Opendata, web and dolomites

OPRECOMP SIGNED

Open transPREcision COMPuting

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 OPRECOMP project word cloud

Explore the words cloud of the OPRECOMP project. It provides you a very rough idea of what is the project "OPRECOMP" about.

exponential    guaranteed    full    industrial    complete    oprecomp    orders    era    deep    theoretical    shift    efficient    prove    constant    intermediate    foundations    numerical    first    conservative    mainstay    approximate    megawatt    centers    internet    big    improvement    mathematical    elementary    simulations    computing    idea    domains    energy    efficiency    respect    huge    ultra    tools    milliwatt    will    data    replacing    precise    holds    circuits    paradigms    think    computation    learning    calculations    transprecision    tiny    practical    demonstrators    lifted    analytics    relax    software    framework    sub    operation    mandatory    twilight    moore    reliability    fueled    things    flexible    time    theory    boost    communicated    nodes    algorithms    overcome    iot    picojoule    quality    ideas    demolishing    scenarios    hpc    spanning    nine    processed    improvements    freedom    view    physical    bounds    law    stored    accuracy    abstraction    obtainable    power    realizations    precision    error    magnitude    wall    mission   

Project "OPRECOMP" data sheet

The following table provides information about the project.

Coordinator
IBM RESEARCH GMBH 

Organization address
address: SAEUMERSTRASSE 4
city: RUESCHLIKON
postcode: 8803
website: www.zurich.ibm.com

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Switzerland [CH]
 Project website http://oprecomp.eu/
 Total cost 5˙990˙510 €
 EC max contribution 5˙990˙510 € (100%)
 Programme 1. H2020-EU.1.2.2. (FET Proactive)
 Code Call FETPROACT-2016
 Funding Scheme RIA
 Starting year 2017
 Duration (year-month-day) from 2017-01-01   to  2020-12-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    IBM RESEARCH GMBH CH (RUESCHLIKON) coordinator 1˙183˙000.00
2    EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZUERICH CH (ZUERICH) participant 758˙800.00
3    THE QUEEN'S UNIVERSITY OF BELFAST UK (BELFAST) participant 705˙625.00
4    COMMISSARIAT A L ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES FR (PARIS 15) participant 548˙860.00
5    ALMA MATER STUDIORUM - UNIVERSITA DI BOLOGNA IT (BOLOGNA) participant 547˙500.00
6    TECHNISCHE UNIVERSITAET KAISERSLAUTERN DE (KAISERSLAUTERN) participant 530˙975.00
7    UNIVERSITAT JAUME I DE CASTELLON ES (CASTELLON DE LA PLANA) participant 491˙250.00
8    GREENWAVES TECHNOLOGIES FR (VILLARD-BONNOT) participant 473˙000.00
9    CINECA CONSORZIO INTERUNIVERSITARIO IT (CASALECCHIO DI RENO BO) participant 390˙000.00
10    UNIVERSITA DEGLI STUDI DI PERUGIA IT (PERUGIA) participant 361˙500.00

Map

 Project objective

Guaranteed numerical precision of each elementary step in a complex computation has been the mainstay of traditional computing systems for many years. This era, fueled by Moore's law and the constant exponential improvement in computing efficiency, is at its twilight: from tiny nodes of the Internet-of-Things, to large HPC computing centers, sub-picoJoule/operation energy efficiency is essential for practical realizations. To overcome the “power wall”, a shift from traditional computing paradigms is now mandatory.

OPRECOMP aims at demolishing the ultra-conservative “precise” computing abstraction and replacing it with a more flexible and efficient one, namely transprecision computing. OPRECOMP will investigate the theoretical and practical understanding of the energy efficiency boost obtainable when accuracy requirements on data being processed, stored and communicated can be lifted for intermediate calculations. While approximate computing approaches have been used before, in OPRECOMP for the first time ever, a complete framework for transprecision computing, covering devices, circuits, software tools, and algorithms, along with the mathematical theory and physical foundations of the ideas will be developed that not only will provide error bounds with respect to full precision results, but also will enable major energy efficiency improvements even when there is no freedom to relax end-to-end application quality-of-results.

The mission of OPRECOMP is to demonstrate using physical demonstrators that this idea holds in a huge range of application scenarios in the domains of IoT, Big Data Analytics, Deep Learning, and HPC simulations: from the sub-milliWatt to the MegaWatt range, spanning nine orders of magnitude. In view of industrial exploitation, we will prove the quality and reliability and demonstrate that transprecision computing is the way to think about future systems.

 Deliverables

List of deliverables.
Initial version of transprecision software stack Other 2019-12-04 14:11:58
Numerical analysis of algorithms Documents, reports 2019-12-04 14:11:59
Evaluation results for heterogeneous memories Documents, reports 2019-12-04 14:11:58
Error-energy relations: fundamental limits Documents, reports 2019-12-04 14:11:59
Initial applications progress report Documents, reports 2019-12-04 14:11:58
Transprecision software stack design Documents, reports 2019-12-04 14:11:58
Initial version of the kW pilot-platform Demonstrators, pilots, prototypes 2019-12-04 14:11:59
Intermediate dissemination and exploitation plan report Documents, reports 2019-12-04 14:11:59
ReRAM and heterogeneous 3D-memory architecture models Documents, reports 2019-12-04 14:11:59
Error-energy relations: technological limits Documents, reports 2019-12-04 14:11:59
First summer school Websites, patent fillings, videos etc. 2019-12-04 14:11:59
Initial version of the mW pilot-platform Demonstrators, pilots, prototypes 2019-12-04 14:11:59
Intermediate applications progress report Documents, reports 2019-12-04 14:11:59
Initial report of big data applications using transprecision computing Documents, reports 2019-12-04 14:11:59
Second summer school Websites, patent fillings, videos etc. 2019-12-04 14:11:59
Intermediate communication activity and plan report Documents, reports 2019-12-04 14:11:59
Initial report of embedded deep learning using transprecision computing Documents, reports 2019-12-04 14:11:59
Simulation results for NEMS memory devices Documents, reports 2019-12-04 14:11:58
Evaluation of approximate computing techniques Documents, reports 2019-12-04 14:11:58
Prototype version of the algorithms Documents, reports 2019-12-04 14:11:58
Intermediate version of transprecision software stack Other 2019-12-04 14:11:58
Evaluation of transprecision Documents, reports 2019-12-04 14:11:59
Final version of the algorithms Documents, reports 2019-12-04 14:11:58
Numerical analysis of transprecision Documents, reports 2019-12-04 14:11:57
Initial report on micro-benchmarks Documents, reports 2019-12-04 14:11:57
Initial dissemination and exploitation plan report Documents, reports 2019-12-04 14:11:57
Web-site and project logo Websites, patent fillings, videos etc. 2019-12-04 14:11:57
Definition of the hardware abstraction layer Documents, reports 2019-12-04 14:11:57
Processing unit for controllable precision Documents, reports 2019-12-04 14:11:57
Initial communication activity and plan report Documents, reports 2019-12-04 14:11:57
Fundamental physics limits Documents, reports 2019-12-04 14:11:57
Initial data management plan Open Research Data Pilot 2019-12-04 14:11:57
Error resilience Documents, reports 2019-12-04 14:11:57
Quality metrics Documents, reports 2019-12-04 14:11:57
Set up of intranet, data repository, and project management tool Websites, patent fillings, videos etc. 2019-12-04 14:11:57

Take a look to the deliverables list in detail:  detailed list of OPRECOMP deliverables.

 Publications

year authors and title journal last update
List of publications.
2019 Hartwig Anzt, Jack Dongarra, Goran Flegar, Nicholas J. Higham, Enrique S. Quintana-Ortí
Adaptive precision in block-Jacobi preconditioning for iterative sparse linear system solvers
published pages: e4460, ISSN: 1532-0626, DOI: 10.1002/cpe.4460
Concurrency and Computation: Practice and Experience 31/6 2019-12-04
2018 Di Mauro, Alfio; Rossi, Davide; Pullini, Antonio; Flatresse, Philippe; Benini, Luca; id_orcid0000-0001-8068-3806
Independent Body-Biasing of P-N Transistors in an 28nm UTBB FD-SOI ULP Near-Threshold Multi-Core Cluster
published pages: , ISSN: , DOI: 10.3929/ethz-b-000314386
2018 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S) 1 2019-12-04
2019 Antonio Pullini, Davide Rossi, Igor Loi, Giuseppe Tagliavini, Luca Benini
Mr.Wolf: An Energy-Precision Scalable Parallel Ultra Low Power SoC for IoT Edge Processing
published pages: 1970-1981, ISSN: 0018-9200, DOI: 10.1109/jssc.2019.2912307
IEEE Journal of Solid-State Circuits 54/7 2019-12-04
2019 Ioannis Tsiokanos, Lev Mukhanov, Dimitrios S. Nikolopoulos, Georgios Karakonstantis
Significance-Driven Data Truncation for Preventing Timing Failures
published pages: 25-36, ISSN: 1530-4388, DOI: 10.1109/tdmr.2019.2898949
IEEE Transactions on Device and Materials Reliability 19/1 2019-12-04
2019 Andrés E. Tomás, Rafael Rodríguez-Sánchez, Sandra Catalán, Rocío Carratalá-Sáez, Enrique S. Quintana-Ortí
Dynamic look-ahead in the reduction to band form for the singular value decomposition
published pages: 22-31, ISSN: 0167-8191, DOI: 10.1016/j.parco.2018.11.001
Parallel Computing 81 2019-12-04
2019 Benatti, Simone; Montagna, Fabio; Kartsch, Victor; Rahimi, Abbas; id_orcid0000-0003-3141-4970; Rossi, Davide; Benini, Luca; id_orcid0000-0001-8068-3806
Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform using Hyperdimensional Computing
published pages: 516-528, ISSN: 1940-9990, DOI: 10.3929/ethz-b-000339838
IEEE Transactions on Biomedical Circuits and Systems (TBioCAS), 13 (3) 1 2019-12-04
2018 JunKyu Lee, Hans Vandierendonck, Mahwish Arif, Gregory D. Peterson, Dimitrios S. Nikolopoulos
Energy-Efficient Iterative Refinement Using Dynamic Precision
published pages: 722-735, ISSN: 2156-3357, DOI: 10.1109/jetcas.2018.2850665
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 8/4 2019-12-04
2019 Hartwig Anzt, Goran Flegar, Thomas Grützmacher, Enrique S Quintana-Ortí
Toward a modular precision ecosystem for high-performance computing
published pages: 109434201984654, ISSN: 1094-3420, DOI: 10.1177/1094342019846547
The International Journal of High Performance Computing Applications 2019-12-04
2019 Dionysios Diamantopoulos, Christoph Hagleitner
HelmGemm: Managing GPUs and FPGAs for transprecision GEMM workloads in containerized environments
published pages: , ISSN: , DOI:
2019-12-04
2018 Schiavone, Pasquale D.; Rossi, Davide; Pullini, Antonio; Di Mauro, Alfio; Conti, Francesco; id_orcid0000-0002-7924-933X; Benini, Luca
Quentin: an Ultra-Low-Power PULPissimo SoC in 22nm FDX
published pages: , ISSN: , DOI: 10.3929/ethz-b-000314427
2018 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S) 1 2019-12-04
2019 Hartwig Anzt, Jack Dongarra, Goran Flegar, Enrique S. Quintana-Ortí
Variable-size batched Gauss–Jordan elimination for block-Jacobi preconditioning on graphics processors
published pages: 131-146, ISSN: 0167-8191, DOI: 10.1016/j.parco.2017.12.006
Parallel Computing 81 2019-12-04
2018 D. Chiuchiù, M. López-Suárez, I. Neri, M. C. Diamantini, L. Gammaitoni
Cost of remembering a bit of information
published pages: Phys. Rev. A 97,, ISSN: 2469-9926, DOI: 10.1103/PhysRevA.97.052108
Physical Review A 97/5 2019-12-04
2018 Giuseppe Tagliavini, Andrea Marongiu, Luca Benini
FlexFloat: A Software Library for Transprecision Computing
published pages: 1-1, ISSN: 0278-0070, DOI: 10.1109/TCAD.2018.2883902
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems December 2018 2019-12-04
2018 Paolo Meloni, Alessandro Capotondi, Gianfranco Deriu, Michele Brian, Francesco Conti, Davide Rossi, Luigi Raffo, Luca Benini
NEURA ghe
published pages: 1-24, ISSN: 1936-7406, DOI: 10.1145/3284357
ACM Transactions on Reconfigurable Technology and Systems 11/3 2019-12-04
2017 Goran Flegar, Enrique S. Quintana-Ortí
Balanced CSR Sparse Matrix-Vector Product on Graphics Processors
published pages: 697-709, ISSN: , DOI: 10.1007/978-3-319-64203-1_50
Euro-Par 2017: Parallel Processing: 23rd International Conference on Parallel and Distributed Computing, Santiago de Compostela, Spain, August 28 – September 1, 2017, Proceedings 2019-12-04
2017 Simone Benatti, Bojan Milosevic, Elisabetta Farella, Emanuele Gruppioni, Luca Benini
A Prosthetic Hand Body Area Controller Based on Efficient Pattern Recognition Control Strategies
published pages: 869, ISSN: 1424-8220, DOI: 10.3390/s17040869
Sensors 17/4 2019-12-04
2018 Giovanni Rovere, Schekeb Fateh, Luca Benini
\"A 2.2- $mu$ W Cognitive Always-On Wake-Up Circuit for Event-Driven Duty-Cycling of IoT Sensor Nodes\"
published pages: 543-554, ISSN: 2156-3357, DOI: 10.1109/JETCAS.2018.2828505
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 8/3 2019-12-04
2017 Fabio Montagna, Simone Benatti, Davide Rossi
Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection
published pages: 16, ISSN: 2079-9268, DOI: 10.3390/jlpea7020016
Journal of Low Power Electronics and Applications 7/2 2019-12-04
2017 Francesco Conti, Robert Schilling, Pasquale Davide Schiavone, Antonio Pullini, Davide Rossi, Frank Kagan Gurkaynak, Michael Muehlberghuber, Michael Gautschi, Igor Loi, Germain Haugou, Stefan Mangard, Luca Benini
An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics
published pages: 2481-2494, ISSN: 1549-8328, DOI: 10.1109/TCSI.2017.2698019
IEEE Transactions on Circuits and Systems I: Regular Papers 64/9 2019-12-04
2019 Abbas Rahimi, Pentti Kanerva, Luca Benini, Jan M. Rabaey
Efficient Biosignal Processing Using Hyperdimensional Computing: Network Templates for Combined Learning and Classification of ExG Signals
published pages: 123-143, ISSN: 0018-9219, DOI: 10.1109/JPROC.2018.2871163
Proceedings of the IEEE 107/1 2019-12-04
2019 Fabian Schuiki, Michael Schaffner, Frank K. Gurkaynak, Luca Benini
A Scalable Near-Memory Architecture for Training Deep Neural Networks on Large In-Memory Datasets
published pages: 484-497, ISSN: 0018-9340, DOI: 10.1109/tc.2018.2876312
IEEE Transactions on Computers 68/4 2019-12-04
2019 Rafael Rodríguez-Sánchez, Sandra Catalán, José R. Herrero, Enrique S. Quintana-Ortí, Andrés E. Tomás
Look-ahead in the two-sided reduction to compact band forms for symmetric eigenvalue problems and the SVD
published pages: 635-660, ISSN: 1017-1398, DOI: 10.1007/s11075-018-0500-8
Numerical Algorithms 80/2 2019-12-04
2017 Maryam Payami, Erfan Azarkhish, Igor Loi, Luca Benini
A Hybrid Instruction Prefetching Mechanism for Ultra Low-Power Multicore Clusters
published pages: 125-128, ISSN: 1943-0663, DOI: 10.1109/LES.2017.2707978
IEEE Embedded Systems Letters 9/4 2019-12-04
2018 Erfan Azarkhish, Davide Rossi, Igor Loi, Luca Benini
Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes
published pages: 420-434, ISSN: 1045-9219, DOI: 10.1109/TPDS.2017.2752706
IEEE Transactions on Parallel and Distributed Systems 29/2 2019-12-04
2018 Satyajit Das, Kevin J. M. Martin, Davide Rossi, Philippe Coussy, Luca Benini
An Energy-Efficient Integrated Programmable Array Accelerator and Compilation flow for Near-Sensor Ultra-low Power Processing
published pages: 1-1, ISSN: 0278-0070, DOI: 10.1109/TCAD.2018.2834397
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2019-12-04
2017 Fabio Montagna, Marco Buiatti, Simone Benatti, Davide Rossi, Elisabetta Farella, Luca Benini
A machine learning approach for automated wide-range frequency tagging analysis in embedded neuromonitoring systems
published pages: 96-107, ISSN: 1046-2023, DOI: 10.1016/j.ymeth.2017.06.019
Methods 129 2019-12-04
2018 Igor Loi, Alessandro Capotondi, Davide Rossi, Andrea Marongiu, Luca Benini
The Quest for Energy-Efficient I$ Design in Ultra-Low-Power Clustered Many-Cores
published pages: 99-112, ISSN: 2332-7766, DOI: 10.1109/TMSCS.2017.2769046
IEEE Transactions on Multi-Scale Computing Systems 4/2 2019-12-04
2018 Victor Javier Kartsch, Simone Benatti, Pasquale Davide Schiavone, Davide Rossi, Luca Benini
A sensor fusion approach for drowsiness detection in wearable ultra-low-power systems
published pages: 66-76, ISSN: 1566-2535, DOI: 10.1016/j.inffus.2017.11.005
Information Fusion 43 2019-12-04

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "OPRECOMP" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "OPRECOMP" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.2.2.)

HPCWE (2019)

High performance computing for wind energy

Read More  

EPiGRAM-HS (2018)

Exascale Programming Models for Heterogeneous Systems

Read More  

NEUROTECH (2018)

Neuromorphic Technology

Read More