TRANSPARENT APPLICATION DEPLOYMENT IN A SECURE, ACCELERATED AND COGNITIVE CLOUD CONTINUUM

Informazioni relative al progetto

SERRANO

ID dell’accordo di sovvenzione: 101017168

DOI

10.3030/101017168

Progetto chiuso

Data della firma CE 8 Dicembre 2020

Data di avvio 1 Gennaio 2021

Data di completamento 31 Dicembre 2023

Finanziato da

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

Costo totale

€ 4 343 180,00

Contributo UE

€ 4 343 180,00

Coordinato da

EREVNITIKO PANEPISTIMIAKO INSTITOUTO SYSTIMATON EPIKOINONION KAI YPOLOGISTON
Greece

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (23)

Final version of SERRANO architecture

It will include the final and detailed version of the overall SERRANO architecture all the required building blocks their interactions and specifications for the required vertical and horizontal interfaces

Abstraction models and intelligent service orchestration

It will include the developed abstraction models for resources services and applications the application profiling mechanisms and the AIenhanced Service Orchestrator along with the AIML techniques for transparent deployment of applications

Report on standardization activities

It will include the initial report on standardization and collaboration activities

Final report on standardization activities

It will include the final report on standardization and collaboration activities.

Business, end user and technical evaluation

It will include the evaluation outcomes after the initial integration and testing for the SERRANO use cases, from the technical, business and end user perspective.

SERRANO use cases, platform requirements and KPIs analysis

It will include the initial report regarding the SERRANO platform requirements and use cases definitions and descriptions It will also include the appropriate KPIs that will be used for evaluating the innovations developed in the project

Framework for seamlessly integration of heterogeneous workload-aware performance improvement

This deliverable will include a holistic framework for rapid prototyping of HWSW kernels based on enhanced versions of PlugChip VVUQ and REMAP flows including abstraction for serverless workloads

SERRANO architecture

It will include the initial version of the overall SERRANO architecture its key building blocks and their interactions along with specifications for the required vertical and horizontal interfaces

The SERRANO integrated platform

It will include the first release of the integrated platform and will report the outcomes of the initial diverse tests unit integration subsystem end to end

Final version of SERRANO use cases, platform requirements and KPIs analysis

It will include the final report regarding the SERRANO platform requirements use cases descriptions and KPIs for evaluating the innovations developed in the project

Algorithmic framework, performance and power models

It will include the developed multiobjective networkaware resource allocation and service orchestration optimization algorithms the AIMLdriven service assurance selfconfiguration and reoptimization mechanisms It will also include the energy and resource aware flow mapping framework

Final Release of the SERRANO Cloud and Edge Acceleration Platforms and Tools

This deliverable constitutes the final release of the platforms, frameworks and tools developed in WP4 following the user, technical and business feedback received during the first round in WP7.

Final version of business, end user and technical evaluation

It will include the final evaluation outcomes for the SERRANO use cases, from the technical, business and end user perspective.

Final release of SERRANO Secure Infrastructure Layer

It will be the final version of the WP3 technological outcomes following the user, technical and business feedback received during the first round in WP7.

Final publishable activity report

It will include the final publishable report.

Resource orchestration, telemetry and lightweight virtualization mechanisms

It will include the developed AIMLassisted cloud and network telemetry framework and the hierarchical resource orchestration mechanisms It will also include the lightweight virtualization and hypervisor mechanisms

State of the art analysis report

It will include the state of the art analysis performed in Task 21 regarding the different SERRANO technologies

HW/SW IPs for workload acceleration in disaggregated DCs

This deliverable will provide the repository with HWSW codesigned kernels that realize the SERRANO manyaccelerator platform

Secure Cloud Storage System

It will include a scalable secure storage system enabling massive storage deletion by cryptokey handling and mechanisms for distributed operation over multiple clouds and multiple edge storage nodes

Intelligent service and resource orchestration mechanisms

It will include the manual and prototype of the final tools and mechanisms developed in WP5.

Trust and isolated execution on untrusted physical tenders

It will include the development for the efficient lightweight hypervisor for isolated workload execution

Performance Maximization under Maximum Affordable Error for the HW and SW IPs

This deliverable will include the developments that improve the energy and delay metrics of HW SW IP kernels by applying transprecision and approximate computing techniques

Accelerated encrypted storage architecture

It will include an architecture definition of both the software and the hardware acceleration simulator implementation of the software and hardware solution and a hardware prototype that demonstrates the performance of the solution

Websites, patent fillings, videos etc. (3)

Intermediate project dissemination material and updates

It will include the dissemination material including website lay summary social media accounts posters white papers

Final project dissemination material and updates

It will include the dissemination material, including website, lay summary, social media accounts, posters, white papers.

Project dissemination material and updates

It will include the dissemination material including website lay summary social media accounts posters white papers

Demonstrators, pilots, prototypes (1)

Final version of SERRANO integrated platform

It will provide the final release of integrated platform and will report the outcomes of the final diverse tests.

Pubblicazioni

Conference proceedings (20)

Enabling An Isolated And Energy-Aware Deployment of Computationally Intensive Kernels on Multi-Tenant Environments

Autori: A. Kokkinis, A. Nanos, K. Siozios
Pubblicato in: International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS 2023), 2023, ISBN 978-3-031-46077-7
Editore: Springer
DOI: 10.1007/978-3-031-46077-7_27

Optimizing Savitzky-Golay Filter on GPU and FPGA Accelerators for Financial Applications

Autori: I. Oroutzoglou, A. Kokkinis, A.Ferikoglou, D. Danopoulos, D. Masouros and K. Siozios
Pubblicato in: IEEE International Conference on Modern Circuits and Systems Technologies (MOCAST), 2022
Editore: IEEE

Cycle Detection and Clustering for Cyber Physical Systems

Autori: G. Iuhasz, S. Panica, A. Duma
Pubblicato in: International Conference on Advanced Information Networking and Applications, 2023
Editore: Springer
DOI: 10.1007/978-3-031-28694-0_10

A Quality of Experience Illustrator User Interface for Cloud Provider Recommendations

Autori: P. Kokkinos, D. Margaris and D. Spiliotopoulos
Pubblicato in: International Conference on Human-Computer Interaction, 2022
Editore: Springer
DOI: 10.1007/978-3-031-06417-3_42

Dynamic Heap Management in High-Level Synthesis for Many-Accelerator Architectures

Autori: A. Kokkinis, D. Diamantopoulos, K. Siozios
Pubblicato in: IEEE 32nd International Conference on Field-Programmable Logic and Applications (FPL 2022), 2022
Editore: IEEE
DOI: 10.1109/fpl57034.2022.00051

The SERRANO platform: Stepping towards seamless application development & deployment in the heterogeneous edge-cloud continuum

Autori: A. Ferikoglou, A. Kokkinis, D. Danopoulos, I. Oroutzoglou, A. Nanos, S. Karanastasis, M. Sipos, J. Ghotbi, J.J. Vegas-Olmos, D. Masouros, K. Siozios
Pubblicato in: Design, Automation & Test in Europe Conference & Exhibition (DATE 2023), 2023, ISBN 979-8-3503-9624-9
Editore: IEEE
DOI: 10.23919/date56975.2023.10137039

Towards the Realization of Converged Cloud, Edge and Networking Infrastructures in Smart MegaCities

Autori: P. Kokkinos
Pubblicato in: 27th IEEE Symposium on Computers and Communications (ISCC 2022), 2022
Editore: IEEE

Securitization of cloud, edge and IoT communications through hardware accelerations/offloadings

Autori: B. Pismenny, J.J. Olmos, Y. Zack, L. Liss, A. Dömeke, C. Stan, C. Garcia, I. Monroy, P. Kokkinos, A. Kretsis and M. Varvarigos
Pubblicato in: Workshop on Intelligent operations, security, and acceleration for edge computing (MeditCom), 2021
Editore: IEEE
DOI: 10.1109/meditcom49071.2021.9647500

Machine Learning Network Tomography with partial topology knowledge and dynamic routing

Autori: I. Sartzetakis and E. Varvarigos
Pubblicato in: IEEE Global Communications Conference, 2022, ISBN 978-1-6654-3540-6
Editore: IEEE
DOI: 10.1109/globecom48099.2022.10001622

Secured Distributed Storage Resource Allocation on Cloud-Edge Infrastructures

Autori: K. Kontodimas, P. Soumplis, P. Kokkinos, E. Varvarigos
Pubblicato in: IEEE 10th International Conference on Cloud Networking (CloudNet), 2021
Editore: IEEE
DOI: 10.1109/cloudnet53349.2021.9657156

HW/SW Acceleration of Multiple Workloads Within the SERRANO’s Computing Continuum

Autori: A. Kokkinis, A. Ferikoglou, I. Oroutzoglou, D. Danopoulos, D. Masouros, and K. Siozios
Pubblicato in: International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS 2022), 2022
Editore: Springer
DOI: 10.1007/978-3-031-15074-6_25

Dynamic Edge/Cloud Resource Allocation for Distributed Computation under Semi-Static Demands

Autori: I. Sartzetakis, P. Pantazopoulos, K. V. Katsaros, V. Sourlas, E. Varvarigos
Pubblicato in: IEEE 2024 IEEE International Conference on Communications (ICC 2024), 2024
Editore: IEEE

TUFA: A TOSCA extension for the specification of accelerator-aware applications in the Cloud Continuum

Autori: Florin-Adrian Spataru, Gabriel Iuhasz, Silviu Panica
Pubblicato in: IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), 2022
Editore: IEEE
DOI: 10.1109/compsac54236.2022.00185

Towards Efficient HW Acceleration in Edge-Cloud Infrastructures: The SERRANO Approach

Autori: A. Ferikoglou, I. Oroutzoglou, A. Kokkinis, D. Danopoulos, D. Masouros, E. Chondrogiannis, A. Fernandez Gomez, A. Kretsis, P. Kokkinos, E. Varvarigos and K. Siozios
Pubblicato in: International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS), 2022
Editore: Springer
DOI: 10.1007/978-3-031-04580-6_24

SERRANO: Transparent Application Deployment in a Secure, Accelerated and Cognitive Cloud Continuum

Autori: A. Kretsis, P. Kokkinos, P. Soumplis, J.J. Olmos, M. Feher, M. Sipos, D. Lucani, D. Khabi, D. Masouros, K. Siozios, P. Bourgos, S. Tsekeridou, F. Zyulkyarov, E. Karanastasis, E. Chrondrogiannis, V. Andronikou, A. Gomez, S. Panica, G. Luhasz, A. Nanos, C. Chalios and E, Varvarigos
Pubblicato in: Workshop on Intelligent operations, security, and acceleration for edge computing (MeditCom), 2021
Editore: IEEE
DOI: 10.1109/meditcom49071.2021.9647689

Leveraging HW approximation for exploiting performance-energy trade-offs within edge-cloud computing continuum

Autori: A. Kokkinis, A. Ferikoglou, D. Danopoulos, D. Masouros and K. Siozios
Pubblicato in: Workshop on Virtualization in High-Performance Cloud Computing (VHPC), 2021
Editore: Springer
DOI: 10.1007/978-3-030-90539-2_27

Hardware-Accelerated FaaS for the Edge-Cloud Continuum

Autori: A.Nanos, A. Kretsis, C. Mainas, G. Ntouskos, A. Ferikoglou, D. Danopoulos, A. Kokkinis, D. Masouros, K. Siozios, P. Soumplis, P. Kokkinos, J.J. Vegas Olmos, and E. Varvarigos
Pubblicato in: Cloud-Edge Continuum Worksho, 2023
Editore: IEEE
DOI: 10.1109/icnp59255.2023.10355594

Intent-based AI-enhanced Service Orchestration for application deployment and execution in the Cloud Continuum

Autori: E. Chondrogiannis, E. Karanastasis, V. Andronikou, A. Spătaru, A. Nanos, A. Kretsis, P.Kokkinos
Pubblicato in: 10th European Conference On Service-Oriented And Cloud Computing (ESOCC 2023), 2023, ISBN 978-3-031-46235-1
Editore: Springer
DOI: 10.1007/978-3-031-46235-1_17

Resource Allocation for Distributed Machine Learning at the (Edge-Cloud) Continuum

Autori: I. Sartzetakis, P. Soumplis, P. Pantazopoulos, K. Katsaros, V. Sourlas, E. Varvarigos
Pubblicato in: IEEE International Conference on Communications (ICC), 2022
Editore: IEEE
DOI: 10.5281/zenodo.6861466

Hardware-Aware Automated Neural Minimization for Printed Multilayer Perceptrons

Autori: A. Kokkinis, G. Zervakis, K. Siozios, M. B. Tahoori and J. Henkel
Pubblicato in: Design, Automation & Test in Europe Conference & Exhibition (DATE 2023), 2023
Editore: -

Peer reviewed articles (9)

Network Tomography with Partial Topology Knowledge and Dynamic Routing

Autori: I. Sartzetakis, E. Varvarigos
Pubblicato in: Journal of Network and Systems Management, 2023
Editore: springer
DOI: 10.1007/s10922-023-09763-y

Variability-Aware Approximate Circuit Synthesis via Genetic Optimization

Autori: K. Balaskas, F. Klemme, G. Zervakis, K. Siozios, H. Amrouch, J. Henkel
Pubblicato in: IEEE Transactions on Circuits and Systems I: Regular Papers, 2022
Editore: IEEE
DOI: 10.1109/tcsi.2022.3183858

Anomaly detection for fault detection in wireless community networks using machine learning

Autori: L. Cerdà-Alabern, G. Iuhasz, G, Gemmi
Pubblicato in: Computer Communications, 2023, ISSN 0000-0000
Editore: Elsevier
DOI: 10.1016/j.comcom.2023.02.019

Edge/Cloud Infinite-time Horizon Resource Allocation for Distributed Machine Learning and General Tasks

Autori: I. Sartzetakis, P. Soumplis, P. Pantazopoulos, K. V. Katsaros, V. Sourlas and E. Varvarigos
Pubblicato in: IEEE Transactions on Network and Service Management, 2023, ISSN 0000-0000
Editore: IEEE

Secure Distributed Storage Orchestration on Heterogeneous Cloud-Edge Infrastructures

Autori: K. Kontodimas, P. Soumplis, A. Kretsis, P. Kokkinos, M. Fehér, D. Lucani, E. Varvarigos
Pubblicato in: IEEE Transactions on Cloud Computing, 2023, ISSN 2168-7161
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/tcc.2023.3287653

AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch

Autori: D. Danopoulos, G. Zervakis, K. Siozios, D. Soudris and J. Henkel
Pubblicato in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, ISSN 0278-0070
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcad.2022.3212645

Automated Design Approximation to Overcome Circuit Aging

Autori: K. Balaskas, G. Zervakis, H. Amrouch, J. Henkel and K. Siozios
Pubblicato in: IEEE Transactions on Circuits and Systems I: Regular Papers, 2021, ISSN 1558-0806
Editore: IEEE
DOI: 10.1109/tcsi.2021.3106149

Dynamic Optimization of On-Chip Memories for HLS Targeting Many-Accelerator Platforms

Autori: A. Kokkinis, D. Diamantopoulos and K. Siozios
Pubblicato in: IEEE Computer Architecture Letters, 2022, ISSN 1556-6056
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lca.2022.3190048

Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization

Autori: K. Balaskas, A. Karatzas, C. Sad, K. Siozios, I. Anagnostopoulos, G. Zervakis, J. Henkel
Pubblicato in: IEEE Transactions on Emerging Topics in Computing, 2023, ISSN 0000-0000
Editore: IEEE