Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:

Deep Learning on Summit Supercomputer Powers Insights for Nuclear Waste Remediation

A research collaboration between LBNL, PNNL, Brown University, and NVIDIA has achieved exaflop (half-precision) performance on the Summit supercomputer with a deep learning application used to model subsurface flow in the study of nuclear waste remediation. Their achievement, which will be presented during the “Deep Learning on Supercomputers” workshop at SC19, demonstrates the promise of physics-informed generative adversarial networks (GANs) for analyzing complex, large-scale science problems.

Podcast: ExaStar Project Seeks Answers in Cosmos

In this podcast, Daniel Kasen from LBNL and Bronson Messer of ORNL discuss advancing cosmology through EXASTAR, part of the Exascale Computing Project. “We want to figure out how space and time get warped by gravitational waves, how neutrinos and other subatomic particles were produced in these explosions, and how they sort of lead us down to a chain of events that finally produced us.”

John Shalf from LBNL on Computing Challenges Beyond Moore’s Law

In this special guest feature from Scientific Computing World, Robert Roe interviews John Shalf from LBNL on the development of digital computing in the post Moore’s law era. “In his keynote speech at the ISC conference in Frankfurt, Shalf described the lab-wide project at Berkeley and the DOE’s efforts to overcome these challenges through the development acceleration of the design of new computing technologies.”

Video: Exascale Deep Learning for Climate Analytics

Thorsten Kurth Josh Romero gave this talk at the GPU Technology Conference. “We’ll discuss how we scaled the training of a single deep learning model to 27,360 V100 GPUs (4,560 nodes) on the OLCF Summit HPC System using the high-productivity TensorFlow framework. This talk is targeted at deep learning practitioners who are interested in learning what optimizations are necessary for training their models efficiently at massive scale.”

DOE powers Aluminum and Steelmaking Research through HPC4Manufacturing Program

Today the HPC4Manufacturing Program announced four federal funding awards for solving key manufacturing challenges in steelmaking and aluminum production through supercomputing. “Primary metals industries are significant energy users, so opportunities to reduce energy consumption in this area is of great interest to our sponsors,” said HPC4Manufacturing Director Robin Miles of LLNL. “Additionally, this program is helping U.S. steel makers produce the higher strength steels vital to light weighting the next generation of automobiles.”

John Shalf and Thomas Sterling to Keynote ISC 2019 in Frankfurt

Today ISC 2019 announced that its lineup of keynote speakers will include John Shalf from LBNL and Thomas Sterling from Indiana University. The event takes place June 16-20 in Frankfurt, Germany. “On June 18, John Shalf, from Lawrence Berkeley National Laboratory will offer his thoughts on how the slowdown and eventual demise of Moore’s Law will affect the prospects for high performance computing in the next decade. On June 19, Thomas Sterling will present his annual retrospective of the most important developments in HPC over the last 12 months.”

Researchers Gear Up for Exascale at ECP Meeting in Houston

Scientists and Engineers at Berkeley Lab are busy preparing for Exascale supercomputing this week at the ECP Annual Meeting in Houston. With a full agenda running five days, LBL researchers will contribute Two Plenaries, Five Tutorials, 15 Breakouts and 20 Posters. “Sponsored by the Exascale Computing Project, the ECP Annual Meeting centers around the many technical accomplishments of our talented research teams, while providing a collaborative working forum that includes featured speakers, workshops, tutorials, and numerous planning and co-design meetings in support of integrated project understanding, team building and continued progress.”

DOE to Showcase World-Class Computational Science at SC18

Researchers and staff from 15 National Labs will showcase DOE’s latest computing and networking innovations and accomplishments at SC18 in Dallas next week. “Several of the talks and demos will highlight achievements by DOE’s Exascale Computing Program (ECP), a multi-lab, seven-year collaborative effort focused on accelerating the delivery of a capable exascale computing ecosystem by 2021.”

Job of the Week: Software Developer for the FATES Project at LBNL

LBNL is seeking a Software Developer for the FATES Project in our Job of the Week. “The engineer will work with the FATES model, which is a size and age structured dynamic vegetation model that represents plant physiology and ecosystem assembly processes for use within Earth system models. This position will be principally funded by the NGEE-Tropics project, which is a long-term, DOE-supported effort to bring together observational and theoretical approaches to build, inform, and test the representation of tropical forests within Earth system models.”

Watch 5,000 Robots Merge to Map the Universe in 3-D

In this video, scientists describe how the Dark Energy Spectroscopic Instrument (DESI) will measure the effect of dark energy on the expansion of the universe. It will obtain optical spectra for tens of millions of galaxies and quasars, constructing a 3D map spanning the nearby universe to 11 billion light years. “How do you create the largest 3D map of the universe? It’s as easy as teaching 5,000 robots how to “dance.” DESI, the Dark Energy Spectroscopic Instrument, is an experiment that will target millions of distant galaxies by automatically swiveling fiber-optic positioners (the robots) to point at them and gather their light.”