A distributed data-mining software platform for extreme data across the compute continuum

Informations projet

EXTRACT

N° de convention de subvention: 101093110

DOI

10.3030/101093110

Date de signature de la CE 16 Novembre 2022

Date de début 1 Janvier 2023

Date de fin 31 Decembre 2025

Financé au titre de

• Digital, Industry and Space

Coût total

€ 4 997 875,00

Contribution de l’UE

€ 4 997 875,00

Coordonné par

BARCELONA SUPERCOMPUTING CENTER CENTRO NACIONAL DE SUPERCOMPUTACION
Spain

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

Documents, reports (9)

Use-case requirements

Report including the specification of the use-case requirements.

Data infrastructure and data mining framework requirements

Report including the specification of the Data infrastructure and Data mining framework.

First release of the EXTRACT data infrastructure and data mining framework

First release of software components of the data infrastructure and framework. Complete specification and APIs.

Project management plan and quality guidelines

Report of main project procedures (contractual framework, governance, monitoring, internal communication, etc.) and standards and quality procedures.

First release of the data-driven orchestration and monitoring

Prototype of orchestra-tor and monitoring with limited functionality and a report describing it.

Compute Continuum Specification and first integration plan

Requirements and early design of the EXTRACT compute continuum abstraction layer and the initial integration plan.

Dissemination, exploitation and community building report

Description of the activities performed in the first period, and the list of foreseen training materials and actions, based on Phase 1 requirement.

Updated dissemination, exploitation and community building, and first sustainability report

Description of the activities performed and update on the initial plan covering the Phase 2, establishing new objectives and actions if needed.

Data-driven orchestration requirements

Description of: (1) workflow and continuum in-formation for orchestration, (2) orchestration and monitoring architecture and (3) software components selection.

Other (2)

First release of the EXTRACT use-cases

First released of the PER and TASKA use-cases developed with the EXTRACT technology at Phase 2, and a report describing them.

First release of the Compute Continuum and final integration plan

D4.2 defines the first architecture and deployment of the EXTRACT compute continuum abstraction layer and the EXTRACT platform.

Data Management Plan (1)

Data Management Plan

Report data management from internal/external point of view, including a table specifying data exploitation, shared for verification and reuse. Updates will be provided if need.

Publications

Conference proceedings (4)

Glider: Serverless Ephemeral Stateful Near-Data Computation

Auteurs: Daniel Barcelona-Pons, Pedro García-López, and Bernard Metzler.
Publié dans: Middleware '23: Proceedings of the 24th International Middleware Conference, 2023, ISBN 979-8-4007-0177-1
Éditeur: Association for Computing Machinery
DOI: 10.1145/3590140.3629119

Scaling a Variant Calling Genomics Pipeline with FaaS

Auteurs: Aitor Arjona, Arnau Gabriel-Atienza, Sara Lanuza-Orna, Xavier Roca-Canals, Ayman Bourramouss, Tyler K. Chafin, Lucio Marcello, Paolo Ribeca, and Pedro García-López
Publié dans: 9th International Workshop on Serverless Computing, 2023, ISBN 979-8-4007-0455-0
Éditeur: ACM
DOI: 10.1145/3631295.3631403

Multi-party Computation for Privacy and Security in Machine Learning: a Practical Review

Auteurs: Alessandro Bellini, Emanuele Bellini, Massimo Bertini, Doaa Almhaithawi, Stefano Cuomo
Publié dans: 2023 IEEE International Conference on Cyber Security and Resilience (CSR), 2023, ISBN 979-8-3503-1170-9
Éditeur: IEEE
DOI: 10.1109/CSR57506.2023.10224826

Is Performance of Object Storage Predictable for Serverless I/O Workloads? A Comparative Study

Auteurs: G. Eizaguirre and M. Sanchez-Artigas
Publié dans: Cloud-Edge Continuum Workshop 2023 (IEEE 31st International Conference on Network Protocols, 2023, ISBN 979-8-3503-0322-3
Éditeur: IEEE Computer Society
DOI: 10.1109/ICNP59255.2023.10355617

Peer reviewed articles (2)

Corrigendum to “MLLess: Achieving Cost Efficiency in Serverless Machine Learning Training

Auteurs: Pablo Gimeno Sarroca, Marc Sánchez-Artigas
Publié dans: Journal of Parallel and Distributed Computing, Numéro 183, 2024, ISSN 0743-7315
Éditeur: Elsevier Inc.
DOI: 10.48550/arXiv.2206.05786

Semantic Segmentation of Solar Radio Spikes at Low Frequencies

Auteurs: Pearse C Murphy, Stéphane Aicardi, Baptiste Cecconi, Carine Briand, Thibault Peccoux
Publié dans: The Open Journal of Astrophysics, Numéro 7, 2024, ISSN 0000-0000
Éditeur: Maynooth Academic Publishing
DOI: 10.48550/ARXIV.2403.08546