This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| OpenHPC | |
|---|---|
| Name | OpenHPC |
| Developer | Intel Corporation; collaborative community |
| Released | 2015 |
| Programming language | C, Python, Shell |
| Operating system | CentOS, SUSE Linux Enterprise Server, Ubuntu |
| Platform | x86-64, ARM |
| License | GPL, BSD, various |
OpenHPC OpenHPC is a collaborative, community-driven collection of pre-built packages, tools, and best-practice recipes for building and managing high performance computing clusters. It provides a curated software stack for provisioning, resource management, monitoring, and scientific libraries to accelerate deployment for research institutions, national laboratories, and enterprise datacenters. The project focuses on interoperability with ecosystem projects and products from major vendors and consortia.
OpenHPC aggregates software from projects and organizations such as Intel Corporation, Hewlett Packard Enterprise, SUSE, The Linux Foundation, and research facilities like Argonne National Laboratory to form a coherent HPC stack. The distribution assembles components including provisioning systems, resource managers, parallel libraries, I/O frameworks, performance tools, and system utilities drawn from upstream projects such as Slurm Workload Manager, OpenMPI, MPICH, GCC, Python (programming language), Boost (C++ libraries), and HDF5. By packaging interoperable versions of Kubernetes, Ceph, and other infrastructure projects in conjunction with HPC-specific software, OpenHPC aims to bridge efforts by communities like European Organization for Nuclear Research and Oak Ridge National Laboratory with vendor platforms like Dell Technologies and Lenovo.
OpenHPC emerged in 2015 with initial leadership and contributions from Intel Corporation and collaborators across academia and industry, inspired by earlier consolidation efforts such as Rocky Linux and initiatives at Lawrence Livermore National Laboratory. Early roadmap discussions included representatives from National Energy Research Scientific Computing Center, Sandia National Laboratories, and university centers like University of California, Berkeley to ensure scientific reproducibility and portability. Subsequent development incorporated packages from projects like GROMACS, LAMMPS, and FFTW driven by user requirements from communities centered at facilities such as NERSC and CERN. Governance evolved to include open community processes similar to models used by Apache Software Foundation and The Linux Foundation.
The OpenHPC stack is modular, organized into collections for provisioning (system installation), resource management, and scientific middleware. Provisioning may employ tools related to PXE boot workflows and automation projects used by Red Hat, Inc. and SUSE; resource management predominantly integrates Slurm Workload Manager and alternatives like Grid Engine-derived systems. Communication and runtime libraries include OpenMPI and MPICH with underlying toolchains like GCC and Intel oneAPI. Performance and profiling integrate suites influenced by Perf and tools from Arm Limited ecosystems. Storage and I/O layers reference technologies from Lustre (file system), Ceph, and NetApp, Inc., while monitoring links to telemetry systems connected to Prometheus (software). Packaging and dependency management use formats established by RPM Package Manager and Debian (operating system). The architecture emphasizes reproducible builds, ABI stability, and integration testing to support scientific workflows developed at institutions like MIT and Stanford University.
OpenHPC provides binary packages and recipes for distributions such as CentOS, SUSE Linux Enterprise Server, and Ubuntu (operating system), and targets architectures including x86-64 and ARM (company)-based systems. Packaging policies follow conventions from RPM Package Manager and Debian (operating system) ecosystems to enable compatibility with hardware from vendors like Dell Technologies, Hewlett Packard Enterprise, and Lenovo. Build and CI systems draw on practices used in projects at GitHub, Inc. and GitLab B.V. to produce tested releases. Community-maintained binary repositories and modulefiles support environment modules consistent with standards from organizations such as ELIXIR and national computing centers.
Typical deployment workflows described by OpenHPC combine provisioning tools, configuration management, and orchestration. System administrators leverage technologies aligned with projects like Ansible (software), Kickstart (Linux), and Cobbler for rapid cluster rollouts. Scheduling and accounting integrate with Slurm Workload Manager configurations and ecosystem tools used at facilities such as Oak Ridge National Laboratory and Argonne National Laboratory. Container and virtualization strategies reference Singularity (software), Docker (software), and emerging approaches from Kubernetes to support reproducible research and hybrid cloud bursts with providers like Amazon Web Services and Microsoft Azure where applicable. Documentation and deployment guides echo best practices from academic computing centers such as Princeton University and Caltech.
OpenHPC operates with a collaborative community model that includes contributors from corporations, national laboratories, and universities, reflecting structures seen in Apache Software Foundation and The Linux Foundation projects. Contributors include software engineers from Intel Corporation, packaging maintainers from SUSE, and researchers from centers like National Renewable Energy Laboratory. Decision-making uses open mailing lists, issue trackers hosted on platforms similar to GitHub, Inc., and periodic community meetings akin to workshops held at SC Conference venues. Licensing mixes permissive and copyleft licenses consistent with policies from organizations like Free Software Foundation and community standards.
OpenHPC has been adopted for academic research clusters, national laboratory systems, and industry testbeds where reproducible scientific stacks are required. Workloads include molecular dynamics with GROMACS, computational fluid dynamics using OpenFOAM, machine learning experiments using TensorFlow, and materials modeling with LAMMPS. Deployments have been reported at institutions and consortia such as Lawrence Berkeley National Laboratory, Argonne National Laboratory, and university HPC centers across Europe and North America. Integration with vendor ecosystems from Dell Technologies and Hewlett Packard Enterprise and interoperability with cloud providers like Amazon Web Services supports hybrid research infrastructures.
Category:High performance computing software