REliable power and time-ConstraInts-aware Predictive management of heterogeneous Exascale systems

Informazioni relative al progetto

RECIPE

ID dell’accordo di sovvenzione: 801137

DOI 10.3030/801137

Progetto chiuso

Data della firma CE 18 Aprile 2018

Data di avvio 1 Maggio 2018

Data di completamento 31 Ottobre 2021

Finanziato da

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Costo totale € 3 318 327,93

Contributo UE € 3 285 300,00

Coordinato da

POLITECNICO DI MILANO
Italy

Risultati finali

Other (11)

RECIPE Global Resource Manager Prototype

The global resource manager developed in T2.2, at prototype stage.

RECIPE Local Resource Manager Prototype

The local resource manager developed in T2.1, at prototype stage.

Prototype Deployments update

Updated version of D42 to reflect the Jetson board addition

RECIPE Application Programming Interface

The application programming interface developed in T2.3, at prototype stage.

RECIPE Timing Analysis Tools

Tools developed in T32

Website & Dissemination materials

The project website, flyer, social media accounts and other dissemination materials. The accompanying report will be updated at M9, M18 and M36, while the website and social media will be continuously updated.

RECIPE Integrated Software Stack

RECIPE integrated software stack

RECIPE Thermal Simulation Tools

Tools developed in T33

Runtime Resource Management Policies

RTRM policies for each application based on the characterization done in T34 Outcome of T35

RECIPE Fault Prediction Tools

Tools developed in T31

Prototype Deployments

This deliverable will describe the prototype implemented for the project. All the components will be described and justified from a technical point of view. This deliverable will include all the activities performed in T.4.2.

Documents, reports (7)

State of the Art on Predictive Reliability Techniques

Report on the state of the art of predictive reliability techniques, outcome of T3.1 with contributions from T3.2 and T3.3.

Technology Assessment Report

This report provides an assessment of the RECIPE technologies on the target applications as outcome of T14 and T15

Lessons Learnt

Final report available to the public providing hindsight on project choices management and technical experience and future directions including observations from the advisory board

Report on Reconfigurable Accelerator Infrastructure Deployment

This report describes the adaptations and modifications performed to the original MANGO infrastructure cluster to enable its efficient use in the RECIPE project. This report will include all the activities performed in Task 4.1.

Fault-tolerance and QoS support

This report will provide all the provisions performed in the project related to fault-tolerance and QoS. The report will include activities of task 4.4.

Dissemination Plan 1

Initial dissemination plan, including specification of the data management policy.

Report on Predictive Reliability Techniques

Report on the activities of WP3 at M18, providing an overview of the work done in the first reporting period.

Open Research Data Pilot (2)

Dissemination Plan 2

Intermediate dissemination plan with identification of the open data sets generated by the project

Dissemination Plan 3

Final dissemination plan with final open data sets generated by the project

Pubblicazioni

Conference proceedings (17)

Back to the future - resource management in post-cloud solutions

Autori: Michele Zanella, Giuseppe Massari, Andrea Galimberti, William Fornaciari
Pubblicato in: Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications, 2018, Pagina/e 33-38, ISBN 9781450365987
Editore: ACM
DOI: 10.1145/3285017.3285028

A Game Theory Approach to Heterogeneous Resource Management: Work-in-Progress

Autori: Lara Premi; Federico Reghenzani; Giuseppe Massari; William Fornaciari
Pubblicato in: 2020 International Conference on Embedded Software (EMSOFT), 2020, ISBN 978-1-7281-9195-9
Editore: IEEE
DOI: 10.1109/emsoft51651.2020.9244046

Evaluating the Trade-offs in the Hardware Design of the LEDAcrypt Encryption Functions

Autori: Alessandro Barenghi, William Fornaciari, Andrea Galimberti, Gerardo Pelosi, Davide Zoni
Pubblicato in: 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2019, Pagina/e 739-742, ISBN 978-1-7281-0996-1
Editore: IEEE
DOI: 10.1109/icecs46596.2019.8964882

From a FPGA Prototyping Platform to a Computing Platform: The MANGO Experience

Autori: J. Flich, R. Tornero, D. Rodriguez, D. Russo, J.M. Martinez, C. Hernandez
Pubblicato in: 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Numero year, 2021, Pagina/e 7-12, ISBN 978-3-9819263-5-4
Editore: IEEE
DOI: 10.23919/date51398.2021.9474051

Predictive Resource Management in Energy-constrained Embedded Systems

Autori: Simone Crippa, Giuseppe Massari, Federico Reghenzani, Michele Zanella, William Fornaciari
Pubblicato in: 2020 23rd Euromicro Conference on Digital System Design (DSD), 2020, Pagina/e 159-166, ISBN 978-1-7281-9535-3
Editore: IEEE
DOI: 10.1109/dsd51259.2020.00035

Why statistical power matters for probabilistic real-time - work-in-progress

Autori: Federico Reghenzani, Luca Santinelli, William Fornaciari
Pubblicato in: Proceedings of the International Conference on Embedded Software Companion - EMSOFT '19, 2019, Pagina/e 1-2, ISBN 9781450369244
Editore: ACM Press
DOI: 10.1145/3349568.3351555

Analysis and countermeasures to side-channel attacks: a hardware design perspective

Autori: Davide Zoni
Pubblicato in: 2019 14th International Symposium on Reconfigurable Communication-centric Systems-on-Chip (ReCoSoC), 2019, Pagina/e 1-4, ISBN 978-1-7281-4770-3
Editore: IEEE
DOI: 10.1109/recosoc48741.2019.9034935

A Probabilistic Approach to Energy-Constrained Mixed-Criticality Systems

Autori: Federico Reghenzani, Giuseppe Massari, William Fornaciari
Pubblicato in: 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), 2019, Pagina/e 1-6, ISBN 978-1-7281-2954-9
Editore: IEEE
DOI: 10.1109/islped.2019.8824991

Run-Time Managed Mobile Application Execution

Autori: Michele Zanella, Giuseppe Massari, William Fornaciari
Pubblicato in: 2019 Fourth International Conference on Fog and Mobile Edge Computing (FMEC), 2019, Pagina/e 74-77, ISBN 978-1-7281-1796-6
Editore: IEEE
DOI: 10.1109/fmec.2019.8795323

Challenges in Deeply Heterogeneous High Performance Systems

Autori: Giovanni Agosta, Rafael Tornero Gavila, Marina Zapater Sancho, William Fornaciari, David Atienza, Ramon Canal, Alessandro Cilardo, Jose Flich, Carles Hernandez Luz, Michal Kulczewski, Giuseppe Massari
Pubblicato in: 2019 22nd Euromicro Conference on Digital System Design (DSD), 2019, Pagina/e 428-435, ISBN 978-1-7281-2862-7
Editore: IEEE
DOI: 10.1109/dsd.2019.00068

Prediction-based partitions evaluation algorithm for resource allocation

Autori: Pupykina, A.; Agosta, G.
Pubblicato in: Advances in Parallel Computing, Numero Volume 36: Parallel Computing: Technology Trends, 2020, Pagina/e 364 - 375
Editore: IOS Press
DOI: 10.3233/apc200061

Reliable power and time-constraints-aware predictive management of heterogeneous exascale systems

Autori: William Fornaciari, Carles Hernandez, Michal Kulchewski, Simone Libutti, José Maria Martínez, Giuseppe Massari, Ariel Oleksiak, Anna Pupykina, Federico Reghenzani, Rafael Tornero, Michele Zanella, Giovanni Agosta, Marina Zapater, Davide Zoni, David Atienza, Carlo Brandolese, Leila Cammoun, Luca Cremona, Alessandro Cilardo, Albert Farres, José Flich
Pubblicato in: Proceedings of the 18th International Conference on Embedded Computer Systems Architectures, Modeling, and Simulation - SAMOS '18, Numero year, 2018, Pagina/e 187-194, ISBN 9781-450364942
Editore: ACM Press
DOI: 10.1145/3229631.3239368

A constrained extremum-seeking control for CPU thermal management

Autori: Federico Reghenzani, Simone Formentin, Giuseppe Massari, William Fornaciari
Pubblicato in: Proceedings of the 15th ACM International Conference on Computing Frontiers - CF '18, Numero year, 2018, Pagina/e 320-325, ISBN 9781-450357616
Editore: ACM Press
DOI: 10.1145/3203217.3204464

DCFNoC - A Delayed Conflict-Free Time Division Multiplexing Network on Chip

Autori: Tomás Picornell, José Flich, Carles Hernández, José Duato
Pubblicato in: Proceedings of the 56th Annual Design Automation Conference 2019 on - DAC '19, 2019, Pagina/e 1-6, ISBN 9781-450367257
Editore: ACM Press
DOI: 10.1145/3316781.3317794

Dynamic Thermal Management with Proactive Fan Speed Control Through Reinforcement Learning

Autori: Arman Iranfar, Federico Terraneo, Gabor Csordas, Marina Zapater, William Fornaciari, David Atienza
Pubblicato in: 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020, Pagina/e 418-423, ISBN 978-3-9819263-4-7
Editore: IEEE
DOI: 10.23919/date48585.2020.9116510

BLADE - A BitLine Accelerator for Devices on the Edge

Autori: William Andrew Simon, Yasir Mahmood Qureshi, Alexandre Levisse, Marina Zapater, David Atienza
Pubblicato in: Proceedings of the 2019 on Great Lakes Symposium on VLSI, 2019, Pagina/e 207-212, ISBN 9781450362528
Editore: ACM
DOI: 10.1145/3299874.3317979

Probabilistic-WCET Reliability - On the experimental validation of EVT hypotheses

Autori: Federico Reghenzani, Giuseppe Massari, William Fornaciari, Andrea Galimberti
Pubblicato in: Proceedings of the International Conference on Omni-Layer Intelligent Systems, 2019, Pagina/e 229-234, ISBN 9781450366403
Editore: ACM
DOI: 10.1145/3312614.3312660

Peer reviewed articles (28)

Design of side-channel resistant power monitors

Autori: Davide Zoni, Luca Cremona, William Fornaciari
Pubblicato in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, Pagina/e 1-1, ISSN 0278-0070
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcad.2021.3088781

ECOGreen: Electricity Cost Optimization for Green Datacenters in Emerging Power Markets

Autori: Ali Pahlevan, Marina Zapater, Ayse K. Coskun, David Atienza
Pubblicato in: IEEE Transactions on Sustainable Computing, Numero 6/2, 2021, Pagina/e 289-305, ISSN 2377-3782
Editore: IEEE
DOI: 10.1109/tsusc.2020.2983571

Optimizing Energy in Non-Preemptive Mixed-Criticality Scheduling by Exploiting Probabilistic Information

Autori: Ashikahmed Bhuiyan, Federico Reghenzani, William Fornaciari, Zhishan Guo
Pubblicato in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Numero 39/11, 2020, Pagina/e 3906-3917, ISSN 0278-0070
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcad.2020.3012231

Dealing with Uncertainty in pWCET Estimations

Autori: Federico Reghenzani, Luca Santinelli, William Fornaciari
Pubblicato in: ACM Transactions on Embedded Computing Systems, Numero 19/5, 2020, Pagina/e 1-23, ISSN 1539-9087
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3396234

An FPU design template to optimize the accuracy-efficiency-area trade-off

Autori: Davide Zoni; Andrea Galimberti; William Fornaciari
Pubblicato in: Sustainable Computing: Informatics and Systems, Numero 29, A, 2021, ISSN 2210-5379
Editore: Elsevier USA
DOI: 10.1016/j.suscom.2020.100450

Efficient and Scalable FPGA-Oriented Design of QC-LDPC Bit-Flipping Decoders for Post-Quantum Cryptography

Autori: Davide Zoni, Andrea Galimberti, William Fornaciari
Pubblicato in: IEEE Access, Numero 8, 2020, Pagina/e 163419-163433, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2020.3020262

A Fresh View on the Microarchitectural Design of FPGA-Based RISC CPUs in the IoT Era

Autori: Giovanni Scotti, Davide Zoni
Pubblicato in: Journal of Low Power Electronics and Applications, Numero 9/1, 2019, Pagina/e 9, ISSN 2079-9268
Editore: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/jlpea9010009

Interpreting deep learning models for epileptic seizure detection on EEG signals

Autori: Valentin Gabeff, Tomas Teijeiro, Marina Zapater, Leila Cammoun, Sylvain Rheims, Philippe Ryvlin, David Atienza
Pubblicato in: Artificial Intelligence in Medicine, Numero 117, 2021, Pagina/e 102084, ISSN 0933-3657
Editore: Elsevier BV
DOI: 10.1016/j.artmed.2021.102084

The Real-Time Linux Kernel: A Survey on PREEMPT_RT

Autori: Reghenzani, Federico; Massari, Giuseppe; Fornaciari, William
Pubblicato in: ACM Computing Surveys, Numero 52, 1, 2019, Pagina/e 1-36, ISSN 0360-0300
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3297714

Flexible and Scalable FPGA-Oriented Design of Multipliers for Large Binary Polynomials

Autori: Davide Zoni, Andrea Galimberti, William Fornaciari
Pubblicato in: IEEE Access, Numero 8, 2020, Pagina/e 75809-75821, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2020.2989423

Evaluation of HPC Acceleration and Interconnect Technologies for High-Throughput Data Acquisition

Autori: Alessandro Cilardo
Pubblicato in: Sensors, 2021, ISSN 1424-8220
Editore: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/s21227759

Automatic identification and hardware implementation of a resource-constrained power model for embedded systems

Autori: Luca Cremona, William Fornaciari, Davide Zoni
Pubblicato in: Sustainable Computing: Informatics and Systems, Numero 29, 2021, Pagina/e 100467, ISSN 2210-5379
Editore: Elsevier USA
DOI: 10.1016/j.suscom.2020.100467

Statistical power estimation dataset for external validation GoF tests on EVT distribution

Autori: Federico Reghenzani, Giuseppe Massari, Luca Santinelli, William Fornaciari
Pubblicato in: Data in Brief, Numero 25, 2019, Pagina/e 104071, ISSN 2352-3409
Editore: Elsevier BV
DOI: 10.1016/j.dib.2019.104071

On the Use of Probabilistic Worst-Case Execution Time Estimation for Parallel Applications in High Performance Systems

Autori: Matteo Fusi, Fabio Mazzocchetti, Albert Farres, Leonidas Kosmidis, Ramon Canal, Francisco J. Cazorla, Jaume Abella
Pubblicato in: Mathematics, Numero 8/3, 2020, Pagina/e 314, ISSN 2227-7390
Editore: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/math8030314

Enforcing Predictability of Many-Cores With DCFNoC

Autori: Tomas Picornell, Jose Flich, Carles Hernandez, Jose Duato
Pubblicato in: IEEE Transactions on Computers, Numero 70/2, 2021, Pagina/e 270-283, ISSN 0018-9340
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tc.2020.2987797

A Flexible Framework for Exploring, Evaluating, and Comparing SHA-2 Designs

Autori: Raffaele Martino, Alessandro Cilardo
Pubblicato in: IEEE Access, Numero 7, 2019, Pagina/e 72443-72456, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2019.2920089

3D-ICE 3.0: efficient nonlinear MPSoC thermal simulation with pluggable heat sink models

Autori: Federico Terraneo, Alberto Leva, William Fornaciari, Marina Zapater, David Atienza
Pubblicato in: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2020, Pagina/e 1-1, ISSN 0278-0070
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcad.2021.3074613

Predictive Reliability and Fault Management in Exascale Systems

Autori: Ramon Canal, Carles Hernandez, Rafa Tornero, Alessandro Cilardo, Giuseppe Massari, Federico Reghenzani, William Fornaciari, Marina Zapater, David Atienza, Ariel Oleksiak, Wojciech PiĄtek, Jaume Abella
Pubblicato in: ACM Computing Surveys, Numero 53/5, 2020, Pagina/e 1-32, ISSN 0360-0300
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3403956

The Misconception of Exponential Tail Upper-Bounding in Probabilistic Real-Time

Autori: Federico Reghenzani, Giuseppe Massari, William Fornaciari
Pubblicato in: IEEE Embedded Systems Letters, 2019, Pagina/e 1-1, ISSN 1943-0663
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/les.2018.2889114

Gem5-X

Autori: Yasir Mahmood Qureshi, William Andrew Simon, Marina Zapater, Katzalin Olcoz, David Atienza
Pubblicato in: ACM Transactions on Architecture and Code Optimization, Numero 18/4, 2021, Pagina/e 1-27, ISSN 1544-3566
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3461662

Resource Management for Power-Constrained HEVC Transcoding Using Reinforcement Learning

Autori: Luis Costero, Arman Iranfar, Marina Zapater, Francisco D. Igual, Katzalin Olcoz, David Atienza
Pubblicato in: IEEE Transactions on Parallel and Distributed Systems, Numero 31/12, 2020, Pagina/e 2834-2850, ISSN 1045-9219
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpds.2020.3004735

All-Digital Energy-Constrained Controller for General-Purpose Accelerators and CPUs

Autori: Davide Zoni, Luca Cremona, William Fornaciari
Pubblicato in: IEEE Embedded Systems Letters, Numero 12/1, 2020, Pagina/e 17-20, ISSN 1943-0663
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/les.2019.2914136

Scramble Suit: A Profile Differentiation Countermeasure to Prevent Template Attacks

Autori: Alessandro Barenghi; William Fornaciari; Gerardo Pelosi; Davide Zoni
Pubblicato in: IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, Numero 39/9, 2020, Pagina/e 1778-1791, ISSN 0278-0070
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcad.2019.2926389

All-Digital Control-Theoretic Scheme to Optimize Energy Budget and Allocation in Multi-Cores

Autori: Davide Zoni, Luca Cremona, William Fornaciari
Pubblicato in: IEEE Transactions on Computers, Numero 69/5, 2020, Pagina/e 706-721, ISSN 0018-9340
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tc.2019.2963859

Timing Predictability in High-Performance Computing With Probabilistic Real-Time

Autori: Federico Reghenzani, Giuseppe Massari, William Fornaciari
Pubblicato in: IEEE Access, Numero 8, 2020, Pagina/e 208566-208582, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2020.3038559

The RECIPE approach to challenges in deeply heterogeneous high performance systems

Autori: Giovanni Agosta, William Fornaciari, David Atienza, Ramon Canal, Alessandro Cilardo, José Flich Cardo, Carles Hernandez Luz, Michal Kulczewski, Giuseppe Massari, Rafael Tornero Gavilá, Marina Zapater
Pubblicato in: Microprocessors and Microsystems, Numero 77, 2020, Pagina/e 103185, ISSN 0141-9331
Editore: Elsevier BV
DOI: 10.1016/j.micpro.2020.103185

Probabilistic-WCET reliability: Statistical testing of EVT hypotheses

Autori: Federico Reghenzani, Giuseppe Massari, William Fornaciari
Pubblicato in: Microprocessors and Microsystems, Numero 77, 2020, Pagina/e 103135, ISSN 0141-9331
Editore: Elsevier BV
DOI: 10.1016/j.micpro.2020.103135

Survey of Memory Management Techniques for HPC and Cloud Computing

Autori: Anna Pupykina, Giovanni Agosta
Pubblicato in: IEEE Access, Numero 7, 2019, Pagina/e 167351-167373, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2019.2954169

Other (1)

Towards Resilient EU HPC Systems: A Blueprint

Autori: Radojkovic, Petar; Marazakis, Manolis; Carpenter, Paul; Jeyapaul, Reiley; Gizopoulos, Dimitris; Schulz, Martin; Armejach, Adria; Ayguade, Eduard,; Bodin, François; Canal, Ramon; Cappello, Franck; Chaix, Fabien; Colin De Verdiere, Guillaume; Derradji, Said; Di Carlo, Stefano; Engelmann, Christian; Laguna, Ignacio; Moreto, Miquel; Mutlu, Onur; Papadopoulos, Lazaros; Perks, Olly; Ploumidis, Manolis;
Pubblicato in: Research Report - European HPC resilience initiative, Numero 4, 2020
Editore: HAL

Book chapters (3)

An Open-Hardware Platform for MPSoC Thermal Modeling

Autori: Federico Terraneo, Alberto Leva, William Fornaciari
Pubblicato in: Embedded Computer Systems: Architectures, Modeling, and Simulation - 19th International Conference, SAMOS 2019, Samos, Greece, July 7–11, 2019, Proceedings, Numero 11733, 2019, Pagina/e 184-196, ISBN 978-3-030-27561-7
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-27562-4_13

VGM-Bench: FPU Benchmark Suite for Computer Vision, Computer Graphics and Machine Learning Applications

Autori: Luca Cremona, William Fornaciari, Andrea Galimberti, Andrea Romanoni, Davide Zoni
Pubblicato in: Embedded Computer Systems: Architectures, Modeling, and Simulation - 20th International Conference, SAMOS 2020, Samos, Greece, July 5–9, 2020, Proceedings, Numero 12471, 2020, Pagina/e 323-335, ISBN 978-3-030-60938-2
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-60939-9_23

Predictive Resource Management for Next-Generation High-Performance Computing Heterogeneous Platforms

Autori: Giuseppe Massari, Anna Pupykina, Giovanni Agosta, William Fornaciari
Pubblicato in: Embedded Computer Systems: Architectures, Modeling, and Simulation - 19th International Conference, SAMOS 2019, Samos, Greece, July 7–11, 2019, Proceedings, Numero 11733, 2019, Pagina/e 470-483, ISBN 978-3-030-27561-7
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-27562-4_34