Topic: HPC Systems and Software

An LLNL-led team has developed a method for optimizing application performance on large-scale GPU systems, providing a useful tool for developers running on GPU-based massively parallel and distributed machines.

Johannes Doerfert, a computer scientist in the Center for Applied Scientific Computing, was one of three researchers awarded the honor at SC23 in Denver.

A record number of attendees—more than 14,000—experts, researchers, vendors and enthusiasts in the field of HPC descended on the Mile High City for the 2023 International Conference for High Performance Computing, Networking, Storage and Analysis, colloquially known as SC23.

Leading HPC publication HPCwire presented Spack developers with the Editor's Choice Award for Best HPC Programming Tool or Technology at SC23.

The debut of the NNSA Commodity Technology Systems-2 computing clusters Dane and Bengal on the Top500 List of the world’s most powerful supercomputers brings the total of LLNL-sited systems on the list to 11, the most of any supercomputing center in the world.

LLNL is participating in the 35th annual Supercomputing Conference (SC23), which will be held both virtually and in Denver on November 12–17, 2023.

Merlin is an open-source workflow orchestration and coordination tool that makes it easy to build, run, and process large-scale workflows.

Over several years, teams have prepared the infrastructure for El Capitan, designing and building the computing facility’s upgrades for power and cooling, installing storage and compute components and connecting everything together. Once all the pieces are in place, the life of El Cap as world-class supercomputer begins.

The Data and Visualization efforts in the DOE’s Exascale Computing Project provide an ecosystem of capabilities for data management, analysis, lossy compression, and visualization.

Quandary is an open-source C++ package for optimal control of quantum systems on classical high performance computing platforms.

Tammy Dahlgren has worked on a variety of projects at the Lab, including supervisory control systems for the National Ignition Facility, animal disease modeling, mass hierarchical storage systems, RADIUSS, and more.

The Center for Efficient Exascale Discretizations has developed innovative mathematical algorithms for the DOE’s next generation of supercomputers.

Hosted at LLNL, the Center for Efficient Exascale Discretizations’ annual event featured breakout discussions, more than two dozen speakers, and an evening of bocce ball.

The Tri-Lab Operating System Stack (TOSS) ensures other national labs’ supercomputing needs are met.

Livermore Computing is making significant progress toward siting the NNSA’s first exascale supercomputer.

Innovative hardware provides near-node local storage alongside large-capacity storage.

Siting a supercomputer requires close coordination of hardware, software, applications, and Livermore Computing facilities.

Flux, next-generation resource and job management software, steps up to support emerging use cases.

Anna Maria Bailey, LLNL’s Chief Engineer for HPC and a Distinguished Member of Technical Staff, has enjoyed her “many careers” at the Lab and the ability to jump around to follow her interests.

Splitting memory resources in HPC between local nodes and a larger shared remote pool can help better support computational applications.

As CTO of Livermore Computing, de Supinski is responsible for formulating, overseeing, and implementing LLNL’s large-scale computing strategy, requiring managing multiple collaborations with the HPC industry and academia.

Updating a compiler can affect how code runs, leading to inconsistencies in outputs and creating problems for scientists. A new tool automatically finds the sources of these inconsistencies.

LLNL participates in the ISC High Performance Conference (ISC23) on May 21–25.

An LLNL Distinguished Member of Technical Staff, Gokhale is considered an expert in her field, and continues to enjoy the fast pace of innovation and change in computing.

LC’s adaptation of OpenZFS software provides high performance parallel file systems with better performance and scalability.