Intel® HPC Developer Conference 2017

Keynote & Plenary Sessions

Welcome and Opening Keynote: The Future
(24 min)

Joe Curley, Gadi Singer, and Dr. Al Gara, Intel

Plenary Session: Gravitational Waves: The Role of Computing in Opening a New Field of Astronomy
(29 min)

On September 14, 2015, the two detectors of the Laser Interferometer Gravitational-Wave Observatory (LIGO) made the first direct observation of gravitational waves from two merging black holes. On August 17, 2017, the LIGO and Virgo observatories detected gravitational waves from the merging of two neutron stars—an event seen as both a short gamma-ray burst and subsequent kilonova by space- and ground-based observatories. These and other discoveries mark the beginning of gravitational wave astronomy. In this talk, we highlight what we have learned and hope to learn in this new field, and point out many of the ways in which high-throughput and high-performance computing have been essential to its progress.

Dan Stanzione, Texas Advanced Computing Center, University of Texas
Joshua L. Willis, PhD

Plenary Session: Deep Learning for Science
(57 min)

Deep learning has revolutionized the fields of computer vision, speech recognition, and control systems. Can deep learning work for scientific problems? This talk explores a variety of Lawrence Berkeley National Laboratory applications that are currently benefiting from deep learning. We cover:

  • Classification and regression problems in astronomy, cosmology, neuroscience, genomics, and high-energy physics
  • Results from a deep-dive into the problem of detecting extreme weather patterns in climate simulations
  • Short- and long-term challenges at the frontier of deep learning research, and speculation about the role of deep learning and AI in the future of scientific discovery

Mr. Prabhat and Michael F. Wehner

Plenary Session: Leading the Evolution of Compute: Neuromorphic and Quantum Computing
(33 min)

Intel recently announced important progress in the research into future novel microarchitectures and device technologies: neuromorphic and quantum computing. Neuromorphic computing draws inspiration from our current understanding of the brain’s architecture and its associated computations. Loihi, Intel's recently announced neuromorphic research chip, is extremely energy-efficient, uses data to learn and make inferences, gets smarter over time, and does not need to be trained in the traditional way. Quantum computing offers the potential for exponentially greater performance on many algorithms that are computationally challenging on today’s computing architectures. We’ve just delivered a 17 superconducting qubit chip to our research partner QuTech (TU-Delft and TNO) in the Netherlands for measurement and evaluation as part of our investigation into full computing system stacks for two quantum device technologies. This talk gives a brief overview of our directions and progress in developing these novel architectures

Jim Held, PhD, Intel