Comparison of PRACE prototypes and benchmarks. Axel Berg (SARA, NL), ISC 10 Hamburg June 1 st 2010
|
|
- Julia Sharp
- 5 years ago
- Views:
Transcription
1 Comparison of PRACE prototypes and benchmarks Axel Berg (SARA, NL), ISC 10 Hamburg June 1 st 2010
2 What is a prototype? 2
3 The prototype according to Wikipedia A prototype is an original type, form, or instance of something serving as a typical example, basis, or standard for other things of the same category. The word derives from the Greek πρωτότυπον (prototypon), "primitive form", neutral of πρωτότυπος (prototypos), "original, primitive", from πρῶτος (protos), "first" and τύπος (typos), "impression". 3
4 Prototypes in PRACE prototypes of leadership class systems at selected sites that are likely to become productions level systems in 2009/2010 prototypes of potential Petaflop/s systems/architectures for the near future ( ) PRACE WP5 prototypes prototypes of testable components and technology (HW & SW) for multi-petaflop/s systems beyond 2011 PRACE WP8 prototypes t 4
5 Prototypes in PRACE prototypes of leadership class systems at selected sites that are likely to become productions level systems in 2009/2010 prototypes of potential Petaflop/s systems/architectures for the near future ( ) PRACE WP5 prototypes prototypes of testable components and technology (HW & SW) for multi-petaflop/s systems beyond 2010 PRACE WP8 prototypes t 5
6 Deployment and assessment of Prototype Systems selection and installation ti of prototype t systems test t integration ti and operation in close to production conditions evaluation of the technical capabilities user application benchmarking 6
7 Selected PRACE prototypes Site FZJ Germany Architecture Vendor/Technology MPP IBM BlueGene/P Point of contact Michael Stephan CSC-CSCSCSCS MPP Janne Ignatius Finland+Switzerland Cray XT5 - AMD Opteron janne.ignatius@csc.fi CEA-FZJ France+Germany NCF/SARA Netherlands BSC Spain SMP-TN Bull/SUN Intel Nehalem SMP-FN IBM Power6 Hybrid fine grain IBM Cell Gilles Wiber gilles.wiber@cea.fr Norbert Eicker n.eicker@fz-juelich.de Axel Berg axel@sara.nl Peter Michielse p.michielse@nwo.nl Sergi Girona sergi.girona@bsc.es HLRS Hybrid coarse grain Stefan Wesner Germany NEC Vector SX/9 + Intel Nehalem wesner@hlrs.de 7
8 Installed PRACE prototypes IBM BlueGene/P (FZJ) IBM Power6 (SARA) Cray XT5 (CSC) IBM Cell (BSC) NEC SX9, vector part (HLRS) cluster part (HLRS) Bull Intel Nehalem (CEA) SUN/Bull Intel Nehalem (FZJ)
9 Basic features of the prototypes IBM BlueGene/P FZJ IBM Power6 SARA Cray XT4/5 CSC IBM Cell BSC NEC SX 9 HLRS NEC Nehalem HLRS Bull Nehalem CEA SUN Nehalem FZJ CPU IBM PPC450d 0,85 GHz IBM Power6 4,7 GHz AMD IBM Power NEC Intel Intel Intel Barc./Shang XCell 8i 3,2 GHz Nehalem Nehalem Nehalem 2,3/2,7 GHz 3,2 GHz 2,8 GHz 2,8 GHz 2,93 GHz Nr of nodes / Nr. of cores / Nr. of cores/node / Memory size/node 2 GB GB 4 8 GB 8 32 GB 512 GB 12 GB 24 GB 24 GB Interconnect Proprietary Qlogic IB 8 Cray Direct NEC IXS IB IB QDR IB QDR way SeaStart2+ connection Peak performance 223 TF 63 TF 86 TF 16 TF 19 TF 60 TF 11 TF 207 TF File system IBM GPFS IBM GPFS Lustre IBM GPFS GstorageFS GstorageFS Lustre Lustre Cooling type Air Water Air Air Air Air Water/air Water/air 9
10 Use and benefits of PRACE prototypes HPC infrastructure available for all partners, sharing infrastructure, results, knowledge and experience First PRACE infrastructure available to the user community for porting and testing real applications user awareness Testing of the PRACE peer review system Engagement of HPC vendors with PRACE through prototypes; individual collaboration between centres and vendors were fruitful in assessing and driving future technology Gained insight i in actual status t and potential ti of technology and vendors for delivering Petascale systems 10
11 Use and benefits of PRACE prototypes Results of technical assessments were useful in evaluation of technologies and architectures All prototypes have been used to port, optimize and scale selected applications adaptation of applications to future technology acceleration of application deployment of PRACE Tier-0 systems Results of the applications benchmarks show which applications run well on which prototype/architecture Testing and evaluation of middleware for integration of system into a European service gaining experience and collaboration among centres on the operational and technical level 11
12 Sensitivity of results NDA s with vendors (site specific and PRACE-wide) PRACE intends to work with vendors to continuously verify benchmark results, i.e. synthetic benchmarks Focus on methodologies and general experience and results 12
13 Installation reports of prototype systems installation at planning (start t date, completion o date, planned and actual) for each phase installation experiences and recommendations site preparation system delivery and physical installation system software installation application environment installation system installation to be ready for test users software preparation/configuration p of system for production installation of software for distributed system management acceptance of the system role of the vendor in installation ti process 13
14 Installation experiences and best practices Site preparation, at system delivery e and physical installation at Infrastructure planning can be very complex careful planning E.g. floor planning with precise drawings above and under floor for air flow and cabling Weight of racks, weight capacity if raised floor and route to raised floor System acceptance Power measurement Functionality tests Performance measurements (Linpack, I/O, application, throughput) Reliability test Relation with vendors Collaborate as much as possible with vendor: knowledge transfer, working relationship on technical level 14
15 Installation experiences and best practices Site preparation, at system delivery e and physical installation at Infrastructure planning can be very complex careful planning E.g. floor planning with precise drawings above and under floor for air flow and cabling Weight of racks, weight capacity if raised floor and route to raised floor System acceptance Power measurement Functionality tests Performance measurements (Linpack, I/O, application, throughput) Reliability test Relation with vendors Collaborate as much as possible with vendor: knowledge transfer, working relationship on technical level 15
16 Technical assessments of prototypes Mainly synthetic benchmarks, some qualitative measures es JuBE Benchmark framework, script-based framework to easily create benchmark sets, run those sets on different computer systems and evaluate the results ( Scalability wherever possible benchmarks on: a single core, half of the cores on a node, all cores on a node, all cores on an increasing i number of nodes, all nodes in the prototype Comparing results is a challenge Prototypes are different in size Prototypes have different production status Prototypes have I/O systems s designed ed for different e levels e of performance Prototypes represent different generations of technology 16
17 Technical assessments system performance Linpack sustained performance EuroBen intrinsic operations EuroBen representative ti algorithms Sustained memory bandwidth (at different cache levels) (STREAM/STREAM2) Cache miss performance (RandomAccess) message passing MPI performance (SKaMPI) Overlap between computation and MPI communication performance (SMB) internal I/O Metadata I/O (Bonnie++) Data I/O (IOR) 17
18 Technical assessments continued system balance a Memory bandwidth per Flop/s MPI bandwidth per Flop/s at different scales Disk I/O per Flop/s at different scales OS performance OS Noise (P-SNAP), OS Jitter (Selfish), OS System resource usage system availability and reliability design + experience manageability of the system system start-up times In general: sufficiently mature technology exists in most if not all aspects of systems to provide Petaflop/s in very near future 18
19 Particle User application benchmarks User applications have been identified ed as being representative of current and future usage of major European HPC systems Initial choice of representative applications based on results of surveys of applications, systems usage and key users Good spread of applications areas, algorithm classes, geographical distribution and prototype o coverage Updated after actual scaling results from PRACE prototypes Plasma Physics 3.3 Computational Engineering 3.7 Life Sciences 5.3 Astronomy & Cosmology 5.8 Earth & Climate 7.8 CFD 8.6 Other 5.8 Condensed Matter Physics 14.2 Particle Physics 23.5 Computational Chemistry 22.1 Application benchmarks used were not I/O intensive i Measure performance of basic architecture No unduly influence by particular I/O system, in some cases I/O systems were not representative of production systems 19
20 User application benchmarks To make meaningful comparisons, s, benchmarks were e run on partitions tto of prototypes which have the same nominal peak performance e.g. 10Tflop/s peak: 3000 cores of IBM BG/P 1000 cores of Cray XT5 500 cores of IBM Power6 100 SX9 vector cores 100 IBM Cells 3000 cores 1000 cores 500 cores 100 cores 100 cores Run on a small number of partition sizes (e.g. 5, 10, 20, 40 Tflop/s) For each partition size, the same input data will be used on all systems Partial coverage of possible application/prototype combinations Compile or runtime failures Lack of available experts for porting Late availability of some prototypes 20
21 Application IBM Power6 IBM BlueGene/P Cray XT5b Cray XT5s Sun x86 cluster Bull x86 cluster IBM Cell NEC SX-9 NEC x86 cluster Code_Saturne CP2K CPMD EUTERPE GADGET GROMACS NAMD NEMO NS3D QCD Quantum_Espresso WRF ALYA AVBP BSIT ELMER GPAW HELIUM OCTOPUS PEPC existence of benchmark data on 10 Tflop/s peak partition, status December
22 General remarks on user application benchmarks Spread of performance numbers across different e prototypes is not huge for most applications Many prototypes show application performance in same order of magnitude (factor between 0,5 and 2) No orders of magnitude difference Selection of a system for running the applications makes sense but is not crucial For some applications spread of performance numbers across prototypes is large Selection of a system for running the application is very relevant Results obtained are very useful for selection the right system/architecture for certain applications 22
23 Scaling of user application benchmarks Benchmark results give good indication of the scaling properties of applications on the various prototype systems Combination of the application and the prototype architecture determines performance scaling Very difficult to predict scaling properties of application-prototype combinations beyond the tested t sizes Performance modelling is required to make such predictions Ex xecution time 1.0E E+02 10E E E+00 IBM BlueGene/P IBM Power Number of CPUs 23
24 Final remarks Huge amount of data has been collected through synthetic and user benchmarks on different prototype systems Detailed insight in large number of important characteristics of systems and architectures, useful comparisons can be made using these benchmarks Important set of reference material for assessment of systems in the future Early access to new systems and architectures is important for testing under close to production conditions Both from system side as from application side 24
25 Final remarks cont d Much more difficult to derive e clear and unambiguous recommendations e o for selection of near-future multi Petaflop/s systems Large number of variables to consider in selection of HPC system Not one system will fit best all applications PRACE will offer variety of systems and architectures Assessed prototypes had very different system sizes and technical maturity Results do provide good guideline for what system/architecture shows good performance on certain features or applications Scaling has been evaluated up to the scale of the prototype systems Predicting scaling beyond the size of the prototype is speculative or at most indicative 25
26 Thank you for your attention Acknowledgements PRACE partners with prototypes: BSC, CEA, CSC, FZJ, HLRS, SARA Task leaders: Jonathan Evans (BSC), Patrice Lucas (CEA), Mark Bull (EPCC) Vendors: Bull, Cray, IBM, NEC, SUN EC FP7/ under grant agreement n RI For more information: PRACE project ( Axel Berg (axel@sara.nl) 26
Prototypes Systems for PRACE. François Robin, GENCI, WP7 leader
Prototypes Systems for PRACE François Robin, GENCI, WP7 leader Outline Motivation Summary of the selection process Description of the set of prototypes selected by the Management Board Conclusions 2 Outline
More informationPRACE prototypes. ICT 08, Lyon, Nov. 26, 2008 Dr. J.Ph. Nominé, CEA/DIF
PRACE prototypes ICT 08, Lyon, Nov. 26, 2008 Dr. J.Ph. Nominé, CEA/DIF jean-philippe.nomine@cea.fr Credits and acknowledgements: FZJ, CEA, NCF/SARA, HLRS, BSC, CSC, CSCS F. Robin (PRACE WP7 Leader) 2 PRACE
More informationCreating a European Supercomputing Infrastructure Thomas Lippert, Forschungszentrum Jülich, Germany
The Next-Generation Supercomputing Symposium 2009, Tokyo, Japan Creating a European Supercomputing Infrastructure Thomas Lippert, Forschungszentrum Jülich, Germany Regards from Prof. Dr. Achim Bachem Coordinator
More informationSEVENTH FRAMEWORK PROGRAMME Research Infrastructures
SEVENTH FRAMEWORK PROGRAMME Research Infrastructures INFRA-2007-2.2.2.1 - Preparatory phase for 'Computer and Data Treatment' research infrastructures in the 2006 ESFRI Roadmap PRACE Partnership for Advanced
More informationCreating a European Supercomputing Infrastructure Thomas Lippert, Forschungszentrum Jülich, Germany
25e Forum ORAP, EDF R&D Clamart, France, 13 36 14 octobre 2009 Creating a European Supercomputing Infrastructure Thomas Lippert, Forschungszentrum Jülich, Germany Regards from Prof. Dr. Achim Bachem Coordinator
More informationHigh Performance Computing : Code_Saturne in the PRACE project
High Performance Computing : Code_Saturne in the PRACE project Andy SUNDERLAND Charles MOULINEC STFC Daresbury Laboratory, UK Code_Saturne User Meeting Chatou 1st-2nd Dec 28 STFC Daresbury Laboratory HPC
More informationJülich Supercomputing Centre
Mitglied der Helmholtz-Gemeinschaft Jülich Supercomputing Centre Norbert Attig Jülich Supercomputing Centre (JSC) Forschungszentrum Jülich (FZJ) Aug 26, 2009 DOAG Regionaltreffen NRW 2 Supercomputing at
More informationVýpočetní zdroje IT4Innovations a PRACE pro využití ve vědě a výzkumu
Výpočetní zdroje IT4Innovations a PRACE pro využití ve vědě a výzkumu Filip Staněk Seminář gridového počítání 2011, MetaCentrum, Brno, 7. 11. 2011 Introduction I Project objectives: to establish a centre
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 6 th CALL (Tier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 6 th CALL (Tier-0) Contributing sites and the corresponding computer systems for this call are: GCS@Jülich, Germany IBM Blue Gene/Q GENCI@CEA, France Bull Bullx
More informationThe PRACE Project and using the high performance computing for large Monte Carlo simulations. Krassimir Georgiev, IICT-BAS and NCSA, Bulgaria
The PRACE Project and using the high performance computing for large Monte Carlo simulations Krassimir Georgiev, IICT-BAS and NCSA, Bulgaria Overview (1 of 8) Building a world-class pan-european High Performance
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 11th CALL (T ier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 11th CALL (T ier-0) Contributing sites and the corresponding computer systems for this call are: BSC, Spain IBM System X idataplex CINECA, Italy The site selection
More informationJÜLICH SUPERCOMPUTING CENTRE Site Introduction Michael Stephan Forschungszentrum Jülich
JÜLICH SUPERCOMPUTING CENTRE Site Introduction 09.04.2018 Michael Stephan JSC @ Forschungszentrum Jülich FORSCHUNGSZENTRUM JÜLICH Research Centre Jülich One of the 15 Helmholtz Research Centers in Germany
More informationStockholm Brain Institute Blue Gene/L
Stockholm Brain Institute Blue Gene/L 1 Stockholm Brain Institute Blue Gene/L 2 IBM Systems & Technology Group and IBM Research IBM Blue Gene /P - An Overview of a Petaflop Capable System Carl G. Tengwall
More informationUpdate on Cray Activities in the Earth Sciences
Update on Cray Activities in the Earth Sciences Presented to the 13 th ECMWF Workshop on the Use of HPC in Meteorology 3-7 November 2008 Per Nyberg nyberg@cray.com Director, Marketing and Business Development
More informationBrand-New Vector Supercomputer
Brand-New Vector Supercomputer NEC Corporation IT Platform Division Shintaro MOMOSE SC13 1 New Product NEC Released A Brand-New Vector Supercomputer, SX-ACE Just Now. Vector Supercomputer for Memory Bandwidth
More informationWelcome to the. Jülich Supercomputing Centre. D. Rohe and N. Attig Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich
Mitglied der Helmholtz-Gemeinschaft Welcome to the Jülich Supercomputing Centre D. Rohe and N. Attig Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich Schedule: Monday, May 18 13:00-13:30 Welcome
More informationPRACE Overview. Lennart Johnsson KTH and University of Houston
PRACE Overview Lennart Johnsson KTH and University of Houston Outline What is the vision and mission What is PRACE What has been achieved Current status What are the plans PRACE Vision and Mission Vision:
More informationWorkshop: Innovation Procurement in Horizon 2020 PCP Contractors wanted
Workshop: Innovation Procurement in Horizon 2020 PCP Contractors wanted Supercomputing Centre Institute for Advanced Simulation / FZJ 1 www.prace-ri.eu Challenges: Aging Society Energy Food How we can
More informationWelcome to the. Jülich Supercomputing Centre. D. Rohe and N. Attig Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich
Mitglied der Helmholtz-Gemeinschaft Welcome to the Jülich Supercomputing Centre D. Rohe and N. Attig Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich Schedule: Thursday, Nov 26 13:00-13:30
More informationAim High. Intel Technical Update Teratec 07 Symposium. June 20, Stephen R. Wheat, Ph.D. Director, HPC Digital Enterprise Group
Aim High Intel Technical Update Teratec 07 Symposium June 20, 2007 Stephen R. Wheat, Ph.D. Director, HPC Digital Enterprise Group Risk Factors Today s s presentations contain forward-looking statements.
More informationSEVENTH FRAMEWORK PROGRAMME Research Infrastructures
SEVENTH FRAMEWORK PROGRAMME Research Infrastructures INFRA-2007-2.2.2.1 - Preparatory phase for 'Computer and Data Treatment' research infrastructures in the 2006 ESFRI Roadmap PRACE Partnership for Advanced
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 16 th CALL (T ier-0)
PRACE 16th Call Technical Guidelines for Applicants V1: published on 26/09/17 TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 16 th CALL (T ier-0) The contributing sites and the corresponding computer systems
More informationOptimizing LS-DYNA Productivity in Cluster Environments
10 th International LS-DYNA Users Conference Computing Technology Optimizing LS-DYNA Productivity in Cluster Environments Gilad Shainer and Swati Kher Mellanox Technologies Abstract Increasing demand for
More informationPRACE Project Access Technical Guidelines - 19 th Call for Proposals
PRACE Project Access Technical Guidelines - 19 th Call for Proposals Peer-Review Office Version 5 06/03/2019 The contributing sites and the corresponding computer systems for this call are: System Architecture
More informationPrototyping in PRACE PRACE Energy to Solution prototype at LRZ
Prototyping in PRACE PRACE Energy to Solution prototype at LRZ Torsten Wilde 1IP-WP9 co-lead and 2IP-WP11 lead (GSC-LRZ) PRACE Industy Seminar, Bologna, April 16, 2012 Leibniz Supercomputing Center 2 Outline
More informationEuropean energy efficient supercomputer project
http://www.montblanc-project.eu European energy efficient supercomputer project Simon McIntosh-Smith University of Bristol (Based on slides from Alex Ramirez, BSC) Disclaimer: Speaking for myself... All
More informationI/O Monitoring at JSC, SIONlib & Resiliency
Mitglied der Helmholtz-Gemeinschaft I/O Monitoring at JSC, SIONlib & Resiliency Update: I/O Infrastructure @ JSC Update: Monitoring with LLview (I/O, Memory, Load) I/O Workloads on Jureca SIONlib: Task-Local
More informationHECToR. UK National Supercomputing Service. Andy Turner & Chris Johnson
HECToR UK National Supercomputing Service Andy Turner & Chris Johnson Outline EPCC HECToR Introduction HECToR Phase 3 Introduction to AMD Bulldozer Architecture Performance Application placement the hardware
More informationThe Architecture and the Application Performance of the Earth Simulator
The Architecture and the Application Performance of the Earth Simulator Ken ichi Itakura (JAMSTEC) http://www.jamstec.go.jp 15 Dec., 2011 ICTS-TIFR Discussion Meeting-2011 1 Location of Earth Simulator
More informationThe Mont-Blanc approach towards Exascale
http://www.montblanc-project.eu The Mont-Blanc approach towards Exascale Alex Ramirez Barcelona Supercomputing Center Disclaimer: Not only I speak for myself... All references to unavailable products are
More informationThe Effect of In-Network Computing-Capable Interconnects on the Scalability of CAE Simulations
The Effect of In-Network Computing-Capable Interconnects on the Scalability of CAE Simulations Ophir Maor HPC Advisory Council ophir@hpcadvisorycouncil.com The HPC-AI Advisory Council World-wide HPC non-profit
More informationExperiences with GPGPUs at HLRS
::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: Experiences with GPGPUs at HLRS Stefan Wesner, Managing Director High
More informationThe way toward peta-flops
The way toward peta-flops ISC-2011 Dr. Pierre Lagier Chief Technology Officer Fujitsu Systems Europe Where things started from DESIGN CONCEPTS 2 New challenges and requirements! Optimal sustained flops
More informationBuilding supercomputers from embedded technologies
http://www.montblanc-project.eu Building supercomputers from embedded technologies Alex Ramirez Barcelona Supercomputing Center Technical Coordinator This project and the research leading to these results
More informationScaling to Petaflop. Ola Torudbakken Distinguished Engineer. Sun Microsystems, Inc
Scaling to Petaflop Ola Torudbakken Distinguished Engineer Sun Microsystems, Inc HPC Market growth is strong CAGR increased from 9.2% (2006) to 15.5% (2007) Market in 2007 doubled from 2003 (Source: IDC
More informationQuantifying power consumption variations of HPC systems using SPEC MPI benchmarks
Center for Information Services and High Performance Computing (ZIH) Quantifying power consumption variations of HPC systems using SPEC MPI benchmarks EnA-HPC, Sept 16 th 2010, Robert Schöne, Daniel Molka,
More informationFuture Routing Schemes in Petascale clusters
Future Routing Schemes in Petascale clusters Gilad Shainer, Mellanox, USA Ola Torudbakken, Sun Microsystems, Norway Richard Graham, Oak Ridge National Laboratory, USA Birds of a Feather Presentation Abstract
More informationPreparing GPU-Accelerated Applications for the Summit Supercomputer
Preparing GPU-Accelerated Applications for the Summit Supercomputer Fernanda Foertter HPC User Assistance Group Training Lead foertterfs@ornl.gov This research used resources of the Oak Ridge Leadership
More informationCompute Node Linux: Overview, Progress to Date & Roadmap
Compute Node Linux: Overview, Progress to Date & Roadmap David Wallace Cray Inc ABSTRACT: : This presentation will provide an overview of Compute Node Linux(CNL) for the CRAY XT machine series. Compute
More informationFujitsu s Technologies to the K Computer
Fujitsu s Technologies to the K Computer - a journey to practical Petascale computing platform - June 21 nd, 2011 Motoi Okuda FUJITSU Ltd. Agenda The Next generation supercomputer project of Japan The
More informationFujitsu s Approach to Application Centric Petascale Computing
Fujitsu s Approach to Application Centric Petascale Computing 2 nd Nov. 2010 Motoi Okuda Fujitsu Ltd. Agenda Japanese Next-Generation Supercomputer, K Computer Project Overview Design Targets System Overview
More informationNEMO Performance Benchmark and Profiling. May 2011
NEMO Performance Benchmark and Profiling May 2011 Note The following research was performed under the HPC Advisory Council HPC works working group activities Participating vendors: HP, Intel, Mellanox
More informationCluster Network Products
Cluster Network Products Cluster interconnects include, among others: Gigabit Ethernet Myrinet Quadrics InfiniBand 1 Interconnects in Top500 list 11/2009 2 Interconnects in Top500 list 11/2008 3 Cluster
More informationAltair RADIOSS Performance Benchmark and Profiling. May 2013
Altair RADIOSS Performance Benchmark and Profiling May 2013 Note The following research was performed under the HPC Advisory Council activities Participating vendors: Altair, AMD, Dell, Mellanox Compute
More informationDVS, GPFS and External Lustre at NERSC How It s Working on Hopper. Tina Butler, Rei Chi Lee, Gregory Butler 05/25/11 CUG 2011
DVS, GPFS and External Lustre at NERSC How It s Working on Hopper Tina Butler, Rei Chi Lee, Gregory Butler 05/25/11 CUG 2011 1 NERSC is the Primary Computing Center for DOE Office of Science NERSC serves
More informationThe Future of Interconnect Technology
The Future of Interconnect Technology Michael Kagan, CTO HPC Advisory Council Stanford, 2014 Exponential Data Growth Best Interconnect Required 44X 0.8 Zetabyte 2009 35 Zetabyte 2020 2014 Mellanox Technologies
More informationThe Cray Rainier System: Integrated Scalar/Vector Computing
THE SUPERCOMPUTER COMPANY The Cray Rainier System: Integrated Scalar/Vector Computing Per Nyberg 11 th ECMWF Workshop on HPC in Meteorology Topics Current Product Overview Cray Technology Strengths Rainier
More informationGROMACS Performance Benchmark and Profiling. September 2012
GROMACS Performance Benchmark and Profiling September 2012 Note The following research was performed under the HPC Advisory Council activities Participating vendors: AMD, Dell, Mellanox Compute resource
More informationThread and Data parallelism in CPUs - will GPUs become obsolete?
Thread and Data parallelism in CPUs - will GPUs become obsolete? USP, Sao Paulo 25/03/11 Carsten Trinitis Carsten.Trinitis@tum.de Lehrstuhl für Rechnertechnik und Rechnerorganisation (LRR) Institut für
More informationLustre2.5 Performance Evaluation: Performance Improvements with Large I/O Patches, Metadata Improvements, and Metadata Scaling with DNE
Lustre2.5 Performance Evaluation: Performance Improvements with Large I/O Patches, Metadata Improvements, and Metadata Scaling with DNE Hitoshi Sato *1, Shuichi Ihara *2, Satoshi Matsuoka *1 *1 Tokyo Institute
More informationCESM (Community Earth System Model) Performance Benchmark and Profiling. August 2011
CESM (Community Earth System Model) Performance Benchmark and Profiling August 2011 Note The following research was performed under the HPC Advisory Council activities Participating vendors: Intel, Dell,
More informationSami Saarinen Peter Towers. 11th ECMWF Workshop on the Use of HPC in Meteorology Slide 1
Acknowledgements: Petra Kogel Sami Saarinen Peter Towers 11th ECMWF Workshop on the Use of HPC in Meteorology Slide 1 Motivation Opteron and P690+ clusters MPI communications IFS Forecast Model IFS 4D-Var
More informationHPC Resources & Training
www.bsc.es HPC Resources & Training in the BSC, the RES and PRACE Montse González Ferreiro RES technical and training coordinator + Facilities + Capacity How fit together the BSC, the RES and PRACE? TIER
More informationPorting Scientific Applications to OpenPOWER
Porting Scientific Applications to OpenPOWER Dirk Pleiter Forschungszentrum Jülich / JSC #OpenPOWERSummit Join the conversation at #OpenPOWERSummit 1 JSC s HPC Strategy IBM Power 6 JUMP, 9 TFlop/s Intel
More informationInfiniBand Strengthens Leadership as the Interconnect Of Choice By Providing Best Return on Investment. TOP500 Supercomputers, June 2014
InfiniBand Strengthens Leadership as the Interconnect Of Choice By Providing Best Return on Investment TOP500 Supercomputers, June 2014 TOP500 Performance Trends 38% CAGR 78% CAGR Explosive high-performance
More informationCP2K Performance Benchmark and Profiling. April 2011
CP2K Performance Benchmark and Profiling April 2011 Note The following research was performed under the HPC Advisory Council activities Participating vendors: AMD, Dell, Mellanox Compute resource - HPC
More informationAmazon Web Services: Performance Analysis of High Performance Computing Applications on the Amazon Web Services Cloud
Amazon Web Services: Performance Analysis of High Performance Computing Applications on the Amazon Web Services Cloud Summarized by: Michael Riera 9/17/2011 University of Central Florida CDA5532 Agenda
More informationNAMD Performance Benchmark and Profiling. November 2010
NAMD Performance Benchmark and Profiling November 2010 Note The following research was performed under the HPC Advisory Council activities Participating vendors: HP, Mellanox Compute resource - HPC Advisory
More informationThe Blue Water s File/Archive System. Data Management Challenges Michelle Butler
The Blue Water s File/Archive System Data Management Challenges Michelle Butler (mbutler@ncsa.illinois.edu) NCSA is a World leader in deploying supercomputers and providing scientists with the software
More informationHPC Architectures. Types of resource currently in use
HPC Architectures Types of resource currently in use Reusing this material This work is licensed under a Creative Commons Attribution- NonCommercial-ShareAlike 4.0 International License. http://creativecommons.org/licenses/by-nc-sa/4.0/deed.en_us
More informationHigh Performance Computing in Europe and USA: A Comparison
High Performance Computing in Europe and USA: A Comparison Erich Strohmaier 1 and Hans W. Meuer 2 1 NERSC, Lawrence Berkeley National Laboratory, USA 2 University of Mannheim, Germany 1 Introduction In
More informationManaging Hardware Power Saving Modes for High Performance Computing
Managing Hardware Power Saving Modes for High Performance Computing Second International Green Computing Conference 2011, Orlando Timo Minartz, Michael Knobloch, Thomas Ludwig, Bernd Mohr timo.minartz@informatik.uni-hamburg.de
More informationHPC projects. Grischa Bolls
HPC projects Grischa Bolls Outline Why projects? 7th Framework Programme Infrastructure stack IDataCool, CoolMuc Mont-Blanc Poject Deep Project Exa2Green Project 2 Why projects? Pave the way for exascale
More informationOpenFOAM Scaling on Cray Supercomputers Dr. Stephen Sachs GOFUN 2017
OpenFOAM Scaling on Cray Supercomputers Dr. Stephen Sachs GOFUN 2017 Safe Harbor Statement This presentation may contain forward-looking statements that are based on our current expectations. Forward looking
More informationThe Hopper System: How the Largest* XE6 in the World Went From Requirements to Reality! Katie Antypas, Tina Butler, and Jonathan Carter
The Hopper System: How the Largest* XE6 in the World Went From Requirements to Reality! Katie Antypas, Tina Butler, and Jonathan Carter CUG 2011, May 25th, 2011 1 Requirements to Reality Develop RFP Select
More informationCommunication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems.
Cluster Networks Introduction Communication has significant impact on application performance. Interconnection networks therefore have a vital role in cluster systems. As usual, the driver is performance
More informationWrite a technical report Present your results Write a workshop/conference paper (optional) Could be a real system, simulation and/or theoretical
Identify a problem Review approaches to the problem Propose a novel approach to the problem Define, design, prototype an implementation to evaluate your approach Could be a real system, simulation and/or
More informationSingle-Points of Performance
Single-Points of Performance Mellanox Technologies Inc. 29 Stender Way, Santa Clara, CA 9554 Tel: 48-97-34 Fax: 48-97-343 http://www.mellanox.com High-performance computations are rapidly becoming a critical
More informationPerformance comparison between a massive SMP machine and clusters
Performance comparison between a massive SMP machine and clusters Martin Scarcia, Stefano Alberto Russo Sissa/eLab joint Democritos/Sissa Laboratory for e-science Via Beirut 2/4 34151 Trieste, Italy Stefano
More informationTrends in HPC Architectures
Mitglied der Helmholtz-Gemeinschaft Trends in HPC Architectures Norbert Eicker Institute for Advanced Simulation Jülich Supercomputing Centre PRACE/LinkSCEEM-2 CyI 2011 Winter School Nikosia, Cyprus Forschungszentrum
More informationNVIDIA Update and Directions on GPU Acceleration for Earth System Models
NVIDIA Update and Directions on GPU Acceleration for Earth System Models Stan Posey, HPC Program Manager, ESM and CFD, NVIDIA, Santa Clara, CA, USA Carl Ponder, PhD, Applications Software Engineer, NVIDIA,
More informationHPC Technology Trends
HPC Technology Trends High Performance Embedded Computing Conference September 18, 2007 David S Scott, Ph.D. Petascale Product Line Architect Digital Enterprise Group Risk Factors Today s s presentations
More informationCSCS HPC storage. Hussein N. Harake
CSCS HPC storage Hussein N. Harake Points to Cover - XE6 External Storage (DDN SFA10K, SRP, QDR) - PCI-E SSD Technology - RamSan 620 Technology XE6 External Storage - Installed Q4 2010 - In Production
More informationAcuSolve Performance Benchmark and Profiling. October 2011
AcuSolve Performance Benchmark and Profiling October 2011 Note The following research was performed under the HPC Advisory Council activities Participating vendors: AMD, Dell, Mellanox, Altair Compute
More informationCINECA and the European HPC Ecosystem
CINECA and the European HPC Ecosystem Giovanni Erbacci Supercomputing, Applications and Innovation Department, CINECA g.erbacci@cineca.it Enabling Applications on Intel MIC based Parallel Architectures
More informationHigh Performance Computing Data Management. Philippe Trautmann BDM High Performance Computing Global Research
High Performance Computing Management Philippe Trautmann BDM High Performance Computing Global Education @ Research HPC Market and Trends High Performance Computing: Availability/Sharing is key European
More informationMaking a Case for a Green500 List
Making a Case for a Green500 List S. Sharma, C. Hsu, and W. Feng Los Alamos National Laboratory Virginia Tech Outline Introduction What Is Performance? Motivation: The Need for a Green500 List Challenges
More informationPerformance Evaluation with the HPCC Benchmarks as a Guide on the Way to Peta Scale Systems
Performance Evaluation with the HPCC Benchmarks as a Guide on the Way to Peta Scale Systems Rolf Rabenseifner, Michael M. Resch, Sunil Tiyyagura, Panagiotis Adamidis rabenseifner@hlrs.de resch@hlrs.de
More informationHPC IN EUROPE. Organisation of public HPC resources
HPC IN EUROPE Organisation of public HPC resources Context Focus on publicly-funded HPC resources provided primarily to enable scientific research and development at European universities and other publicly-funded
More informationParallel File Systems Compared
Parallel File Systems Compared Computing Centre (SSCK) University of Karlsruhe, Germany Laifer@rz.uni-karlsruhe.de page 1 Outline» Parallel file systems (PFS) Design and typical usage Important features
More informationThe Optimal CPU and Interconnect for an HPC Cluster
5. LS-DYNA Anwenderforum, Ulm 2006 Cluster / High Performance Computing I The Optimal CPU and Interconnect for an HPC Cluster Andreas Koch Transtec AG, Tübingen, Deutschland F - I - 15 Cluster / High Performance
More informationTECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 14 th CALL (T ier-0)
TECHNICAL GUIDELINES FOR APPLICANTS TO PRACE 14 th CALL (T ier0) Contributing sites and the corresponding computer systems for this call are: GENCI CEA, France Bull Bullx cluster GCS HLRS, Germany Cray
More informationMixed MPI-OpenMP EUROBEN kernels
Mixed MPI-OpenMP EUROBEN kernels Filippo Spiga ( on behalf of CINECA ) PRACE Workshop New Languages & Future Technology Prototypes, March 1-2, LRZ, Germany Outline Short kernel description MPI and OpenMP
More informationA Study of High Performance Computing and the Cray SV1 Supercomputer. Michael Sullivan TJHSST Class of 2004
A Study of High Performance Computing and the Cray SV1 Supercomputer Michael Sullivan TJHSST Class of 2004 June 2004 0.1 Introduction A supercomputer is a device for turning compute-bound problems into
More informationGOING ARM A CODE PERSPECTIVE
GOING ARM A CODE PERSPECTIVE ISC18 Guillaume Colin de Verdière JUNE 2018 GCdV PAGE 1 CEA, DAM, DIF, F-91297 Arpajon, France June 2018 A history of disruptions All dates are installation dates of the machines
More informationBirds of a Feather Presentation
Mellanox InfiniBand QDR 4Gb/s The Fabric of Choice for High Performance Computing Gilad Shainer, shainer@mellanox.com June 28 Birds of a Feather Presentation InfiniBand Technology Leadership Industry Standard
More informationThe STREAM Benchmark. John D. McCalpin, Ph.D. IBM eserver Performance ^ Performance
The STREAM Benchmark John D. McCalpin, Ph.D. IBM eserver Performance 2005-01-27 History Scientific computing was largely based on the vector paradigm from the late 1970 s through the 1980 s E.g., the classic
More informationShared Services Canada Environment and Climate Change Canada HPC Renewal Project
Shared Services Canada Environment and Climate Change Canada HPC Renewal Project CUG 2017 Redmond, WA, USA Deric Sullivan Alain St-Denis & Luc Corbeil May 2017 Background: SSC's HPC Renewal for ECCC Environment
More informationOutline. Execution Environments for Parallel Applications. Supercomputers. Supercomputers
Outline Execution Environments for Parallel Applications Master CANS 2007/2008 Departament d Arquitectura de Computadors Universitat Politècnica de Catalunya Supercomputers OS abstractions Extended OS
More informationSun Lustre Storage System Simplifying and Accelerating Lustre Deployments
Sun Lustre Storage System Simplifying and Accelerating Lustre Deployments Torben Kling-Petersen, PhD Presenter s Name Principle Field Title andengineer Division HPC &Cloud LoB SunComputing Microsystems
More informationPractical Scientific Computing
Practical Scientific Computing Performance-optimized Programming Preliminary discussion: July 11, 2008 Dr. Ralf-Peter Mundani, mundani@tum.de Dipl.-Ing. Ioan Lucian Muntean, muntean@in.tum.de MSc. Csaba
More informationThe Mont-Blanc Project
http://www.montblanc-project.eu The Mont-Blanc Project Daniele Tafani Leibniz Supercomputing Centre 1 Ter@tec Forum 26 th June 2013 This project and the research leading to these results has received funding
More informationABySS Performance Benchmark and Profiling. May 2010
ABySS Performance Benchmark and Profiling May 2010 Note The following research was performed under the HPC Advisory Council activities Participating vendors: AMD, Dell, Mellanox Compute resource - HPC
More informationBlueGene/L. Computer Science, University of Warwick. Source: IBM
BlueGene/L Source: IBM 1 BlueGene/L networking BlueGene system employs various network types. Central is the torus interconnection network: 3D torus with wrap-around. Each node connects to six neighbours
More informationRecent results with elsa on multi-cores
Michel Gazaix (ONERA) Steeve Champagneux (AIRBUS) October 15th, 2009 Outline Short introduction to elsa elsa benchmark on HPC platforms Detailed performance evaluation IBM Power5, AMD Opteron, INTEL Nehalem
More informationOrganizational Update: December 2015
Organizational Update: December 2015 David Hudak Doug Johnson Alan Chalker www.osc.edu Slide 1 OSC Organizational Update Leadership changes State of OSC Roadmap Web app demonstration (if time) Slide 2
More informationVoltaire Making Applications Run Faster
Voltaire Making Applications Run Faster Asaf Somekh Director, Marketing Voltaire, Inc. Agenda HPC Trends InfiniBand Voltaire Grid Backbone Deployment examples About Voltaire HPC Trends Clusters are the
More informationBuilding Self-Healing Mass Storage Arrays. for Large Cluster Systems
Building Self-Healing Mass Storage Arrays for Large Cluster Systems NSC08, Linköping, 14. October 2008 Toine Beckers tbeckers@datadirectnet.com Agenda Company Overview Balanced I/O Systems MTBF and Availability
More informationANSYS HPC Technology Leadership
ANSYS HPC Technology Leadership 1 ANSYS, Inc. November 14, Why ANSYS Users Need HPC Insight you can t get any other way It s all about getting better insight into product behavior quicker! HPC enables
More informationSuperMUC. PetaScale HPC at the Leibniz Supercomputing Centre (LRZ) Top 500 Supercomputer (Juni 2012)
SuperMUC PetaScale HPC at the Leibniz Supercomputing Centre (LRZ) Dieter Kranzlmüller Munich Network Management Team Ludwig Maximilians Universität München (LMU) & Leibniz Supercomputing Centre of the
More information