HPSF aims to build, promote, and promote a portable core software stack for high-performance computing.
The Linux Foundation recently announced , through a blog post, its intention to form a new subgroup dedicated to promoting high-performance computing (HPC), increasing adoption, reducing barriers to contribution, and supporting development efforts.
The HPSF will build, promote, and develop a portable software stack for high-performance computing applications with the help of HPC investments from international projects , such as those of the EuroHPC Joint Venture and the U.S. Department of Energy. Major technology companies will also be involved.
Specifically, the HPSF will provide developers with continuous integration resources , turnkey software stacks, architecture support, and performance regression testing and benchmarking.
The Linux Foundation explained that HPC has truly taken off due to the increasing adoption of scientific computing and AI . By providing a neutral space for HPC projects, the organization hopes that industry, academia, and governments can collaborate on the scientific software stack.
“The High Performance Software Foundation (HPSF) is a great step in promoting collaboration and innovation across Performance Intensive Computing and HPC. For this reason, it is with great enthusiasm that I announce, on behalf of the Apptainer project and community, our intention to join HPSF and directly support a broader community with performance-intensive computing needs.”
– Gregory Kurtzer, CEO of CIQ and founder of open source projects such as CentOS, Rocky Linux, Warewulf, and Apptainer/Singularity.
At launch, 10 open-source projects will be part of the HPSF, including :
- Spack: the HPC package manager
- Kokkos: a portable, high-performance programming model for writing modern C++ applications in a hardware-independent manner.
- AMReX: a high-performance portable software framework designed to accelerate the solution of partial differential equations on adaptively refined block-structured meshes.
- WarpX: a portable, high-performance, in-house particle code with advanced algorithms that won the 2022 Gordon Bell Prize.
- Trilinos: a collection of reusable scientific software libraries, known in particular for their linear, nonlinear and transient solvers, as well as optimization and uncertainty quantification.
- Apptainer: an image format and container system designed specifically for secure, high-performance computing.
- VTK-m: toolbox of scientific visualization algorithms for accelerator architectures.
- HPCToolkit: performance measurement and analysis tools for computers ranging from laptops to the largest GPU-accelerated supercomputers.
- E4S: the scientific software stack at extreme scale
- Charliecloud: Implementation of a lightweight container, suitable for intensive computing and free of privileges.
In addition, it is mentioned that the HPSF aims to make life easier for high-performance software developers through a number of specific initiatives, including:
- Continuous integration resources adapted to HPC projects.
- Continuously built turnkey software stacks
- Architecture support
- performance regression testing and benchmarking.
Acting as an umbrella project under the Linux Foundation, the HPSF will provide a neutral space for critical projects in the high-performance software ecosystem, enabling industry, academia, and government entities to collaborate together on the scientific software stack.
HPSF already benefits from strong support, as it is backed by a broad spectrum of HPC companies, including Amazon Web Services, Argonne National Laboratory, CEA, CIQ, Hewlett Packard Enterprise, Intel, Kitware, Lawrence Berkeley National Laboratory, Lawrence Livermore National Laboratory, Los Alamos National Laboratory, NVIDIA, Oak Ridge National Laboratory, Sandia National Laboratory, and the University of Oregon.
Finally, it is mentioned that, based on support organizations and community members, HPSF will establish a technical advisory committee (TAC) that will manage several working groups to address various HPC issues and will follow a governance model based on the Cloud Native Computing Foundation.
Finally, if you are interested in learning more about this , you can find the details at the following link.