The Linux Foundation announces its intention to create a “High-Performance Software Foundation”
This week, the Linux Foundation announced its intention to form the High Performance Software Foundation.
“Through a series of technology projects, the High Performance Software Foundation aims to build, enhance and advance a portable software stack for high performance computing by increasing adoption, lowering barriers to contribution, and supporting development efforts.”
As the use of high-performance computing becomes ubiquitous in scientific computing and digital engineering, and AI use cases multiply, more and more data centers are deploying GPUs and other computing accelerators. The High Performance Software Foundation intends to leverage investments made by the US Department of Energy’s Exascale Computing Project, the EuroHPC Joint Undertaking, and other international projects in accelerated HPC to exploit the performance of this diverse set of architectures. As an umbrella project within the Linux Foundation, HPSF intends to provide a neutral space for pivotal projects in the high-performance software ecosystem, and enable industry, academia and government agencies to collaborate together on the scientific software portfolio.
The HPC Foundation already benefits from strong support across the HPC landscape, including leading companies and organizations such as Amazon Web Services, Argonne National Laboratory, CEA, CIQ, Hewlett Packard Enterprise, Intel, Kitware, Lawrence Berkeley National Laboratory, and Lawrence Livermore. National Laboratory, Los Alamos National Laboratory, NVIDIA, Oak Ridge National Laboratory, Sandia National Laboratory, and the University of Oregon.
Its first open source technology projects include:
- Spack: High-performance computing package manager
- Kokkos: A portable, performance programming model for writing modern C++ applications in a hardware-agnostic way.
- AMReX: A high-performance portable software framework designed to accelerate the solution of partial differential equations on adaptively structured and optimized grids.
- WarpX: Portable in-cell particle code with advanced algorithms won the 2022 Gordon Bell Prize
- Trilinos: A set of reusable scientific software libraries, known in particular for linear, nonlinear and transient solutions, as well as optimization and uncertainty quantification.
- Apptainer: A container and image format system designed specifically for secure, high-performance computing.
- VTK-m: A toolkit of scientific visualization algorithms for accelerator architectures.
- HPCToolkit: Performance measurement and analysis tools for computers from laptops to the world’s largest GPU supercomputers.
- E4S: Extensive scientific software package
- Charliecloud: A high-performance, custom-built, lightweight and completely featureless container implementation.