Journal Publications

  • libVersioningCompiler: An easy-to-use library for dynamic generation and invocation of multiple code versions.
    Stefano Cherubin, Giovanni Agosta
    SoftwareX, 2018, Elsevier
    DOI: 10.1016/j.softx.2018.03.006
  • Quantifying the Impact of Variability and Heterogeneity on the Energy Efficiency for a Next-Generation Ultra-Green Supercomputer.
    Francesco Fraternali, Andrea Bartolini, Carlo Cavazzoni, Luca Benini
    IEEE Transactions on Parallel and Distributed Systems, 2018, IEEE
    DOI: 10.1109/TPDS.2017.2766151
  • mARGOt: a Dynamic Autotuning Framework for Self-aware Approximate Computing.
    Davide Gadioli, Emanuele Vitali, Gianluca Palermo, Cristina Silvano
    IEEE Transactions on Computers, 2018, IEEE
    DOI: 10.1109/TC.2018.2883597
  • Feasibility Analysis Of Using the MAUI Scheduler for Job Simulation of Large-scale PBS Based Clusters.
    Georg Zitzlsberger, Branislav Jansík, Jan Martinovič
    IADIS International Journal on Computer Science and Information Systems, 2018, IADIS Press
    DOI: N/A
  • Aspect composition for multiple target languages using LARA.
    Pedro Pinto, Tiago Carvalho, João Bispo, Miguel António Ramalho, João M. P. Cardoso
    Computer Languages Systems & Structures, 2018, Elsevier
    DOI: 10.1016/j.cl.2017.12.003
  • MiCOMP: Mitigating the Compiler Phase-Ordering Problem Using Optimization Sub-Sequences and Machine Learning.
    Amir Hossein Ashouri, Andrea Bignoli, Gianluca Palermo, Cristina Silvano, Sameer Kulkarni, John Cavazos:
    ACM Transactions on Architecture and Code Optimization, 2017, ACM
    DOI: 10.1145/3124452
  • Thermal Analysis and Interpolation Techniques for a Logic + WideIO Stacked DRAM Test Chip.
    Francesco Beneventi, Andrea Bartolini, Pascal Vivet, and Luca Benini
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2016, IEEE
    DOI: 10.1109/TCAD.2015.2474382
  • COBAYN: Compiler Autotuning Framework using Bayesian Networks.
    Amir Hossein Ashouri, Giovanni Mariani, Gianluca Palermo, Eunjung Park, John Cavazos, Cristina Silvano
    ACM Transactions on Architecture and Code Optimization, 2016, ACM
    DOI: 10.1145/2928270

Conference Publications

  • Vertex importance extension of betweenness centrality algorithm.
    Jiří Hanzelka, Michal Běloch, Jan Martinovič, Kateřina Slaninová
    2nd International Conference on Data Management, Analytics and Innovation, ICDMAI 2018, 2019, Springer Singapure
    DOI: 10.1007/978-981-13-1402-5_5
  • An OpenMP based Parallelization Compiler for C Applications.
    Hamid Arabnejad, João Bispo, Jorge Manuel Gomes Barbosa, João M. P. Cardoso
    IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA 2018), 2018, IEEE
    DOI: N/A
  • A scalable framework for online power modelling of high-performance computing nodes in production.
    Federico Pittino, Francesco Beneventi, Andrea Bartolini, Luca Benini
    2018 International Conference on High Performance Computing & Simulation (HPCS), 2018, IEEE
    DOI: 10.1109/HPCS.2018.00058
  • Autotuning and adaptivity in energy efficient HPC systems: The ANTAREX toolbox.
    Cristina Silvano, Gianluca Palermo, Giovanni Agosta, Amir H. Ashouri, Davide Gadioli, Stefano Cherubin, Emanuele Vitali, Luca Benini, Andrea Bartolini, Daniele Cesarini, Joao Cardoso, Joao Bispo, Pedro Pinto, Riccardo Nobre, Erven Rohou, Loïc Besnard, Imane Lasri, Nico Sanna, Carlo Cavazzoni, Radim Cmar, Jan Martinovič, Kateřina Slaninová, Martin Golasowski, Andrea R. Beccari, Candida Manelfi
    2018 ACM International Conference on Computing Frontiers, CF 2018 - Proceedings, 2018, ACM
    DOI: 10.1145/3203217.3205338
  • SOCRATES - A seamless online compiler and system runtime autotuning framework for energy-aware applications.
    Davide Gadioli, Ricardo Nobre, Pedro Pinto, Emanuele Vitali, Amir H. Ashouri, Gianluca Palermo, Joao Cardoso, Cristina Silvano
    Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018, 2018, IEEE
    DOI: 10.23919/DATE.2018.8342183
  • Embedded Operating System Optimization through Floating to Fixed Point Compiler Transformation.
    Daniele Cattaneo, Antonio Di Bello, Stefano Cherubin, Federico Terraneo, Giovanni Agosta
    Euromicro Conference on Digital System Design (DSD), 2018
    DOI: 10.1109/DSD.2018.00042
  • Real time traffic simulator for self-adaptive navigation system validation.
    Vít Ptošek, Jiří Ševčík, Jan Martinovič, Kateřina Slaninová, Lukáš Rapant, Radim Cmar
    30th European Modeling and Simulation Symposium, EMSS 2018, 2018, Dime University of Genoa
    DOI: N/A
  • Exploitation of HPC Infrastructure Services for Real-Time Critical Small Requests.
    Jiří Ševčík, Martin Golasowski, Jan Martinovič, David Vojtek, Jan Faltýnek
    30th European Modeling and Simulation Symposium, EMSS 2018, 2018, Dime University of Genoa
    DOI: N/A
  • Multinode Approach for Map Data Processing.
    Vít Ptošek, Kateřina Slaninová
    6th International Doctoral Symposium on Applied Computation and Security Systems ACSS 2018, 2018, Springer Singapure
    DOI: 10.1007/978-981-13-3250-0_7
  • The ANTAREX tool flow for monitoring and autotuning energy efficient HPC systems.
    Cristina Silvano, Giovanni Agosta, Jorge Barbosa, Andrea Bartolini, Andrea R. Beccari, Luca Benini, Joao Bispo, João M. P. Cardoso, Carlo Cavazzoni, Stefano Cherubin, Radim Cmar, Davide Gadioli, Candida Manelfi, Jan Martinovič, Ricardo Nobre, Gianluca Palermo, Martin Palkovič, Pedro Pinto, Erven Rohou, Nico Sanna, Kateřina Slaninová
    Proceedings - 2017 17th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2017, 2017, IEEE
    DOI: 10.1109/SAMOS.2017.8344645
  • Continuous learning of HPC infrastructure models using big data analytics and in-memory processing tools.
    Francesco Beneventi, Andrea Bartolini, Carlo Cavazzoni, Luca Benini
    Design, Automation Test in Europe Conference Exhibition (DATE), 2017, IEEE
    DOI: 10.23919/DATE.2017.7927143
  • Prediction horizon vs. efficiency of optimal dynamic thermal control policies in HPC nodes.
    Daniele Cesarini, Andrea Bartolini, Luca Benini
    IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC), 2017, 2017, IFIP/IEEE
    DOI: 10.1109/VLSI-SoC.2017.8203471
  • Server-Side Navigation Service Benchmarking Tool.
    Martin Golasowski, Kateřina Slaninová, Jiří Ševčík, Vít Ptošek, David Vojtek
    Proceedings of the 14th International Symposium on Operational Research, SOR 2017, 2017, SLOVENIAN SOCIETY INFORMATIKA
    DOI: N/A
  • Expressing and Applying C++ Code Transformations for the HDF5 API Through a DSL.
    Martin Golasowski, João Bispo, Jan Martinovic, Kateřina Slaninová, João MP Cardoso
    16th International Conference on Computer Information Systems and Industrial Management Applications (CISIM 2017), 2017, Springer
    DOI: 10.1007/978-3-319-59105-6_26
  • LARA as a Language-Independent Aspect-Oriented Programming Approach.
    Pedro Pinto, Tiago Carvalho, João Bispo and João MP Cardoso
    32nd ACM/SIGAPP SAC Symposium on Applied Computing (SAC’17), 2017, ACM
    DOI: 10.1145/3019612.3019749
  • Cooling-Aware Node-level Task Allocation for Next-Generation Green HPC Systems.
    Francesco Benventi, Andrea Bartolini, Carlo Cavazzoni and Luca Benini
    2016 International Conference on High Performance Computing & Simulation (HPCS), 2016, IEEE
    DOI: 10.1109/HPCSim.2016.7568402
  • Evaluation of Synchronization Protocols for fine-grain HPC sensor data time-stamping and collection.
    Antonio Libri, Andrea Bartolini, Michele Magno and Luca Benini
    2016 International Conference on High Performance Computing & Simulation (HPCS), 2016, IEEE
    DOI: 10.1109/HPCSim.2016.7568419
  • AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems: the ANTAREX Approach.
    Cristina Silvano, Giovanni Agosta, Andrea Bartolini, Andrea R. Beccari, Luca Benini, João Bispo, Radim Cmar, João M. P. Cardoso, Carlo Cavazzoni, Jan Martinovic, Gianluca Palermo, Martin Palkovic, Pedro Pinto, Erven ohou, Nico Sanna, and Katerina Slaninová
    Design, Automation & Test in Europe Conference & Exhibition, 2016, IEEE
    DOI: 10.3850/9783981537079_1012
  • The ANTAREX Approach to Autotuning and Adaptivity for Energy Efficient HPC Systems.
    Cristina Silvano, Giovanni Agosta, Stefano Cherubin, Davide Gadioli, Gianluca Palermo, Andrea Bartolini, Luca Benini, Jan Martinovic, Martin Palkovic, Katerina Slaninová, João Bispo, João M. P. Cardoso, Rui Abreu, Pedro Pinto, Carlo Cavazzoni, Nico Sanna, Andrea R. Beccari, Radim Cmar, Erven Rohou
    Proceedings of the ACM International Conference on Computing Frontiers, 2016, ACM
    DOI: 10.1145/2903150.2903470
  • ANTAREX - AutoTuning and Adaptivity appRoach for Energy Efficient eXascale HPC Systems.
    Cristina Silvano, Giovanni Agosta, Andrea Bartolini, Andrea Beccari, Luca Benini, João M. P. Cardoso, Carlo Cavazzoni, Radim Cmar, Jan Martic, Gianluca Palermo, Martin Palkovic, Erven Rohou, Nico Sanna, and Katerina Slaninov
    18th IEEE International Conference on Computational Science and Engineering, 2015, IEEE
    DOI: 10.1109/CSE.2015.58

Organization of Events

  • [PRACE Training School] Data Analytics for System and Facility Energy Management (Supercomputing 2018)
    ETHZ, 11-16 November, 2018, Dallas, USA
  • [Bird of Feather] Data Analytics for System and Facility Energy Management (Supercomputing 2018)
    ETHZ, 11-16 November, 2018, Dallas, USA
  • [Workshop organization] ANDARE: Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems
    UPORTO+POLIMI+ETHZ, 4 November, 2018, Limassol, Cyprus
  • [PRACE On Demand Event/School] ANTAREX: Monitoring, Compilation and Autotuning Approach for Energy-Efficient HPC Systems
    IT4I+POLIMI+UPORTO, 22-23 October, 2018, Ostrava, Czech Republic
  • [Tutorial] Clava+LARA: A Source-to-source C/C++ Compiler for Instrumentation and Code Transformations (IEEE 16th International Conference on Industrial Informatics (INDIN’2018))
    UPORTO, 18-20 July, 2018, Porto, Portugal
  • [Workshop organization] EETHPC - Energy Efficiency Tools for High Performance Computing
    Organized jointly with the FET-HPC projects: READEX, ANTAREX, and GEOPM, As part of the ISC High Performance 2018, 28 June, 2018, FRANKFURT AM MAIN, Germany
  • [Workshop organization] HPCAFE-2018: High-Performance Computing Approaches for Monitoring, Exploring, Optimizing and Autotuning (European HPC Summit Week 2018)
    UPORTO (ALLSCALE + READEX + ExCAPE FET-HPC projects), 28 May - 01 June, 2018, Ljubljana, Slovenia
  • [Workshop organization] ANDARE: Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems
    UPORTO+POLIMI+ETHZ, 9 September, 2017, Portland, Oregon, USA
  • [Workshop organization] HeteroPar: Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms (in Euro-Par 2017)
    UPORTO, 28-29 August, 2017, Santiago de Compostela, Spain
  • [Workshop organization] HPCAFE-2017: High-Performance Computing Approaches for Monitoring, Exploring, Optimizing and Autotuning (European HPC Summit Week 2017)
    UPORTO (ALLSCALE + READEX FET-HPC projects), 19 May, 2017, Barcelona, Spain
  • [Workshop organization] PARMA-DITAM'2017, Workshop colocated with HiPEAC'2017
    POLIMI + UPORTO, 25 January, 2017, Stockholm, Sweden
  • [Workshop organization] International Workshop on Energy-aware high performance Heterogeneous Architectures and Accelerators
    ETHZ, 18-22 July, 2016, Innsbruck, Austria
  • [Workshop organization] 1st Workshop about Computational Challenges on Climate Modelling and Weather Prediction (CLIMA’2016), co-located with the 12th International Meeting on High-Performance Computing for Computational Science (VECPAR 2016)
    UPORTO, 1 July, 2016., University of Porto, FEUP, Porto, Portugal
  • [Organization Committee] 12th International Meeting on High Performance Computing for Computational Science (VECPAR’2016)
    UPORTO, 28-30 June, 2016, University of Porto, FEUP, Porto, Portugal
  • [Event organization] PRACEdays 2016
    IT4I, 10-12 May, 2016, Prague, Czech Republic
  • [Thematic Session Organization] Programming Models and Tools towards Energy-efficient Exascale Computing Systems
    UPORTO (University of Innsbruck + INESC-ID), 20 April, 2016, Porto, Portugal
  • [Event organization] HiPEAC Computing System Week (CSW)
    UPORTO, 20 April, 2016, Porto, Portugal
  • [Tutorial] LARA Tutorial: A DSL-based Approach for Cross Layer Programming: Monitoring, Adaptivity and Tuning
    UPORTO, 20-22 April, 2016, Porto, Portugal
  • [Workshop organization] RES4ANT Workshop at DATE2016 Conference
    POLIMI, 18 March, 2016, Dresden, Germany
  • [Conference organization] 10th International Conference on High-Performance and Embedded Architectures and Compilers (HiPEAC’2016)
    IT4I, 18-20 January, 2016, Prague, Czech Republic
  • [Workshop organization] PARMA-DITAM'2016, Workshop colocated with HiPEAC'2016
    POLIMI + UPORTO, 18 January, 2016, Stockholm, Sweden

Presentations

  • [Booth] Self-Adaptable Navigation for Smart Cities Use-Case Prototype
    [Speaker] Jan Martinovic, Kateřina Slaninová, Radim Cmar
    Transport Research Arena (TRA 2018), April 16-19, 2018, Vienna, Austria
  • [University Booth] Clava + mArgot = C/C++ to C/C++ Compiler and Runtime Autotuning Framework.
    [Speaker] Pedro Pinto and Davide Gadioli
    Design, Automation and Test in Europe 2018 (DATE’2018), March 20-21, 2018, Dresden, Germany
  • [Invited Talk] Empowering OpenPOWER.
    [Speaker] Andrea Bartolini, ETHZ
    OpenPOWER Summit US 2018, March 19, 2018, Las Vegas, USA
  • [Workshop Organization] ANDARE'17 - Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems.
    Chairs: Andrea Bartolini, João M. P. Cardoso and Cristina Silvano
    Co-located with the 26th Edition of the International COnference on Parallel Architectures and Compilation Techniques (PACT), September 9, 2017, Portland, USA
  • [Invited Talk] Application autotuning for energy efficient heterogeneous HPC systems
    [Speaker] Cristina Silvano, POLIMI
    15th International Workshop on Scalable Approaches to High Performance and High Productivity Computing, September 18, 2017, Bertinoro, Italy
  • [Keynote] Application autotuning for energy efficient heterogeneous HPC systems
    [Speaker] Cristina Silvano, POLIMI
    15th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms. The workshop was co-located with the 23rd edition of EuroPar'2017, the International European Conference on Parallel and Distributed Computing, August 28, 2017, Santiago de Compostela, Spain
  • [Invited Talk] Energy-efficient and accelerated servers
    [Speaker] Cristina Silvano, POLIMI
    The 17th edition of the SAMOS International Conference on Embedded Computer Systems: Architecture, Modeling and Simulation, July 16, 2017, Samos, Greece
  • [Invited talk] GPS Navigation companies needs and experiences with high performance computing
    PARMA-DITAM 2017 Workshop, January 25, 2017, Stockholm, Sweden
  • [Invited Talk] On the Path towards Exascale Computing in the Czech Republic and in Europe.
    [Speaker] Martin Palkovič, IT4I
    Exascale II: Roadmaps and Challenges, The 14th HPC Connection Workshop@SC16, November 16, 2016, Salt Lake City, UT, USA
  • [Poster] DSL and Autotuning Tools for Code Optimization on HPC Inspired by Navigation Use Case.
    [Speaker] Kateřina Slaninová, IT4I
    SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, November 13-18, 2016, Salt Lake City, UT, USA
  • [Oral Presentation] The ANTAREX Approach to Autotuning and Adaptivity for Energy Efficient HPC Systems.
    [Speaker] Jorge Barbosa, FEUP
    Nesus Fifth Working Group Meeting, July 8, 2016, Ljubljana, Slovenia
  • [Invited talk] AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems: The ANTAREX Approach
    Workshop about Computational Challenges on Climate Modelling and Weather Prediction (CLIMA’2016), July 1, 2016, Porto, Portugal
  • [Oral Presentation] The LARA-based Compiler Toolsuite
    ACM Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES’2016), June 13-14, 2016, Santa Barbara, California, USA
  • [Seminar] Design Space and Application Autotuning for Runtime Adaptivity in Multicore Architectures
    Brain Inspired Computing Group, IBM Research, Austin, June 9, 2016, Austin, Texas, USA
  • [Seminar] Design Space and Application Autotuning for Runtime Adaptivity in Multicore Architectures
    The University of Texas at Austin, Electrical and Computer Engineering, Computer Architecture Seminar, June 3, 2016, Austin, Texas, USA
  • [Invited Talk] The ANTAREX Approach to Autotuning and Adaptivity for Energy Efficient HPC Systems
    [Speaker] Cristina Silvano, POLIMI
    ACM International Conference on Computing Frontiers (CF’2016), May 16-18, 2016, Como, Italy
  • [Keynote] Sub-PicoJoule per Operation scalable computing - Why, When, How?
    [Speaker] Luca Benini, ETHZ
    ACM International Conference on Computing Frontiers (CF’2016), May 16-18, 2016, Como, Italy
  • [Poster] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale
    [Speaker] Kateřina Slaninová, IT4I
    HPC systems PRACE Scientific & Industrial Conference, PRACEdays 2016, 2016, Prague, Czech Republic
  • [Invited Talk] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale
    [Speaker] Martin Palkovic, IT4Innovations
    European HPC Summit week: EXDCI (European eXtreme Data and Computing Initiative) Workshop, 2016, Prague, Czech Republic
  • [Invited Talk] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems.
    Cristina Silvano
    Thematic Session: Programming Models and Tools towards Energy-efficient Exascale Computing Systems, in HiPEAC Computing System Week, April 20, 2016, Porto, Portugal
  • [Tutorial] A DSL-based Approach for Cross Layer Programming: Monitoring, Adaptivity and Tuning.
    [Speakers] João M. P. Cardoso, João Bispo, Tiago Carvalho, Pedro Pinto, Luís Reis, Ricardo Nobre, UPORTO
    Thematic Session: LARA Tutorial: A DSL-based Approach for Cross Layer Programming: Monitoring, Adaptivity and Tuning, in HiPEAC Computing System Week, April 18, 2016, Porto, Portugal
  • [Panel] Moore's law is still alive! So why resource awareness?
    [Panel Participant] João M. P. Cardoso, UPORTO [Member of the Organization] Cristina Silvano, POLIMI
    First Workshop on Resource Awareness and Application Autotuning in Adaptive and Heterogeneous Computing, March 18, 2016, Dresden, Germany
  • [Invited Talk] A DSL-based Approach for Cross Layer Programming: Monitoring, Adaptivity and Tuning
    [Speaker] João M. P. Cardoso
    First Workshop on Resource Awareness and Application Autotuning in Adaptive and Heterogeneous Computing, March 18, 2016, Dresden, Germany
  • [Oral Presentation] AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems: the ANTAREX Approach
    [Speaker] Cristina Silvano, POLIMI
    DATE2016-EU-Track, EU Special Session: Energy Efficiency drives Design, March 16, 2016, Dresden, Germany
  • [Poster] Stack Size Estimation on Machine-Independent Intermediate Code for OpenCL Kernels.
    [Speaker] Stefano Cherubin, POLIMI
    European LLVM Developers' Meeting, March 17-18, 2016, Barcelona, Spain
  • [Oral Presentation] A Predictive Modeling Framework For Compiler Phase-ordering Problem
    [Speaker] Amir Hossein Ashouri, POLIMI
    Student Research Competition (SRC), The 14th International Symposium on Code Generation and Optimization (CGO’2016), March, 2016, Barcelona, Spain
  • [Invited Talk] Trends in Energy and Thermal efficiency of High Performance computing infrastructure
    [Speaker] Andrea Bartolini, ETHZ
    International Workshop on Dynamic Code Auto-Tuning (DCAT2016), part of International Symposium for Code Generation and Optimization (CGO’2016), March 12, 2016, Barcelona, Spain
  • [Invited Talk] Multiscale Energy-Thermal Management for Green Supercomputers
    [Speaker] Andrea Bartolini, ETHZ
    Dagstuhl Seminar 16052, Dark Silicon: From Embedded to HPC Systems - Dagstuhl Schloss, January 31, 2016, Wadern, Germany
  • [Poster] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems
    [Speaker] Cristina Silvano, POLIMI
    10th International Conference on High-Performance and Embedded Architectures and Compilers (HiPEAC’2016), January 20, 2016, Prague, Czech Republic
  • [Keynote] Sub-pj per operation scalable computing - the next challenge
    [Speaker] Luca Benini, ETHZ
    ICT-Energy: Minimizing Energy Consumption of Computing to the Limit, workshop co-located with HiPEAC’2016, January 18, 2016, Prague, Czech Republic
  • [Invited Talk] Programming tools and algorithms for exascale systems
    [Speaker] Martin Palkovic, IT4Innovations
    PARMA-DITAM 2016 Workshop, 7th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures, 5th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms, co-located with HiPEAC’2016, January 18, 2016, Prague, Czech Republic
  • [Poster] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems
    [Speaker] Erven Rohou, INRIA
    Green ICT Day, November 30, 2015, Rennes, France
  • [Birds of a Feather] Taking on Exascale Challenges: Key Lessons and International Collaboration Opportunities Delivered by European Cutting-Edge HPC Initiatives
    [Speaker] Martin Palkovic, IT4Innovations
    International Conference for High Performance Computing, Networking, Storage and Analysis (SC’2015), November 15-20, 2015, Austin, TX, USA
  • [Invited Talk] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems
    Green ICT @ IRISA, November 30, 2015, Rennes, France
  • [Oral Presentation] ANTAREX Project, CINECA SuperComputing Applications and Innovation Department
    [Speaker] Nico Sanna, CINECA
    SCAI (FET HPC), Future and Emerging Technologies: Giornata Nazionale di Lancio dei Bandi 2016-17 in Horizon 2020, November 29, 2015, Roma, Italy
  • [Poster] ANTAREX: AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems.
    [Speaker] Cristina Silvano
    18th IEEE International Conference on Computational Science and Engineering / 13th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, October 23, 2015, Porto, Portugal
    Download poster here.
  • [Keynote] Design Space Exploration and Application Autotuning for Runtime Adaptivity in Multicore Architectures.
    Cristina Silvano, POLIMI
    18th IEEE International Conference on Computational Science and Engineering / 13th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, October 21, 2015, Porto, Portugal
  • [Invited Talk] Trends in Energy, Power and Thermal Efficiency of HPC systems
    [Speaker] Andrea Bartolini, ETHZ
    Workshop on Computational Science Infrastructure and Applications for Academic Development in the ICTP, October, 2015, Trieste, Italy
  • [Oral Presentation] ANTAREX -- AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems.
    Cristina Silvano, POLIMI
    ETP4HPC (European Technology Platform for High Performance Computing) - EXDCI (European eXtreme Data and Computing Initiative) Workshop, September 29-30, 2015, Rome, Italy
  • [Oral Presentation] ANTAREX -- AutoTuning and Adaptivity appRoach for Energy efficient eXascale HPC systems.
    Cristina Silvano, POLIMI
    Thematic Session on: Challenges and Opportunities in Next-Generation HPC Systems for Real-Time Applications, HiPEAC Comptuting System Week, September 21, 2015

Public Deliverables

Workpackage 1 - Requirements and Specifications

  • D1.1 - Requirements
  • D1.2 - Data Management Plan
  • D1.3 - Specification of Holistic Approach, Tools and APIs

Workpackage 2 - Programming Models and Languages for Self-adaptivity

  • D2.1 - Programming Model and DSL for Adaptivity
  • D2.2 - Code Refactoring Tool Guided by DSL
  • D2.3 - Compiler and Code Generation Support
  • D2.4 - DSL Language Runtime and API Support
  • D2.5 - DSL Support for Extra-Functional Characteristics

Workpackage 3 - Techniques for Self-adaptivity, Monitoring and Runtime Management

  • D3.1 - Monitoring and Profiling Framework to Support Adaptivity
  • D3.2 - Initial Application-Level Self-tuning Framework and APIs
  • D3.3 - Initial Runtime Resource and Power Manager
  • D3.4 - Final Application Level Self-tuning Framework and APIs
  • D3.5 - Final Runtime Resource and Power Manager

Workpackage 4 - UC1: Computer Accelerated Drug Discovery System

  • D4.4 - UC1 Validation and Assessment Report
  • D4.5 - Results on Data Collection, Analysis and Control

Workpackage 5 - UC2: Self-Adaptive Navigation System

  • D5.5 - UC2 Validation and Assessment Report

Workpackage 6 - Dissemination and Exploitation

  • D6.1 - Setup and Maintenance of ANTAREX Website
  • D6.2 - Dissemination of the Foreground Knowledge: Activities and Plans (Dissemination Plan 1)
  • D6.3 - Dissemination of the Foreground Knowledge: Activities and Plans (Dissemination Plan 2))
  • D6.5 - Workshops/Tutorials/Schools on Project Achievements
  • D6.6 - Dissemination of the Foreground Knowledge: Activities and Plans (Dissemination Plan 3)
  • D6.7 - ANTAREX Online Project Book
  • D6.10 - Open Research Data Pilot Report

Workpackage 7 - Project Management

  • D7.3 - Lessons Learnt from ANTAREX Project

Tools

libVersioningCompiler

Enables runtime compilation of source code and dynamic loading of a specified C/C++ function. It also provides support for versioning of the compiled functions.

  • GitHub

Examon

A highly scalable framework for performance and energy monitoring of HPC servers.

  • GitHub

mARGOt

C++ framework to enable dynamic adaptation of applications, in order to face changes in the execution environment or in the application requirements.

  • GitLab

Power Manager

Power capper that selects the best performance point for each core in order to maintain a power constraint.

  • ETHZ

Clava

C/C++ source-to-source tool for code instrumentation and transformations controlled by the LARA language.

  • GitHub
  • Online Demo

Countdown

Runtime to identify and automatically reduce the power consumption of the computing elements during communication and MPI primitives based on ultra-fine grain capabilities for profiling.

  • GitHub
  • ETHZ

ANTAREX YouTube Channel

ANTAREX videos can be found on our YouTube channel.


1. Clava

  • 1.1 - IDE (2:02)
  • 1.2 - Simple Example (1:24)
  • 1.3 - Documentation (1:04)
  • 1.4 - Unit Testing (1:32)
  • 1.5 - CMake Plugin (1:23)
  • 1.6 - C Auto-Parallelization Library (2:21)

2. Clava Integration for ANTAREX Tools

  • 2.1 - mARGOt (6:41)
  • 2.2 - LibVC (1:54)
  • 2.3 - Examon (2:06)
  • 2.4 - Memoization (8:11)
  • 2.5 - Custom Precision (3:57)
  • 2.6 - Loop Splitting (7:39)

3. ANTAREX Tools

  • 3.1 - LibVC: LibVersioningCompiler (7:01)
  • 3.2 - The mARGOt Framework: Runtime Autotuning (11:07)
  • 3.3 - COUNTDOWN and EXAMON (5:49)

4. Use Cases

  • 4.1 - UC2 - Simulation of traffic flow distribution using self-adaptive navigation service (2:29)

Online Book - ANTAREX: Lessons Learned

Summary

The main goal of the ANTAREX project was to provide a breakthrough approach to map, runtime manage and autotune applications for green and heterogeneous HPC systems up to the Exascale level. The key ANTAREX innovations were designed and engineered since the beginning to be scaled-up to the Exascale level. One key innovation of the proposed approach consists of introducing a separation of concerns (where self-adaptivity and energy efficient strategies are specified aside to application functionalities) promoted by the definition of a Domain Specific Language (DSL), inspired by aspect-oriented programming (AOP) concepts for heterogeneous systems. The DSL was introduced for expressing the adaptivity/energy/performance strategies and to enforce at runtime application autotuning and resource and power management. The goal was to support the parallelism, scalability and adaptability of a dynamic workload by exploiting the full system capabilities (including energy management) for emerging large-scale and extreme-scale systems, while reducing the Total Cost of Ownership (TCO) for companies and public organizations.

This online book describes the main tools and libraries that are part of the ANTAREX tool flow.



Table of Contents