Topic: HPC Systems and Software

With a history of student participation and committee service, LLNL computer scientist Kathleen Shoga chaired this year’s competition.

For the first time ever, SC21 went hybrid, with dozens of both in-person and virtual workshops, technical paper presentations, panels, tutorials and “birds of a feather” sessions.

SC21's inaugural Best Reproducibility Advancement Award went to an LLNL team for a benchmark suite aimed at simplifying the evaluation process of approximation techniques for scientific applications.

LLNL is participating in the 33rd annual Supercomputing Conference (SC21), which will be held both virtually and in St. Louis on November 14–19, 2021.

“We’re very excited about the program content. It’s going to be one of the best SC programs ever,” said SC21 General Chair Bronis R. de Supinski, chief technology officer for Livermore Computing at LLNL.

In this IDEAS-ECP webinar, Jean Shuler, who joined LLNL in 1972, shares her stories providing support on a range of computing architectures. The video is an hour long.

The DOE's Exascale Computing Project compiled a video playlist for Exascale Day on October 18 (10¹⁸).

The renowned worldwide competition announced the winners of the 2021 R&D 100 Awards, among them LLNL's Flux workload management software framework in the Software/Services category.

Though the arrival of the exascale supercomputer El Capitan at LLNL is still almost two years away, teams of code developers are busy working on predecessor systems to ensure critical applications are ready for Day One.

To prepare for the next generation of power-hungry supercomputers, LLNL crews have been working throughout the pandemic on a $100 million Exascale Computing Facility Modernization project.

LLNL and partners have awarded a subcontract to Dell Technologies for additional supercomputing systems to support the NNSA's nuclear deterrent mission.

A newly funded project involving LLNL computer scientist Ignacio Laguna will examine numerical aspects of porting scientific applications to different HPC platforms.

From studying radioactive isotope effects to better understanding cancer metastasis, the Laboratory’s relationship with cancer research endures some 60 years after it began, with historical precedent underpinning exciting new research areas.

The renowned worldwide competition announced the finalists for the 2021 R&D 100 Awards, among them LLNL's Flux workload management software framework in the Software/Services category.

At the AWS/Arm Cloud Hackathon, Todd Gamblin and Greg Becker discuss the essential skills and concepts needed to understand how to create and deploy Spack recipes to build scientific codes.

Each new season brings another hackathon, and Computing’s 2021 summer event took place on August 12–13.

The Center for Non-Perturbative Studies of Functional Materials under Non-Equilibrium Conditions advances high performance computing software to support novel materials discovery.

A Livermore-developed programming approach helps software to run on different platforms without major disruption to the source code.

Supported by the Advanced Simulation and Computing program, Axom focuses on developing software infrastructure components that can be shared by HPC apps running on diverse platforms.

Our use of supercomputers is enabled by the codes developed to model and simulate complex physical phenomena on massively parallel architectures.

LLNL participates in the digital ISC High Performance Conference (ISC21) on June 24 through July 2.

This video describes Flux, an open-source software framework that manages and schedules computing workflows to maximize available resources to run applications faster and more efficiently.

Computer scientist Vanessa Sochat isn’t afraid to meet new experiences head on. With a Stanford PhD and a jump-right-in attitude, she joined LLNL to work on the BUILD project, Spack package manager, and other open-source initiatives.

In a talk recorded for the 2020 LLNL Computing Virtual Expo, Computing principal deputy associate director and ECP deputy director Lori Diachin describes the ECP’s goals and the Laboratory's role.

LLNL, IBM, and Red Hat will develop best practices for interfacing HPC schedulers and cloud orchestrators in preparation for supercomputers that use cloud technologies.