Prior to joining ADIA Lab as its inaugural Director in 2022, Dr Simon was at Berkeley Lab from 1996, having served previously as Deputy Director for Research, Associate Laboratory Director for Computing Sciences, and Director of NERSC. In his role as Deputy Director, Dr Simon was instrumental in the creation of new concepts such as Cyclotron Road and CalCharge that support energy innovation and forge stronger connections of the national labs with industry.

He has been honoured twice with the prestigious Gordon Bell Prize, in 2009 for the development of innovative techniques that produce new levels of performance on a real application (in collaboration with IBM researchers) and in 1988 in recognition of superior effort in parallel processing research (with others from Cray and Boeing). He has received the ACM SC Test of Time Award, and the SIAM CSE Career Award. He is a member of the team publishing the biannual TOP500 list of most powerful supercomputers, and he is a SIAM Fellow. 

Seminar Overview:

The field of high-performance computing (HPC) has experienced significant growth, with a major milestone being reached in 2022 with the achievement of Exascale performance level. Recent trends in HPC will be illustrated using the TOP500 list, which ranks the world's most powerful supercomputers based on their performance. However, the approaching fundamental limits of physics signal the end of Moore's Law, which has been a driving force for the development of computing, including HPC, for several decades. The future of HPC faces significant implications as a result. This talk will explore the challenges posed by the approaching limits of Moore's Law in HPC and discuss the strategies being pursued by researchers and industry to overcome these challenges, including the development of novel computing architectures, software, and algorithms, and the use of new materials and technologies. With the rise of AI as a compute-intensive application, its impact on HPC will also be examined. Furthermore, the emergence of new alternatives to traditional HPC, such as quantum computing and neuromorphic computing, will be discussed, and their potential to reshape the computing landscape will be explored.