Professor, Principal Research Physicist, Princeton Plasma Physics Laboratory; Executive Committee, Princeton Institute for Computational Science & Engineering

William Tang of Princeton University is Principal Research Physicist at the Princeton Plasma Physics Laboratory (PPPL)], Lecturer with Rank & Title of Professor in the University’s Dept. of Astrophysical Sciences, Plasma Physics Section, and member of the Executive Board for the University’s interdisciplinary“Princeton Institute for Computational Science and Engineering (PICSciE)，” which he helped establish and for which he served as Associate Director (2003-2009). At PPPL, the DOE national laboratory for Fusion Energy Research, he was the Chief Scientist from 1997-2009. He is a Fellow of the American Physical Society and received the Chinese Institute of Engineers-USA Distinguished Achievement Award “for his outstanding leadership in fusion research and contributions to fundamentals of plasma science” (Oct. 2005). He headed the Basic Science Component of DOE’s Scientific Simulation Initiative (1997-98) which led to the establishment of DOE’s interdisciplinary Scientific Discovery through Advanced Computing (SciDAC) Program (2000-present), and is internationally recognized for expertise in the mathematical formalism as well as associated computational applications dealing with electromagnetic kinetic plasma behavior in complex geometries, and has well over 200 publications with more than 150 peer-reviewed papers and an “h-index” or “impact factor” of 45 on the Web of Science, including over 7000 total citations. Prof. Tang has taught for over 30 years at Princeton U. and has supervised numerous Ph.D. students, including recipients of the Presidential Early Career Award for Scientists and Engineers in 2000 and 2005.

Talk Title:

Accelerated Deep Learning Advances in HPC

Talk Abstract:

Building the scientific foundations needed to deliver accurate predictions in key scientific domains of current interest can best be accomplished by engaging modern big-data-driven statistical methods featuring machine/deep learning (ML/DL). This exciting R&D approach is increasingly deployed in many scientific and industrial domains, such as the new Internet services economy and many other emerging examples. These techniques can be formulated and adapted to enable new avenues of data-driven discovery in key scientific applications areas such as the quest to deliver Fusion Energy – identified by the 2015 CNN “Moonshots for the 21st Century” series as one of 5 prominent grand challenges. An especially time-urgent and most challenging problem facing the development of a fusion energy reactor is the need to reliably predict and avoid large-scale major disruptions in magnetically-confined tokamak systems such as the EUROfusion Joint European Torus (JET) today and the burning plasma ITER device in the near future. Significantly improved methods of prediction with better than 95% predictive capability are required to provide sufficient advanced warning for disruption avoidance or mitigation strategies to be effectively applied before critical damage can be done to ITER – a ground-breaking $25B international burning plasma experiment with the potential capability to exceed “breakeven” fusion power by a factor of 10 or more. This truly formidable task demands accuracy beyond the near-term reach of hypothesis-driven /”first-principles” extreme-scale computing (HPC) simulations that dominate current research and development in the field. Recent HPC-relevant advances in the deployment of deep learning recurrent nets have been demonstrated in exciting scaling studies of Princeton’s new Deep Learning Code -- "FRNN (Fusion Recurrent Neural Net) Code on modern GPU systems. This is clearly a “big-data” project in that it has direct access to the huge EUROFUSION/JET disruption data base of over a half-petabyte to drive these studies1. FRNN implements a distributed data parallel synchronous stochastic gradient approach with “Tensorflow” and “Theano” libraries at the backend and MPI for communications.This has enabled good progress toward the goal of establishing the practical feasibility of using leadership class supercomputers to greatly enhance training of neural nets to enable transformational impact on key discovery science application domains such as Fusion Energy Science. Powerful systems targeted for near-future deployment of our deep learning software include:（1） NVIDIA’s SATURN V – featuring it’s nearly 1000 Pascal P100 GPU’s;(2) Switzerland’s “Piz Daint”CRAY XC50 system with its 4500 P100 GPU’s;(3) Japan’s new “Tsubame 3” system with 3000 P-100 GPU’s; and OLCF’S “Summit-Dev” system. Summarily, statistical Deep Learning software trained on very large data sets hold exciting promise for delivering much-needed predictive tools capable of accelerating scientific knowledge discovery in HPC. The associated creative methods being developed also have significant potential for cross-cutting benefit to a number of important application areas in science and industry.

Update my resume!