Topic: HPC Systems and Software

In this video from the 2019 Stanford HPC Conference, LLNL's Rob Neely presents "Sierra – Science Unleashed." Sierra is NNSA’s first large-scale production heterogeneous system.

News Item

Profile of LLNL's Lori Diachin, who has over 25 years experience in applied mathematics research including mesh quality improvement, mesh component software, numerical methods, and parallel computing.

News Item

Umpire is a resource management library that allows the discovery, provision, and management of memory on next-generation architectures.

Project

Computer scientist Greg Becker contributes to HPC research and development projects for LLNL’s Livermore Computing division.

People Highlight

Highlights include debris an shrapnel modeling at NIF, scalable algorithms for complex engineering systems, magnetic fusion simulation, and data placement optimization on GPUs.

News Item

Users need tools that address the bottlenecks of exascale machines, work seamlessly with the programming models on the target machines, scale to the full size of the machine, provide the necessary automatic analysis capabilities, and be flexible and modular enough to overcome the complexities and changing demands of exascale architectures.

Project

This open-source file system framework supports hierarchical HPC storage systems by utilizing node-local burst buffers.

Project

Highlights include CASC director Jeff Hittinger's vision for the center as well as recent work with PruneJuice DataRaceBench, Caliper, and SUNDIALS.

News Item

As supercomputing power increases, the cost of communicating data both on- and off-node has become a critical factor affecting the overall performance of a parallel application. Livermore's interconnection networks projects improve the communication and overall performance of parallel applications using interconnect topology-aware task mapping.

Project

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

Project

The PRUNERS Toolset offers four novel debugging and testing tools to assist programmers with detecting, remediating, and preventing errors in a coordinated manner.

Project

LLNL's Advanced Simulation Computing program formed the Advanced Architecture and Portability Specialists team to help LLNL code teams identify and implement optimal porting strategies.

Project

BLT software supports HPC software development with built-in CMake macros for external libraries, code health checks, and unit testing.

Project

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

News Item

A new software model helps move million-line codes to various hardware architectures by automating data movement in unique ways.

Project

Sphinx, an integrated parallel microbenchmark suite, consists of a harness for running performance tests and extensive tests of MPI, Pthreads and OpenMP.

Project

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

People Highlight

Highlights include the HYPRE library, recent data science efforts, the IDEALS project, and the latest on the Exascale Computing Project.

News Item

Apollo, an auto-tuning extension of RAJA, improves performance portability in adaptive mesh refinement, multi-physics, and hydrodynamics codes via machine learning classifiers.

Project

Large Linux data centers require flexible system management. At Livermore Computing, we are committed to supporting our Linux ecosystem at the high end of commodity computing.

Project

The sheer size of data poses significant problems in all stages of the visualization pipeline, from offline pre-processing of simulation data, to interactive queries, to real-time rendering. Moreover, visualization data is often unstructured in nature, which further complicates its management and representation. The goal of this project is to develop techniques for reducing bandwidth requirements for large unstructured data, both explicitly, by making use of data compression, and implicitly, by optimizing the layout of the data for better locality and cache reuse.

Project

Livermore builds an open-source community around its award-winning HPC package manager.

Project

Researchers have been developing a standardized and optimized operating system and software for deployment across a series of Linux clusters to enable high performance computing at a reduced cost.

Project