Adaptive multi-tier intelligent data manager for Exascale

Project Information

ADMIRE

Grant agreement ID: 956748

DOI 10.3030/956748

Project closed

EC signature date 2 December 2020

Start date 1 April 2021

End date 30 June 2024

Funded under

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Total cost € 7 963 286,25

EU contribution € 3 981 643,13

Coordinated by

UNIVERSIDAD CARLOS III DE MADRID
Spain

Deliverables

Documents, reports (14)

Report on the intelligent controller design

Report with the design of the modules of the controller

Midterm report

A report describing all activities and results from the first half of project execution time

I/O Scheduler requirements and API

Report describing the IO Requirements API and the design of the IO Scheduler

Dissemination, communication, exploitation, and standardisation plan

A report describing the planned activities for dissemination communication exploitation and standardisation The plan will include a detailed description of objectives and KPIs

Project web site

The web site of the project containing public and private sections performance countersand external feedback forms

Design of the monitoring and profiling tool

Definition of the modules the functionality and the control points of the profiling and monitoring tools

Data Management Plan

A data management plan describing in detail the life cycle of the data collectedprocessed and generated by the project

Definition of requirements for ad-hoc storage systems

A report describing the requirements for theadhoc files system the limitations of existing file semantics and proposed modifications

Applications requirement definition

Deliverable including requirements analysis strategy and a second stage in the shape of the requirement repository

Definitions of the profiling and monitoring requirements

Report with the definition of requirements and API of monitoring infrastructures and applications IO profiling

Report on the intelligent controller requirements

Report with the definition of requirements and API of the control plane

Malleability requirements definition

Definition of the requirements and API for the malleability mechanisms to be provided in ADMIRE

Midterm report on dissemination, communication, exploitation, and standardisation

A report describing the activities and results of the execution of the activities planned and the level of fulfilment of KPIs

Updated Data Management Plan

An updated version of the data management plan

Demonstrators, pilots, prototypes (2)

Base mechanisms for malleability

Design and tested prototype of base mechanisms including documentation

Design of the ad-hoc storage systems

Design report and test suit to check semantical correctness of ad-hoc storage systems and application needs

Publications

Conference proceedings (23)

ElastiSim: A Batch-System Simulator for Malleable Workloads

Author(s): Taylan Özden, Tim Beringer, Arya Mazaheri, Hamid Mohammadi Fard, Felix Wolf
Published in: Proc. of the 51st International Conference on Parallel Processing (ICPP), Bordeaux, France, 2022
Publisher: ACM

Streamlining distributed Deep Learning I/O with ad hoc file systems.

Author(s): Frederic Schimmelpfennig, Marc-André Vef, Reza Salkhordeh, Alberto Miranda, Ramon Nou, and André Brinkmann
Published in: 23rd IEEE Cluster Conference, Issue Proceeding of the 23rd IEEE Cluster Conference, 2021, Page(s) 169-180
Publisher: IEEE
DOI: 10.1109/cluster48925.2021.00062

Data Management in EpiGraph COVID-19 Epidemic Simulator

Author(s): Miguel Guzmán-Merino, Christian Durán, Maria-Cristina Marinescu, Concepción Delgado-Sanz, Diana Gomez-Barroso, Jesus Carretero , David E. Singh
Published in: European Conference on Parallel Processing, 2022, Page(s) 267-278, ISBN 978-3-031-06156-1
Publisher: Springer, Cham
DOI: 10.1007/978-3-031-06156-1_22

Energy Consumption Studies of WRF Executions with the LIMITLESS Monitor

Author(s): Alberto Cascajo, David E. Singh, Jesús Carretero, Andres Bustos, Antonio Juan Rubio-Montero, Elena García-Bustamante, José A. Moriñigo, Rafael Mayo - García
Published in: LATIN AMERICA HIGH PERFORMANCE COMPUTING CONFERENCE - CARLA 2021, 2022, Page(s) 19–33, ISBN 978-3-031-04209-6
Publisher: Springer, Cham
DOI: 10.1007/978-3-031-04209-6_2

Sistema de almacenamiento Ad-Hoc para entornos HPC basado en el sistema de ficheros paralelo Expand

Author(s): Diego Camarmas-Alonso; Felix Garcia-Carballeira; Alejandro Calderon Mateos; Jesus Carretero Perez
Published in: XXXII Jornadas de Paralelismo (JP22), Issue 2, 2022
Publisher: ZENODO.org
DOI: 10.5281/zenodo.6862882

From Static to Malleable: Improving Flexibility and Compatibility in Burst Buffer File Systems

Author(s): Marc-André Vef, Alberto Miranda, Ramon Nou, André Brinkmann
Published in: International Workshop on Malleability Techniques Applications in High-Performance Computing (HPCMall), Issue 2, 2023, Page(s) 3 - 15
Publisher: Springer
DOI: 10.1007/978-3-031-40843-4_1

Xfast: Extreme File Attribute Stat Acceleration for Lustre

Author(s): Yingjin Qian, Wen Cheng, Lingfang Zeng, Xi Li, Marc-André Vef, Andreas Dilger, Siyao Lai, Shuichi Ihara, Yong Fan, André Brinkmann
Published in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), Issue 49, 2023, Page(s) 96:1-96:12
Publisher: ACM
DOI: 10.1145/3581784.3607080

Understanding the Impact of Synchronous, Asynchronous, and Hybrid In-Situ Techniques in Computational Fluid Dynamics Applications

Author(s): Yi Ju, Adalberto Perez, Stefano Markidis, Philipp Schlatter, Erwin Laure
Published in: 2022 IEEE 18th International Conference on e-Science (e-Science), Issue 2022 IEEE 18th International Conference on e-Science (e-Science), 2023, Page(s) 295-305
Publisher: IEEE
DOI: 10.1109/escience55777.2022.00043

Adaptive multi-tier intelligent data manager for Exascale

Author(s): Jesus Carretero; Javier Garcia-Blas; Marco Aldinucci; Jean Baptiste Besnard; Jean-Thomas Acquaviva; André Brinkmann; Marc-André Vef; Emmanuel Jeannot; Alberto Miranda; Ramon Nou; Morris Riedel; Massimo Torquati; Felix Wolf
Published in: CF 2023 - 20th ACM International Conference on Computing Frontiers, Issue 19, 2023
Publisher: ACM
DOI: 10.1145/3587135.3592174

Scheduling distributed I/O resources in HPC systems

Author(s): Bandet, Alexis; Boito, Francieli; Pallez, Guillaume
Published in: 30th International European Conference on Parallel and Distributed Computing 26 - 30 August 2024 Madrid, Spain 30th International European Conference on Parallel and Distributed Computing, Issue 1, 2024, Page(s) 16
Publisher: INRIA

Improving Generalization for Few-Shot Remote Sensing Classification with Meta-Learning

Author(s): Surbhi Sharma, Ribana Roscher, Morris Riedel, Shahbaz Memon and Gabriele Cavallaro
Published in: IEEE International Geoscience and Remote Sensing Symposium (GRSS), 2022, Page(s) 5061-5064
Publisher: IEEE
DOI: 10.1109/igarss46834.2022.9884699

The role of storage target allocation in applications' I/O performance with BeeGFS

Author(s): Boito, Francieli; Pallez, Guillaume; Teylo, Luan
Published in: CLUSTER 2022 - IEEE International Conference on Cluster Computing. https://clustercomp.org/2022/, 2022
Publisher: IEEE

The I/O Trace Initiative: Building a Collaborative I/O Archive to Advance HPC

Author(s): Nafiseh Moti, André Brinkmann, Marc-André Vef, Philippe Deniel, Jesús Carretero, Philip H. Carns, Jean-Thomas Acquaviva, Reza Salkhordeh
Published in: International Parallel Data Systems Workshop (PDSW), Issue 8, 2023, Page(s) 1216--1222
Publisher: ACM
DOI: 10.1145/3624062.3624192

Multi-objective Hybrid Autoscaling of Microservices in {Kubernetes} Clusters

Author(s): Angelina Horn, Hamid Mohammadi Fard, Felix Wolf
Published in: Proc. of the 28th Euro-Par Conference: Parallel Processing, Glasgow, UK, Issue 13440, 2022, Page(s) 233--250, ISBN 978-3-031-12597-3
Publisher: Springer
DOI: 10.1007/978-3-031-12597-3_15

MetaWBC: POSIX-Compliant Metadata Write-Back Caching for Distributed File Systems

Author(s): Yingjin Qian, Wen Cheng, Lingfang Zeng, Marc-André Vef, Oleg Drokin, Andreas Dilger, Shuichi Ihara, Wusheng Zhang, Yang Wang, André Brinkmann
Published in: The International Conference for High Performance Computing, Networking, Storage, and Analysis 2022 (SC22), 2022
Publisher: IEEE

The Italian Research on HPC Key Technologies across EuroHPC

Author(s): Aldinucci, Marco and Agosta, Giovanni and Andreini, Antonio and Ardagna, Claudio A. and Bartolini, Andrea and Cilardo, Alessandro and Cosenza, Biagio and Danelutto, Marco and Esposito, Roberto and Fornaciari, William and Giorgi, Roberto and Lengani, Davide and Montella, Raffaele and Olivieri, Mauro and Saponara, Sergio and Simoni, Daniele and Torquati, Massimo
Published in: Proceedings of the 18th ACM International Conference on Computing Frontiers, Issue CF '21, 2021, Page(s) 178–184, ISBN 9781450384049
Publisher: Association for Computing Machinery
DOI: 10.1145/3457388.3458508

Capturing Periodic I/O Using Frequency Techniques

Author(s): Tarraf, Ahmad; Bandet, Alexis; Zanon Boito, Francieli; Pallez, Guillaume; Wolf, Felix
Published in: Proceedings of the 38th IEEE International Parallel & Distributed Processing Symposium,, Issue 1, 2024, Page(s) 13
Publisher: IEEE

Capturing Periodic I/O Using Frequency Techniques

Author(s): Tarraf, Ahmad; Bandet, Alexis; Zanon Boito, Francieli; Pallez, Guillaume; Wolf, Felix
Published in: IPDPS 2024-38th IEEE International Parallel & Distributed Processing Symposium, Issue 38, 2024, Page(s) 1-13, ISBN 9798350337662
Publisher: IEEE

Protected Functions: User Space Privileged Function Calls

Author(s): Nafiseh Moti, Reza Salkhordeh, André Brinkmann
Published in: ARCS 2022: International Conference on Architecture of Computing Systems, 2022
Publisher: Springer

Pooling critical datasets with Federated Learning

Author(s): Y. Arfat, G. Mittone, I. Colonnelli, F. D'Ascenzo, R. Esposito and M. Aldinucci
Published in: 31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Issue 31, 2023, Page(s) pp. 329–337
Publisher: IEEE
DOI: 10.1109/pdp59025.2023.00057

Towards Smarter Schedulers: Molding Jobs into the Right Shape via Monitoring and Modeling

Author(s): Jean-Baptiste Besnard, Ahmad Tarraf, Clément Barthélemy, Alberto Cascajo, Emmanuel Jeannot, Sameer Shende & Felix Wolf
Published in: ISC High Performance 2023: High Performance Computing, 2023, Page(s) 68-81
Publisher: Springer, Cham
DOI: 10.1007/978-3-031-40843-4_6

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

Author(s): 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
Published in: 2023 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops),, Issue 43, 2023, Page(s) 37-43, ISBN 979-8-3503-7062-1
Publisher: IEEE
DOI: 10.1109/clusterworkshops61457.2023.00016

AIQUAM: Artificial Intelligence-based water QUAlity Model

Author(s): De Vita, Ciro Giuseppe; Mellone, Gennaro; Di Luccio, Diana; Kosta, Sokol; Ciaramella, Angelo; Montella, Raffaele
Published in: 2022 IEEE 18th International Conference on e-Science, Issue 1, 2022, ISBN 978-1-6654-6124-5
Publisher: IEEE
DOI: 10.1109/escience55777.2022.00058

Peer reviewed articles (11)

Malleability techniques applications in high-performance computing

Author(s): Jesus Carretero, Estela Suarez, Martin Schulz
Published in: The International Journal of High Performance Computing Applications, Issue 38, 2024, Page(s) 53-54, ISSN 1094-3420
Publisher: SAGE Publications
DOI: 10.1177/10943420241238032

Monitoring InfiniBand Networks to React Efficiently to Congestion

Author(s): Alberto Cascajo, Gabriel Gomez-Lopez, Jesus Escudero-Sahuquillo, Pedro Javier Garcia, David E. Singh, Francisco Alfaro-Cortés, Francisco J. Quiles, Jesus Carretero
Published in: IEEE Micro, Issue 43, 2024, Page(s) 120-130, ISSN 0272-1732
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/mm.2023.3241840

LIMITLESS - LIght-weight MonItoring Tool for LargE Scale Systems

Author(s): Alberto Cascajo, David E. Singh , Jesús Carretero
Published in: Microprocessors and Microsystems (MICPRO), Issue 01419331, 2022, ISSN 0141-9331
Publisher: Elsevier BV
DOI: 10.1016/j.micpro.2022.104586

Assessing population-sampling strategies for reducing the COVID-19 incidence.

Author(s): Miguel Guzmán-Merino; Christian Durán; Maria-Cristina Marinescu; Concepción Delgado-Sanz; Diana Gómez-Barroso; Jesus Carretero; David E. Singh
Published in: Computers in Biology and Medicine, Issue 00104825, 2021, ISSN 0010-4825
Publisher: Pergamon Press Ltd.
DOI: 10.1016/j.compbiomed.2021.104938

Detecting interference between applications and improving the scheduling using malleable application clones

Author(s): Alberto Cascajo, David E. Singh, Jesús Carretero
Published in: The International Journal of High Performance Computing Applications, Issue 38, 2024, Page(s) 108-133, ISSN 1094-3420
Publisher: SAGE Publications
DOI: 10.1177/10943420231220898

A novel approach for large‐scale environmental data partitioning on cloud and on‐premises storage for compute continuum applications

Author(s): Gennaro Mellone, Ciro Giuseppe De Vita, Dante D. Sánchez‐Gallegos, Genaro Sánchez‐Gallegos, Catherine A. Torres‐Charles, Javier Garcia‐Blas, Jesús Carretero Pérez, J. L. Gonzalez‐Compean, Giuliano Laccetti
Published in: Concurrency and Computation: Practice and Experience, Issue 35, 2023, ISSN 1532-0626
Publisher: John Wiley & Sons Inc.
DOI: 10.1002/cpe.7893

Malleability in Modern HPC Systems: Current Experiences, Challenges, and Future Opportunities

Author(s): Ahmad Tarraf, Martin Schreiber, Alberto Cascajo, Jean-Baptiste Besnard, Marc-André Vef, Dominik Huber, Sonja Happ, André Brinkmann, David E. Singh, Hans-Christian Hoppe, Alberto Miranda, Antonio J. Peña, Rui Machado, Marta Garcia-Gasulla, Martin Schulz, Paul Carpenter, Simon Pickartz, Tiberiu Rotaru, Sergio Iserte, Victor Lopez, Jorge Ejarque, Heena Sirwani, Jesus Carretero, Felix Wolf
Published in: IEEE Transactions on Parallel and Distributed Systems, Issue 35, 2024, Page(s) 1551-1564, ISSN 1045-9219
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpds.2024.3406764

Enhancing the power of two choices load balancing algorithm using round robin policy

Author(s): Garcia-Carballeira, F., Calderon, A. & Carretero, J.
Published in: Cluster Computing, Issue 24, 2021, Page(s) 611–624, ISSN 1386-7857
Publisher: Baltzer Science Publishers B.V.
DOI: 10.1007/s10586-020-03139-6

Detailed parallel social modeling for the analysis of COVID-19 spread

Author(s): Aymar Cublier Martínez, Jesús Carretero, David E. Singh
Published in: The Journal of Supercomputing, Issue 80, 2024, Page(s) 12408-12429, ISSN 0920-8542
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s11227-023-05881-1

A High-Performance Multispectral Adaptation GAN for Harmonizing Dense Time Series of Landsat-8 and Sentinel-2 Images

Author(s): Gabriele Cavallaro; Lorenzo Bruzzone; Rocco Sedona; Claudia Paris
Published in: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Issue 14, 2021, Page(s) 10134-10146, ISSN 2151-1535
Publisher: IEEE
DOI: 10.1109/jstars.2021.3115604

Distributed-memory FastFlow Building Blocks

Author(s): N. Tonci, M. Torquati, G. Mencagli, M. Danelutto
Published in: International Journal of Parallel Programming (IJPP), Issue 51, 2023, Page(s) 1–21, ISSN 0885-7458
Publisher: Kluwer Academic Publishers
DOI: 10.1007/s10766-022-00750-5

Other (14)

Understanding the Impact of Synchronous, Asynchronous, and Hybrid In-Situ Techniques in Computational Fluid Dynamics Applications

Author(s): Yi Ju, Adalberto Perez, Stefano Markidis, Philipp Schlatter, Erwin Laure
Published in: IEEE eScience 2022, 2022
Publisher: IEEE
DOI: 10.5281/zenodo.7152158

FTIO: Detecting I/O Periodicity Using Frequency Techniques

Author(s): Tarraf, Ahmad; Bandet, Alexis; Zanon Boito, Francieli; Pallez, Guillaume; Wolf, Felix
Published in: https://inria.hal.science/hal-04382142, Issue 39, 2023, Page(s) 12
Publisher: INRIA HAL
DOI: 10.48550/arxiv.2306.08601

Profile data of the ADMIRE project use case applications

Author(s): Jean Baptiste Bernard; Jesus Carretero; Raffaelle Montela; Adalberto Pérez; Laura Bellentani; Wojciech Stefaniak; Shahbaz Memon
Published in: Zenodo ADMIRE EUROHPC Project Community, 2022
Publisher: Zenodo
DOI: 10.5281/zenodo.7111282

Evaluation of Vaccination Strategies for the metropolitan area of Madrid

Author(s): David E. Singh; Carmen Olmedo Lucerón; Aurora Limia Sánchez; Miguel Guzman-Merino; Christian Duran; Concepción Delgado-Sanz; Diana Gomez-Barroso; Jesus Carretero; Maria-Cristina Marinescu
Published in: MedRxiv. The prepirnt server for health sciences, Issue 1, 2021, Page(s) 20
Publisher: BMJ, CSH, Yale
DOI: 10.1101/2021.11.29.21267009

The modernization of HPC applications for the cloud era. Fifth EAGE Workshop on High Performance Computing for Upstream. Heterogeneous HPC: Challenges, Current & Future Trends

Author(s): Marco Aldinucci
Published in: Fifth EAGE Workshop on High Performance Computing for Upstream. Heterogeneous HPC: Challenges, Current & Future Trends, Issue 2, 2021
Publisher: EAGE

What are ad-hoc storage systems and the GekkoFS burst buffer file system

Author(s): Marc-André Vef
Published in: ADMIRE Users Day, Issue 1, 2023
Publisher: -

Challenges and benefits of malleable ad-hoc file systems in HPC

Author(s): Marc-André Vef, Javier García Blas
Published in: Minisymposium on ADAPTIVE HPC I/O SYSTEMS @ EUROPAR 2023, Issue 1, 2023, Page(s) -
Publisher: -

IO-Sets: Simple and efficient approaches for I/O bandwidth management

Author(s): Francieli Boito, Guillaume Pallez, Luan Teylo, Nicolas Vidal
Published in: IPDPS 2022, 2023
Publisher: 2023

Doing better for jobs that failed: node stealing from a batch scheduler's perspective

Author(s): Du, Yishu; Marchal, Loris; Pallez, Guillaume; Robert, Yves
Published in: 2022, 2022
Publisher: INRIA

The I/O Trace Initiative: Building a Collaborative I/O Archive to Advance HPC

Author(s): Nafiseh Moti
Published in: IO-SEA: Storage I/O and Data Management for Exascale Architectures (HiPEAC 2024), Issue 1, 2024
Publisher: Hipeac

Implementation of an unbalanced I/O Bandwidth Management system in a Parallel File System

Author(s): Barthélemy, Clément; Zanon Boito, Francieli; Jeannot, Emmanuel; Pallez, Guillaume; Teylo, Luan
Published in: https://inria.hal.science/hal-04417412, Issue research report no 9537, 2024, Page(s) 15
Publisher: INRIA

European Initiative Projects Towards Exascale Computing

Author(s): Jesus Carretero, Tiago Dias, Ricardo Nobre, Mario Kovacs, Anotnio Peña, Didem Unat
Published in: Issue Europar 21, 2021
Publisher: Springer

Improving Congestion Control through Fine-Grain Monitoring of InfiniBand Networks

Author(s): Alberto Cascajo; Gabriel Gomez-Lopez; Jesus Escudero-Sahuquillo; Pedro Javier Garcia; David E. Singh; Francisco Alfaro-Cortés; Francisco J. Quiles; Jesus Carretero
Published in: HOTI 2022, 2022
Publisher: IEEE
DOI: 10.1109/hoti55740.2022.00020

The I/O Trace Initiative: Building a Collaborative I/O Archive to Advance HPC

Author(s): Nafiseh Moti
Published in: EuroHPC Projects Shaping Europe's HPC Landscape (HiPEAC 2024), Issue 1, 2024
Publisher: Hipeac

Thesis and dissertations (1)

New techniques for tracing and designing HPC storage systems

Author(s): Marc-André Vef
Published in: Johannes Gutenberg University Mainz / Ph.D. Thesis, 2023
Publisher: Johannes Gutenberg University Mainz
DOI: 10.25358/openscience-9322