computing performance enables new applications and greater value from computing.  With the end of Moore’s Law and Dennard Scaling, continued performance scaling will come primarily from specialization.   Graphics processing units are an ideal platform on which to build domain-specific accelerators. They provide very efficient, high performance communication and memory subsystems - which are needed by all domains.  Specialization is provided via “cores”, such as tensor cores or ray-tracing cores that accelerate specific applications. This talk will describe some common characteristics of domain-specific accelerators via case studies.

Biography:

• 학력

  Virginia Polytechnic Institute and State University 전기공학 학사

  Stanford University 전기공학 석사

  California Institute of Technology 컴퓨터과학 박사

• 경력

  2009- NVIDIA Chief Scientist and Senior Vice President of Research

  1997- Professor of Computer Science and Electrical Engineering Department at Stanford University