Topic: Co-Design

The NNSA’s exascale milestone is possible only through successful industry partnerships. Hewlett Packard Enterprise staff share their experiences working with LLNL.

The El Capitan Center of Excellence provides a conduit between national labs and commercial vendors, ensuring that the exascale system will meet everyone’s needs.

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.

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.

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.

The addition of the spatial data flow accelerator into LLNL’s Livermore Computing Center is part of an effort to upgrade the Lab’s cognitive simulation (CogSim) program.

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

Highlights include MFEM community workshops, compiler co-design, HPC standards committees, and AI/ML for national security.

LLNL and Amazon Web Services (AWS) have signed a memorandum of understanding to define the role of leadership-class HPC in a future where cloud HPC is ubiquitous.

Technologies developed through the Next-Generation High Performance Computing Network project are expected to support mission-critical applications for HPC, AI and ML, and high performance data analytics.

LC sited two different AI accelerators in 2020: the Cerebras wafer-scale AI engine attached to Lassen; and an AI accelerator from SambaNova Systems into the Corona cluster.

The MAPP incorporates multiple software packages into one integrated code so that multiphysics simulation codes can perform at scale on present and future supercomputers.

Proxy apps serve as specific targets for testing and simulation without the time, effort, and expertise that porting or changing most production codes would require.

Highlights include recent LDRD projects, Livermore Tomography Tools, our work with the open-source software community, fault recovery, and CEED.

Veritas provides a method for validating proxy applications to ensure that they capture the intended characteristics of their parents.