Open-Source Cloud-Based Services on EPI Systems

Informations projet

OpenCUBE

N° de convention de subvention: 101092984

DOI

10.3030/101092984

Date de signature de la CE 2 Decembre 2022

Date de début 1 Janvier 2023

Date de fin 31 Decembre 2026

Financé au titre de

• Digital, Industry and Space

Coût total

€ 4 259 360,00

Contribution de l’UE

€ 4 259 360,00

Coordonné par

KUNGLIGA TEKNISKA HOEGSKOLAN
Sweden

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Data Management Plan (2)

D1.1: Data Management Plan

D1.1: Data Management Plan. (M6, DMP, PU) DMP Report for data and software developed in OpenCUBE.

D1.2: updated Data Management Plan

D1.2: updated Data Management Plan. (M18, DMP, PU) updated DMP Report for data and software developed in OpenCUBE.

Documents, reports (7)

D4.1-Initial system characterisation and middleware requirements, specification, and design

D4.1: Initial system characterisation and middleware requirements and design. (M12, R, PU). Initial design of the middleware for supporting fabric-attached memory, heterogeneous resources, and high-performance network, prototype implementation and system level characterization results

D3.1- OS and system software requirements, specification, and design

Deliverable 3.1 - OS and system software requirements, specification, and design. (M12, R, PU). Initial design document of the software stack including operating system, system services, and programming environment and tools, and report on the current landscape for the cloud software stack, prototype implementation and benchmarking results

D2.1-Pilot System Architecture Design and Prototype Implementation Report

D2.1 - Pilot System Architecture Design and Prototype Implementation Report. (M12, R, PU).Initial design of the pilot platform including compute node architecture, network architecture, and system architecture and prototype implementation and benchmarking results

D6.1-Plan for dissemination, collaboration, exploitation, and standardisation

D6.1 Plan for dissemination, collaboration, exploitation and standardisation. (M6, R, PU) This deliverable presents the initial dissemination plan including target audiences and activities, and exploitation plan.

D3.2- OS and system software prototype implementation

Deliverable 3.2 - Report on OS and system software prototype implementation. (M24, R, PU).Updated design of the software stack components and updated benchmarking results

D6.2-Report on dissemination, collaboration exploitation, and standardisation and updated plan

D6.2 Report on dissemination, collaboration, exploitation and standardisation / updated plan. (M18, R, PU) This deliverable presents OpenCUBE dissemination, training, exploitation activities, and interaction with and collaboration with EPI as well as the MPI Forum. This deliverable will include an update of the dissemination and exploitation plan.

D5.1-Definition of demonstrator applications and workflows

D5.1 - Definition of demonstrator applications and workflows. (M12, R, PU). Definition of application workflows and benchmark suites, including baseline expectations and performance.

Publications

Conference proceedings (7)

Accelerating drug discovery in autodock-gpu with tensor cores

Auteurs: Gabin Schieffer, Ivy Peng
Publié dans: European Conference on Parallel Processing, 2023
Éditeur: Springer
DOI: 10.1007/978-3-031-39698-4_41

A GPU-Accelerated Molecular Docking Workflow with Kubernetes and Apache Airflow

Auteurs: Daniel Medeiros, Gabin Schieffer, Jacob Wahlgren, Ivy Peng
Publié dans: International Conference on High Performance Computing, 2023
Éditeur: Springer
DOI: 10.1007/978-3-031-40843-4_15

Autonomy Loops for Monitoring, Operational Data Analytics, Feedback, and Response in HPC Operations

Auteurs: Boito, Francieli; Brandt, Jim; Cardellini, Valeria; Carns, Philip; Ciorba, Florina M.; Egan, Hilary; Eleliemy, Ahmed; Gentile, Ann; Gruber, Thomas; Hanson, Jeff; Haus, Utz-Uwe; Huck, Kevin; Ilsche, Thomas; Jakobsche, Thomas; Jones, Terry; Karlsson, Sven; Mueen, Abdullah; Ott, Michael; Patki, Tapasya; Peng, Ivy; Raghavan, Krishnan; Simms, Stephen; Shoga, Kathleen; Showerman, Michael; Tiwari, Devesh; Wilde, Torsten; Yamamoto, Keiji
Publié dans: https://inria.hal.science/hal-04382088, 2023
Éditeur: IEEE
DOI: 10.48550/arxiv.2401.16971

Kub: Enabling Elastic HPC Workloads on Containerized Environments

Auteurs: Daniel Medeiros, Gabin Schieffer, Jacob Wahlgren, Ivy Peng
Publié dans: 2023 IEEE 35th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2023
Éditeur: IEEE
DOI: 10.1109/SBAC-PAD59825.2023.00031

OpenCUBE: Building an Open Source Cloud Blueprint with EPI Systems

Auteurs: Ivy Peng, Martin Schultz, Utz-Uwe Haus, Craig Prunty, Pedro Marcuello, Emanuele Danovaro, Gabin Schieffer, Jacob Wahlgren, Daniel Medeiros, Philipp Friese, Stefano Markidis
Publié dans: Lecture Notes in Computer Science (Euro-Par 2023), 2023
Éditeur: Springer
DOI: 10.1007/978-3-031-48803-0_29

Survey of adaptive containerization architectures for HPC

Auteurs: Nina Mujkanovic, Juan J. Durillo, Nicolay Hammer, Tiziano Müller
Publié dans: SC-W '23: Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 2023
Éditeur: ACM
DOI: 10.1145/3624062.3624588

A Quantitative Approach for Adopting Disaggregated Memory in HPC Systems

Auteurs: Jacob Wahlgren; Gabin Schieffer; Maya Gokhale; Ivy Peng
Publié dans: International Conference for High Performance Computing, Networking, Storage and Analysis, 2023
Éditeur: ACM
DOI: 10.1145/3581784.3607108