In this special guest feature, Murali Emani from Argonne writes that a team of scientists from DoE labs have formed a working group called MLPerf-HPC to focus on benchmarking machine learning workloads for high performance computing. “As machine learning (ML) is becoming a critical component to help run applications faster, improve throughput and understand the insights from the data generated from simulations, benchmarking ML methods with scientific workloads at scale will be important as we progress towards next generation supercomputers.”
LBNL Breaks New Ground in Data Center Optimization
February 19, 2020 by
Berkeley Lab has been at the forefront of efforts to design, build, and optimize energy-efficient hyperscale data centers. “In the march to exascale computing, there are real questions about the hard limits you run up against in terms of energy consumption and cooling loads,” Elliott said. “NERSC is very interested in optimizing its facilities to be leaders in energy-efficient HPC.”
Supercomputing a Neutron Star Merger
December 16, 2019 by
Scientists are getting better at modeling the complex tangle of physics properties at play in one of the most powerful events in the known universe: the merger of two neutron stars. “We’re starting from a set of physical principles, carrying out a calculation that nobody has done at this level before, and then asking, ‘Are we reasonably close to observations or are we missing something important?’” said Rodrigo Fernández, a co-author of the latest study and a researcher at the University of Alberta.
Department of Energy to Showcase World-Leading Science at SC19
November 12, 2019 by
The DOE’s national laboratories will be showcased at SC19 next week in Denver, CO. “Computational scientists from DOE laboratories have been involved in the conference since it began in 1988 and this year’s event is no different. Experts from the 17 national laboratories will be sharing a booth featuring speakers, presentations, demonstrations, discussions, and simulations. DOE booth #925 will also feature a display of high performance computing artifacts from past, present and future systems. Lab experts will also contribute to the SC19 conference program by leading tutorials, presenting technical papers, speaking at workshops, leading birds-of-a-feather discussions, and sharing ideas in panel discussions.”
Epic HPC Road Trip stops at NERSC for a look at Big Network and Storage Challenges
November 12, 2019 by
In this special guest feature, Dan Olds from OrionX continues his Epic HPC Road Trip series with a stop at NERSC. “NERSC is unusual in that they receive more data than they send out. Client agencies process their raw data on NERSC systems and then export the results to their own organizations. This puts a lot of pressure on storage and network I/O, making them top priority at NERSC.”
NERSC Unveils Mural for pending Perlmutter Supercomputer
October 4, 2019 by
NERSC has unveiled the mural that will grace the cabinets of the Perlmutter supercomputer that will be installed at Berkeley Lab in 2020. “The mural pays tribute to the system’s namesake, Nobel Laureate Saul Perlmutter. The Berkeley Lab physicist led the team whose work at NERSC contributed to the Nobel prize-winning insight that the universe’s expansion is speeding up. The resulting efforts to explain this acceleration led to today’s model of a universe dominated by dark energy and dark matter.”
Supercomputing and the Scientist: How HPC and Analytics are transforming experimental science
September 5, 2019 by
In this video from DataTech19, Debbie Bard from NERSC presents: Supercomputing and the scientist: How HPC and large-scale data analytics are transforming experimental science. “Debbie Bard leads the Data Science Engagement Group NERSC. NERSC is the mission supercomputing center for the USA Department of Energy, and supports over 7000 scientists and 700 projects with supercomputing needs.”
Supercomputing Post-Wildfire Water Availability
September 4, 2019 by
A new study by scientists at Lawrence Berkeley National Laboratory (Berkeley Lab) uses a numerical model of an important watershed in California to shed light on how wildfires can affect large-scale hydrological processes, such as stream flow, groundwater levels, and snowpack and snowmelt. The team found that post-wildfire conditions resulted in greater winter snowpack and subsequently greater summer runoff as well as increased groundwater storage.
HPC Innovation Excellence Award Showcases Physics-based Scientific Discovery
August 17, 2019 by
A collaboration that includes researchers from NERSC was recently honored with an HPC Innovation Excellence Award for their work on “Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems.” The award was presented in June by Hyperion Research during the ISC19 meeting in Frankfurt, Germany.
Designing Future Flash Storage Systems for HPC and Beyond
August 4, 2019 by
Glenn Lockwood from NERSC gave this talk at the Samsung Forum. “In this talk, we will compare the storage and I/O requirements of large-scale HPC workloads with those of the cloud and show how HPC’s unique requirements have led NERSC to deploy NVMe in the form of burst buffers and all-flash parallel file systems rather than block- and object-based storage. We will then explore how recent technological advances that target enterprise and cloud I/O workloads may also benefit HPC, and we will highlight a few remaining challenge areas in which innovation is required.”
