OpenCUBE
OpenCUBE
Open-Source Cloud-Based Services on EPI Systems
Full project details (EU Research results portal): https://cordis.europa.eu/project/id/101092984
Project description:
This project proposes to design OpenCUBE, a full-stack solution of a validated European Cloud computing blueprint to be deployed on European hardware infrastructure. OpenCUBE will develop a custom cloud installation with the guarantee that an entirely European solution like SiPearl processors and Semidynamics RISC-V accelerators can be deployed reproducibly. OpenCUBE will be built on industry-standard open APIs using Open Source components and will provide a unified software stack that captures the different best practices and open source tooling on the operating system, middleware, and system management level. It will thus provide a solid basis for the European cloud services, research, and commercial deployments envisioned to be core for federated digital services via Gaia-X. To remain competitive for the European Green Deal, OpenCUBE is designed to make energy awareness a core feature at all levels of the stack, exploiting the advanced features of the SiPearl Rhea processor family at the hardware level and exposing the necessary API at the site level, up to and including interfaces to the electricity grid. This project will leverage representative workloads like those of ECMWF characteristics for production and Digital Twin workflows as drivers for the design and deployment of the cluster infrastructure. We will collaborate closely with the projects developing the virtual environments and the open hardware interfaces for current and future European processor and coprocessor technology.
EuroVoc IDs: /natural sciences/computer and information sciences/software
EU Programme: Horizon Europe
EU Project
Project publications:
| EU Project | Has Title | Has Category | Has Type | Has Year | Has DOI |
|---|---|---|---|---|---|
| OpenCUBE | Survey of adaptive containerization architectures for HPC | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1145/3624062.3624588 |
| OpenCUBE | Accelerating drug discovery in autodock-gpu with tensor cores | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1007/978-3-031-39698-4 41 |
| OpenCUBE | A GPU-Accelerated Molecular Docking Workflow with Kubernetes and Apache Airflow | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1007/978-3-031-40843-4 15 |
| OpenCUBE | OpenCUBE: Building an Open Source Cloud Blueprint with EPI Systems | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1007/978-3-031-48803-0 29 |
| OpenCUBE | Autonomy Loops for Monitoring, Operational Data Analytics, Feedback, and Response in HPC Operations | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.48550/arxiv.2401.16971 |
| OpenCUBE | A Quantitative Approach for Adopting Disaggregated Memory in HPC Systems | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1145/3581784.3607108 |
| OpenCUBE | Kub: Enabling Elastic HPC Workloads on Containerized Environments | Hardware Architecture and High-Performance Computing (HPC) | Conference proceedings | 2023 | https://doi.org/10.1109/SBAC-PAD59825.2023.00031 |