HPC News
Developing scientific code on the world’s fastest computers
While our world class supercomputers garner a lot of attention (we have more computers on the top 500 list as of June 2021 than any other institution!), our use of these amazing machines is enabled by the codes developed to model and simulate complex physical phenomena on massively parallel architectures.
Lawrence Livermore team looks at nuclear weapon effects for near-surface detonations
A paper in the Proceedings A of the Royal Society Publishing highlights findings by a Lawrence Livermore National Laboratory team on how nuclear weapon blasts close to the Earth’s surface create complications in their effects and apparent yields. The work is featured on the front cover of the publication.
COVID-19 detection and analysis with Nisha Mulakken
In this episode, guest Nisha Mulakken sits down with TDS to discuss COVID-19 detection and analysis.
Flux: Enabling Modern Supercomputing Workflows
Flux’s fully hierarchical resource management and graph-based scheduling features improve the performance, portability, flexibility, and manageability of both traditional and complex scientific workflows on many types of computing systems—in the cloud, at remote locations, on a laptop, or on next-generation architectures.
ISC21 event calendar
Lawrence Livermore will participate in the ISC High Performance Conference (ISC21) on June 24 through July 2. The online event brings together the HPC community—from research centers, commercial companies, academia, national laboratories, government agencies, exhibitors, and more—to share the latest technology of interest to HPC developers and users.
LLNL, IBM and Red Hat joining forces to explore standardized HPC resource management interface
LLNL, IBM and Red Hat are combining forces to develop best practices for interfacing HPC schedulers and cloud orchestrators, an effort designed to prepare for emerging supercomputers that take advantage of cloud technologies.
The U.S. Exascale Computing Project
The DOE’s Exascale Computing Project (ECP) is accelerating delivery of a capable exascale computing ecosystem to provide breakthrough modeling and simulation solutions to address the most critical challenges in scientific discovery, energy assurance, economic competitiveness, and national security. Computing principal deputy associate director and ECP deputy director Lori Diachin describes the ECP’s goals and the Laboratory's role.
Lori Diachin talks about the U.S. Exascale Computing Project
De Supinski named one of HPCwire’s 'People to Watch'
The high performance computing industry publication HPCwire named Bronis R. de Supinski, Lawrence Livermore National Laboratory’s chief technology officer for Livermore Computing, as one of its People to Watch for 2021.
COVID-19 HPC Consortium Reflects on Past Year
COVID-19 HPC Consortium scientists and stakeholders met virtually on March 23 to mark the consortium’s one-year anniversary.
Research Uncovers Missing Physics in Explosive Hotspots
Molecular dynamics simulations predict that more potential energy is localized in hotspots than their kinetic energy (or temperature) would suggest. Excess potential energy is tied to persistent strained molecular states that are primed for chemical reactions and explain why hotspots react faster than the bulk.
Livermore Converges a Slew of New Ideas for Exascale Storage
Molecular dynamics simulations predict that more potential energy is localized in hotspots than their kinetic energy (or temperature) would suggest. Excess potential energy is tied to persistent strained molecular states that are primed for chemical reactions and explain why hotspots react faster than the bulk.
Livermore’s El Capitan Supercomputer to Debut HPE Rabbit ‘Near-Node’ Storage
A near-node local storage innovation called Rabbit factored heavily into Lawrence Livermore National Laboratory’s decision to select Cray’s proposal for its CORAL-2 machine, the lab’s first exascale-class supercomputer, El Capitan.
LLNL’s de Supinski earns prestigious IEEE Fellowship
IEEE, the world's largest technical professional organization, announced it has elevated Bronis de Supinski to the rank of fellow, recognizing LLNL's Livermore Computing chief technology officer (CTO) for his leadership in the design and use of large-scale computing systems.
Blazing the Trail for Exascale Storage
To get a sense of the size and scope of the storage systems in use at Lawrence Livermore, we had a long conversation recently with Robin Goldstone, HPC strategist in the Advanced Technologies Office at Lawrence Livermore.
Lab stands tall on bi-annual list of Top500 supercomputers
Sierra was one of six Lawrence Livermore National Laboratory supercomputers to make the latest TOP500 List of the most-powerful supercomputers in the world. Sierra held on to the No. 3 spot, achieving 94.6 petaflops on the High Performance LINPACK (HPL) benchmark. LLNL’s presence was bolstered by the addition of Ruby, a recently announced computing cluster that hit 3.7 petaflops on the HPL, ranking it No. 80 in the world.
LLNL welcomes 'Ruby' supercomputer for NNSA mission and COVID-19 research
Lawrence Livermore National Laboratory’s newest supercomputer, Ruby, a 6 petaflop Intel Xeon Platinum-based cluster, will be used for unclassified programmatic work in support of the National Nuclear Security Administration’s stockpile stewardship mission, open science and the search for therapeutic drugs and designer antibodies against SARS-CoV-2, the virus that causes COVID-19.
Spack packs a development boost for top supercomputers
Spack is now the deployment mechanism for the world’s top supercomputer with its Arm base, Fugaku, and has been and 1300 packages on the Summit machine were handled by Spack. It is expected to get further momentum with the future exascale systems as well.
What Put LLNL at the Center of U.S. Supercomputing in 2020?
Lawrence Livermore National Lab has been at the forefront of newer architectures over the last year in particular across multiple systems: Mammoth, expanded Corona, Lassen with Cerebras chip, and Ruby, a top 100-class all CPU (Intel Platinum) super.
At the OpenMP Forefront
Listen to what’s coming in OpenMP 5.1 and beyond, how the C++ ecosystem is evolving, why Python in HPC, and have fun as these two razz each other.
Department of Energy to showcase scientific computational expertise at SC20
The scientific computing and networking leadership of 17 Department of Energy (DOE) national laboratories will be showcased at SC20, the International Conference for High-Performance Computing, Networking, Storage and Analysis, taking place Nov. 9-19 for the first time via a completely virtual format.