The U.S. Department of Energy (DOE) celebrates the arrival of exascale computing and its impact on breakthrough science discoveries at SC22, the International Conference for High-Performance Computing, Networking, Storage and Analysis taking place Nov. 13–18 in Dallas.
For more than 60 years, the DOE national laboratories have developed and deployed many of the world’s most powerful supercomputers. Researchers use these computing resources to tackle the most pressing scientific challenges, like climate change, national security, energy and public health.
“As the nation’s leading provider of high-performance computers, the Department of Energy recognizes that exascale systems will provide the next generation of computing we need to accelerate research,” said Barbara Helland, associate director, DOE Office of Science’s Advanced Scientific Computing Research (ASCR) program. “Supercomputers play a critical role in advancing scientific understanding and ensuring our technical leadership, economic prosperity and national security.”
Attendees at SC22 can learn from the experts at the DOE’s national laboratories. They’ll be leading tutorials, presenting technical papers, speaking at workshops, participating in birds-of-a-feather discussions and sharing ideas in panels. Labs will also be participating in the annual Job Fair.
The DOE booth (#1600) showcases the revolutionary scientific research happening at national laboratories. See how supercomputers are accelerating discoveries, integrating artificial intelligence, and creating simulations and visualizations. Check out artifacts tracing the evolution of computing nodes and graphics processing units, and browse videos that highlight what’s happening at the labs.
Don’t miss the featured talks and demos happening in the DOE booth Nov. 15–17. Topics include next-generation infrastructure, future supercomputing systems, and scientific research including that by a Gordon Bell Prize finalist. Scheduled speakers are noted below. Visit the DOE booth website (scdoe.info) for up-to-date information.
Tuesday, Nov. 15
|10: 45 a.m.||Bogdan Nicolae, Argonne National Laboratory
“Perspectives on the Versatility of a Searchable Lineage for Scalable HPC Data Management”
Checkpointing coupled with a searchable lineage that records the evolution of intermediate data and metadata during runtime can become a powerful technique in a wide range of scenarios at scale.
|11:30 a.m.||Andrew Tasmin Powis, Princeton Plasma Physics Laboratory
“Beyond Fusion— Plasma Simulation for the Semiconductor Industry”
PPPL is developing a new open-source Low-Temperature Plasma (LTP) Particle-in-Cell code. LTPs are widely applied in industry, most notably within semiconductor manufacturing.
|1 p.m.||Sunita Chandrasekaran, Brookhaven National Laboratory
Johannes Doerfert, Lawrence Livermore National Laboratory
“ECP SOLLVE and its Race to Frontier”
Hear how the OpenMP feature set is being extended to meet ECP application needs especially with regard to accelerator support.
|1:45 p.m.||James A. Ang, Pacific Northwest National Laboratory
“New Horizons for HPC”An open innovation model, guided by HPC and enabled by the CHIPS and Science Act, can be an organizing principle for future computing research, bridge new public-private partnership models, and address workforce development.
|2:30 p.m.||Dominic Manno, Los Alamos National Laboratory
“GUFI: The Grand Unified File Index: Performant, Secure, Accessible, and Extensible, Pick Any Four”
GUFI enables data center users and data center administrators to rapidly and securely search and sift through billions of file entries to rapidly locate and characterize data sets of interest.
|3:15 p.m.||Inder Monga, Lawrence Berkeley National Laboratory
“ESnet6: How ESnet’s Next-generation Infrastructure Will Enable Integrated Research Initiative Workflows”Hear about the new upgrade of ESnet6, including the architecture of the new facility, the bandwidth deployed, the automation software stack, and the services it enables.
|4 p.m.||Shantenu Jha, Brookhaven National Laboratory
“ZettaWorks: Taking ExaWorks to the Next Frontier”
Learn how ExaWorks is enabling workflows at extreme scales and a vision for ExaWorks beyond exascale.
Wednesday, Nov. 16
|10:45 a.m.||Ramakrishnan Kannan, Oak Ridge National Laboratory
“ExaFlops Biomedical Knowledge Graph Analytics”
Analysts are mining large-scale collections of written texts of scholarly publications in an effort to discover relationships among concepts. In this context, we present COAST (Exascale Communication-Optimized All-Pairs Shortest Path).
|11:30 a.m.||Chris DePrater, Lawrence Livermore National Laboratory
“Facilities Path to Exascale”
Preparing the Livermore Computing Center for El Capitan and the Exascale Era of supercomputers required an entirely new way of thinking about the facility’s mechanical and electrical capabilities.
|1 p.m.||Matthew Anderson, Idaho National Laboratory
“Field Programmable Gate Arrays in HPC Workflows”
Hear about the rise in usage of field programmable gate arrays in HPC workflows and several examples supporting nuclear energy research.
|1:45 p.m.||Stan Moore, Sandia National Laboratory
“Extreme-Scale Atomistic Simulations of Molten Metal Expansion”
Extreme-scale molecular dynamics simulations (over a billion atoms) on NNSA’s ATS-2 Sierra supercomputer models the expansion of molten supercritical material into the liquid-vapor coexistence region at the atomic level.
|2:30 p.m.||Aaron Andersen, National Renewable Energy Laboratory
“Meet Kestrel: NREL’s Third-Generation High Performance Computing System”
Learn about features of the new system and how its home, the Energy Systems Integration Facility, exemplifies energy efficiency in HPC.
|3:15 p.m.||Graham Heyes, Jefferson Lab
“Computing Models for Processing Streaming Data from DOE Science”Hear some of the techniques and challenges associated with processing streaming data from science experiments and instruments.
|4 p.m.||Lori Diachin, Lawrence Livermore National Laboratory
Erik Draeger, Oak Ridge National Laboratory
Katie Antypas, Lawrence Berkeley National Laboratory
Michael Heroux, Sandia National Laboratory
“The Exascale Computing Project”
Get an overview of the applications and software technologies being developed by ECP, including challenges in the development of new algorithms and physics capabilities that perform well on GPU-accelerated node architectures.
Thursday, Nov. 17
|10:45 a.m.||Giuseppe Barca, Ames National Laboratory
“Enabling GAMESS for Exascale Quantum Chemistry”
Learn about a novel distributed many-GPU algorithm and implementation of the Fragment Molecular Orbital method.
Follow the national labs conference participation on social media at @natlabshpc and #DOEatSC, #SC22, #HpcAccelerates.