Topic: Storage, File Systems, and I/O

This interview with HPC-AI Vanguard Kathryn Mohror covers her thoughts on teamwork, her projects, the field, and more.

The latest issue of R&D World's magazine showcases LLNL's 2024 winning technologies, including UnifyFS and UMap software projects.

The Association for Computing Machinery's (ACM) Special Interest Group on High Performance Computing (SIGHPC) has awarded Kathryn Mohror with its prestigious Emerging Woman Leader in Technical Computing (EWLTC) Award.

Bugs, broken codes, or system failures require added time for troubleshooting and increase the risk of data loss. LLNL has addressed failure recovery by developing the Scalable Checkpoint/Restart (SCR) framework.

With SCR, jobs run more efficiently, recover more work upon failure, and reduce load on critical shared resources.

This open-source file system framework accelerates hierarchical HPC I/O operations with effective, efficient use of node-local storage.

Discover how the software architecture and storage systems that will drive El Capitan’s performance will help LLNL and the NNSA Tri-Labs push the boundaries of computational science.

LLNL's Ian Lee joins a Dots and Bridges panel to discuss HPC as a critical resource for data assimilation and numerical weather prediction research.

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

A research team from Oak Ridge and Lawrence Livermore national labs won the first IPDPS Best Open-Source Contribution Award for the paper “UnifyFS: A User-level Shared File System for Unified Access to Distributed Local Storage.”

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

A multidecade, multi-laboratory collaboration evolves scalable long-term data storage and retrieval solutions to survive the march of time.

LLNL is home to the world’s largest Spectra TFinity^TM system, which offers the speed, agility, and capacity required to take LLNL into the exascale era.

As Computing’s sixth Fernbach Fellow, postdoctoral researcher Chen Wang will work on a new I/O programming paradigm and improve HPC storage consistency models under the mentorship of Kathryn Mohror.

Livermore’s archive leverages a hierarchical storage management application that runs on a cluster architecture that is user-friendly, extremely scalable, and lightning fast.

LLNL participates in the International Parallel and Distributed Processing Symposium (IPDPS) on May 30 through June 3.

From molecular screening, a software platform, and an online data to the computing systems that power these projects.

El Capitan will have a peak performance of more than 2 exaflops—roughly 16 times faster on average than the Sierra system—and is projected to be several times more energy efficient than Sierra.

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

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 complex simulation codes, uncertainty quantification, discrete event simulation, and the Unify file system.

“If applications don’t read and write files in an efficient manner,” system software developer Elsa Gonsiorowski warns, “entire systems can crash.”

Livermore Computing staff is enhancing the high-speed InfiniBand data network used in many of its high performance computing and file systems.

Spindle improves the library-loading performance of dynamically linked HPC applications by plugging into the system’s dynamic linker and intercepting its file operations.

Fast Global File Status (FGFS) is an open-source package that provides scalable mechanisms and programming interfaces to retrieve global information of a file.