Moderator: Daniel Reed (University of Utah)
Panelists: Satoshi Matsuoka (RIKEN Advanced Institute for Computational Science (AICS), National Institute of Advanced Industrial Science and Technology (AIST)), Charles Catlett (Argonne National Laboratory), Rosa M. Badia (Barcelona Supercomputing Center), Greg Koenig (KPMG), Ewa Deelman (University of Southern California)
Abstract: Big data and AI are today’s memes as we shift from rare and expensive to ubiquitous and inexpensive data. Massive digital data, powerful networks and inexpensive accelerators are bringing new data-driven approaches to technical computing. Extensive instrumentation, monitoring and control of high performance computing systems and their data-centers is the big data behind big data. The emergence of big data as a reality is challenging long held beliefs about technical computing approaches and illuminating old questions in new ways. How do we best meet soft real-time constraints for streaming data, subject to energy, communication, operation and cost constraints? For example, can we use AI for performance and efficiency tuning of both HPC applications and the data-center? How does HPC respond to the rapidly shifting hardware and software vendor ecosystem emphasis on AI hardware and software? This panel will discuss how we got here and where we are likely to go.