EXDCI Overview Transversal vision and strategic prospective
|
|
- Brittany Stevens
- 5 years ago
- Views:
Transcription
1 Overview Transversal vision and strategic prospective François Bodin WP4 28 May 2018 The project has received funding from the European Unions Horizon 2020 research and innovation programmed under grant agreement No
2 Introduction, a CSA in a rapidly evolving context Since beginning a lot has happened As planned, new FETHPC projects and CoEs IPCEI European Open Science Cloud EuroHPC Joint Undertaking Exascale still a moving target Now systems 50x to 100x faster than 2017 on real apps in 2022/2023 Pathways to convergence data and compute Extension of the use of supercomputers (e.g. urgent computing) Increased international competition China first machine in
3 Starting Point (EESI2) Scientist teams Pre-processing Data assimilation Compute intensive post -processing Simulation results Data from sensors Data mining Long-term storage In-situ analysis loop 3 Simulation data storage From «Les big data à découvert», CNRS Éditions, 2017 Data extraction Data refinement
4 Where we are now Borrowed to Dan Reed (BDEC 2018 presentation) 4
5 Today: GAFAM Market Dominated Borrowed to Dan Reed (BDEC 2018 presentation) 5
6 Outline of the Talk Aspects of the paradigm shift Petascale to Exascale Supporting Complex Scientific Workflows Addressing the paradigm shift in Disruptive technology SME analysis Analyzing our ecosystem Conclusion & lessons learnt 6
7 Aspects of the Paradigm Shift Petascale to Exascale 7
8 Petascale to Exascale Petascale to Exascale transition is raising many issues Not only related to technology Not happening in isolation In a context of scientific (observational) data deluge Well summarized in the USA National Strategic Computing Initiative (NSCI) NSCI seeks to drive the convergence of compute-intensive and data-intensive systems We are potentially on a paradigm change denoted Exascale but meaning computing generation transition 8
9 Petascale to Exascale cont. Peta-Exa transition is not similar to Tera-Peta transition 9 This is a disruption mainly due to parallel model issues (compute and IO) And the need to deal with large amounts of data from multiple sources (scientific instruments, simulations) Some questions are Can one platform fit all? Is the Cloud a relevant solution? How to move data around (or not)? How to integrate Big Data technologies? How to manage resources?
10 Why Peta-Exa is Not Similar to Tera-Peta Transition? The main Tera-Peta transition was performed before during the Giga-Tera transition Adaption of codes to distributed memory machines Tera to Peta was smooth and with minimum (side-) effects for most HPC users Data issue is changing the game for Peta-Exa New software stack and algorithms Questions the discovery process (e.g The Fourth Paradigm) Data analytics and machine learning Data localization 10
11 What Exascale is Not Exascale == flops of interest for a small community Such as LQCD and field based on embarrassingly parallel methods (e.g. Monte-Carlo) Exascale transition for most people is not about the next increment in machine features The next generation of machines is likely to create a practice and organization disruption It is easy to compute anywhere (c.f. PRACE) but moving data around is (very) slow, if feasible Adherence to a system (including storage and networking) is likely to increase 11
12 Exascale-Wise Applications Characterization* 1. Workload 2. Workflow 3. Code 4. Scalability 5. Operating System 6. I/O 7. HPC Community 8. Hardware 9. Visualization 10.Interactivity 11.Data management and analysis 12.Impact on Science/Society *Computer science point of view 12
13 Exascale Transition Impact on Codes Tera-to-Peta Peta-to-Exa Off-the-Shelf ISV in charge Not addressed (Market?) In-House Languages Update of the codes, but no significant effort compare to Giga-to-Tera Fortran, C/C++, OpenMP, Cuda, OpenACC, OpenCL Too many technologies for an in-house team. Will need to add software engineers, etc. Fortran, C/C++, OpenMP, OpenACC, OpenCL, DSL, interpreted languages, task support, Runtime Accelerator support Runtime must handle more resources Sustainability No significant changes More specialized codes (e.g. DSL), code architecture rendered obsolete Complexity Portability Code refactoring to make it accelerator friendly Not simple, but achievable with careful design Heterogeneous software stack to address the data and task management Very dependent on workflow management and application architectures Performance Retuning (expensive in some cases) possible Tuning is going to be Hell (too many dimensions), energy tuning?* 13 *1w/year 1, 10% of 20MW/Y 2MW/Y 2M /Y ~20 persons/y
14 Exascale Transition Impact Example with Workflows Tera-to-Peta Peta-to-Exa Complexity Code coupling More multiphysics, multiphase models, data assimilations, data analytics, edge computing, Heterogeneity Mostly homogeneous Mix of data analytics and simulation, heterogeneous bricks Localization All in one system Data may come from large scientific instruments, or a large number of small instruments I/O constrained Solvable issue Cannot move the data around, not sure it can be solved Allocation Batch mostly Batch, interactive (guided simulation and analysis), (soft) real-time* (visualization, ) *Big data assimilation for Extreme-scale NWP, Takemasa Miyoshi 14
15 Aspects of the Paradigm Shift Supporting Complex Scientific Workflows 15
16 Combining Edges, Data Centers, Supercomputers-1 Complex workflow and data logistic to map onto the set of systems Bottleneck frontiers The edge Intermediate nodes (CDN, data centers, etc.) Strongly coupled node (Supercomputers, data centers, etc.) How to manage/program applications uniformly across systems? 16
17 Combining Edges, Data Centers, Supercomputers-2 Function of a system node is by destination not by nature Energy / throughput tradeoff, compute vs. communicate Bandwidth and latency between nodes can vary Interoperability is the goal A supercomputer node is not different from an edge node (capabilities only differ) A supercomputer is defined by a set of nodes that are strongly connected by high bandwidth, low latency links Interoperability between nodes helps to create complex workflows that includes all sorts of tasks (i.e. sensing, simulation, analysis, visualization) There are no frontiers between the core supercomputers and their edges or intermediate nodes or the storage nodes Complex workflow can be distributed in a uniform way Storage is just high capacity (e.g. NVM) reliable nodes 17
18 Workflow Model as a Spanning Layer Allows for optimizing cost, latencies, energy and QoS for complex workflows Need a user model What is a user? Can a user have a global credential? How do you link users and resources? Require an extended resource management model Compute, storage, network Composition rules (e.g. synchronizations) Security and privacy Should have a common meta-data referential Data localization, origin, replication, Should apply to all (sets of) nodes 18
19 An Example of Workflow: Air Quality Measurement and Analysis (Including Urgent Computing / closed-loops) New users / applications Storage heterogeneity Communication heterogeneity Computation heterogeneity CPU/hours per simulated day (not an exascale issue) 19 Current AQMO project in Rennes, FR
20 Going Beyond: Incremental Progress Very difficult to extend current infrastructure concepts to fit the future needs Sources of data are growing very fast (in and outside the HPC community) Many future applications rely on complex distributed workflows Conservatism / conflicts of interests of stakeholders is an issue Global end-to-end performance should be the focus With the assumption that data cannot be moved around but need to be accessed from anywhere 20
21 Addressing the Paradigm Shift in 21
22 Addressing the Paradigm Shift in Disruptive technology Understanding which technologies may disrupt practices SME analysis in HPC, how/can SMEs create more economical value? Analyzing our ecosystem What should be changed at ecosystem level? 22
23 Disruptive Technologies Phase 1: analysis of three cross-cutting issues in conjunction with nine disruptive innovation strategies and for each of them proposes recommendations (e.g. NVM, Byte addressable I/O) Phase 2: Focus on Quantum Computing - Promote the use of high-end HPC systems of the PRACE infrastructure to emulate QC and provide tool and environment to allow developer to run and develop applications on the QC emulator - Hire expert people on QC from top institutions and train HPC people by visiting exchanges and other instruments A 2014 prototype of a Google qubit (0.6 cm by 0.6 cm) known as a transmon 1, based on superconducting circuits. From aps.org. Google's quantum computing test will use 49 updated versions of these qubits. - Propose coordination actions at the European level 23
24 Addressing the Paradigm Shift in Disruptive technology SME analysis Understanding our ecosystem 24
25 EU projects as cradle for new technologies and start-ups Supportive environment Partnership already in place (project consortium) Shared risk (via EU financing) Mont-Blanc 1-3 Deep/Deeper/ Deepest Kaleao and Zeropoint Technologies (emerged from Euroserver project) but nevertheless * Projects reported only on very few pieces of technology * Projects seem not aware of existing help for start-ups, nor much sensibility for helping SMEs of their project Only few submissions to FET Launchpad calls * Survey amonst the CoEs and FETHPC projects in March
26 Input from SMEs and start-ups Goal Get the perception of SMEs developing technologies and start-ups on the market, hurdles, specific problems -> via interviews (15) Outcome 1. Reluctance to innovation on the market We don t say its novel HPC centres need above all to comply with their clients needs 2. Difficult to get into the market No one ever got fired for buying intel Pre-condition: have been already part of a top-500 machine Circumvent HPC: penetrate market via applications or via similar markets 26
27 Input from SMEs and start-ups (cont.) 3. Public procurement Financial requirements for bidding more difficult to meet for an SME than for a large company Need for pre-financing can hinder SMEs form bidding Procurement schemes such as PPI not much used 4. Connection to the ecosystem (e.g. via EU projects): important but financially difficult for SME ( we cannot spare 0.5 ETP for a project ) 27
28 SME Recommendation Example R6: Unlocking innovations in EU-projects by stimulating projects spin-off in order to benefit of the existing collaboration (within a running R&I project) and by redirecting funds of the R&I project towards a spin off for exploiting Cupboard IP 28
29 Addressing the Paradigm Shift in Disruptive technology SME analysis Analyzing our ecosystem 29
30 An Ecosystem Cartography (-wise) Showing impact on the Ecosystem How do we connect stakeholders Graph representation Two types of nodes Events that generate a common production SME workshop SRA, PSC, EsD BDEC 2017 Technical Workshops Stakeholders, CoE, FET HPC Edges represent the participate to relationships PSC Cerfacs Eocoe 30
31 Entities Active in Related Activities About 80 entities 31
32 A Map of the Ecosystem as Connected by Includes about 260 entities 32
33 Main Conclusion on the Ecosystem Focus and organize the current efforts in a way that is closer to an integrated industrial project in order to ensure a successful delivery of European Exascale level sustainable systems capable of serving a convergence based scientific discovery process 33
34 Conclusion and Lessons Learnt 34
35 Conclusion and Lessons Learnt 1. HPC is experiencing a paradigm shift HPC vision has changed dramatically since the beginning of 2. The ecosystem is getting wider and more heterogeneous 1. BDEC, Big Data, Cloud, IoT, 2. HPC a strategic tiny part of it 3. And will have to evolve at high speed 3. Difficulties for the emergence of EU HPC SMEs and startups still need a proper response 4. EU R&D organization can still be improved 35
36 Conclusion and Lessons Learnt Exascale transition is a holistic issue that Cannot ignore the data issues Nor the market structure / GAFAM domination EuroHPC the main EU vehicle toward Exascale More EU technologies in HPC systems? Pre-Exascale systems first EU Exascale systems 2019 China, 2021/2022 Japan and US -2 will continue -1 s work 36
37 FEAT Future Emerging Art and Technology Initiative supported by the commission, the artists engaging with the HPC projects participated to one workshop The semiotic of supercomputers (2017), Špela Petrič and Miha Turšič
38 Backup slides 38
39 Understanding our Ecosystem (-wise) How does the Ecosystem contributes to the recommendations? What is the coverage of actions? What type of stakeholders do we have? 39
40 Innovation, SMEs, start-ups and tech transfer Glimpse at the ecosystem (european level) In : A. Get input form the community 1. From the projects (FETHPC and CoEs) 2. From SMEs and start-ups B. What can we do on ecosystem level C. Outlook 40
41 SME Recommendations R1: SME should team up with main bidder for big procurement is encouraged as a way to go especially for large procurement R2: HPC centres should have innovation oriented projects and HPC systems R3: The SME instrument should be better promoted amongst the HPC community and if necessary better adapted to the HPC sector R4: Mechanism to build trust and personal relationship amongst SMEs and Start ups should be encouraged R5: Partnership of SMEs/Start ups with HPC centres and large vendors shall be encouraged 41
the EU framework programme for research and innovation
High Performance Computing First Horizon 2020 Calls (2014-2015) Dr Panagiotis Tsarchopoulos Future and Emerging Technologies DG CONNECT European Commission the EU framework programme for research and innovation
More informationExtreme scale Demonstrators - state of discussion -
Extreme scale Demonstrators - state of discussion - EXDCI workshop Barcelona, Sept. 21 st 22 nd 2016 Thomas Eickermann Marc Duranton September 21-22, 2016 The EXDCI project has received funding from the
More informationEXDCI EXDCI. European extreme Data and Computing Initiative
EXDCI European Extreme Data and Computing Initiative EXDCI European extreme Data and Computing Initiative Sergi Girona Project Coordinator PRACE Chair of the Board of Directors François Bodin Scientific
More informationPercipient StorAGe for Exascale Data Centric Computing Project Summary and Status
Percipient StorAGe for Exascale Data Centric Computing Project Summary and Status Sai Narasimhamurthy Seagate Systems UK ExaIO Workshop SC 16 - Nov 2016 Per-cip-i-ent (pr-sp-nt) Adj. Having the power of
More informationHigh Performance Computing (HPC) and Quantum Technologies in work programmes
High Performance Computing (HPC) and Quantum Technologies in work programmes 2018-2020 Roma, 20 th November 2017 Andrea Feltrin High Performance Computing and Quantum Technologies DG CONNECT European Commission
More informationEuroHPC Joint Undertaking &
EuroHPC Joint Undertaking & cppp ETP4HPC Gustav Kalbe Head of Unit, High Performance Computing & Quantum Technologies DG CONNECT, European Commission HPC status in Europe today EU has no top ranked supercomputers
More informationHigh-Performance Computing in Horizon Dr Panagiotis Tsarchopoulos Future and Emerging Technologies DG CONNECT European Commission
High-Performance Computing in Horizon 2020 Dr Panagiotis Tsarchopoulos Future and Emerging Technologies DG CONNECT European Commission HPC: What for? Weather, Climate & Earth Sciences Bio/Life Sciences
More informationPerformance Optimization and Productivity
Performance Optimization and Productivity EU H2020 Center of Excellence (CoE) 1 October 2015 31 March 2018 (30 months) POP CoE A Center of Excellence On Performance Optimization and Productivity Promoting
More informationDEPEI QIAN. HPC Development in China: A Brief Review and Prospect
DEPEI QIAN Qian Depei, Professor at Sun Yat-sen university and Beihang University, Dean of the School of Data and Computer Science of Sun Yat-sen University. Since 1996 he has been the member of the expert
More informationETP4HPC. PRACE Industrial seminar Bologna, April 16th 2012
ETP4HPC PRACE Industrial seminar Bologna, April 16th 2012 What is an European Technology Platform? ETP is an industry led forum ETPs provide a framework for stakeholders, led by industry, to define research
More informationChallenges in Application Scaling In an Exascale Environment
Challenges in Application Scaling In an Exascale Environment 14 th Workshop on the Use of High Performance Computing In Meteorology November 2, 2010 Dr Don Grice IBM Page 1 Growth of the Largest Computers
More informationJuly, 10 th From exotics to vanillas with GPU Murex 2014
July, 10 th 2014 From exotics to vanillas with GPU Murex 2014 COMPANY Selected Industry Recognition and Rankings 2013-2014 OVERALL #1 TOP TECHNOLOGY VENDOR #1 Trading Systems #1 Pricing & Risk Analytics
More informationThe Internet of Everything and the Research on Big Data. Angelo E. M. Ciarlini Research Head, Brazil R&D Center
The Internet of Everything and the Research on Big Data Angelo E. M. Ciarlini Research Head, Brazil R&D Center A New Industrial Revolution Sensors everywhere: 50 billion connected devices by 2020 Industrial
More informationETP4HPC European Technology Platform for High-Performance Computing. Strategic Research Agenda 2015 Update
ETP4HPC European Technology Platform for High-Performance Computing Strategic Research Agenda 2015 Update European Technology Multi-annual Roadmap Towards Exascale Update to 2013 Roadmap Supported by
More informationCHALLENGES OF EXASCALE COMPUTING, REDUX
CHALLENGES OF EXASCALE COMPUTING, REDUX PAUL MESSINA Argonne National Laboratory May 17, 2018 5 th ENES HPC Workshop Lecce, Italy OUTLINE Why does exascale computing matter? The U.S. DOE Exascale Computing
More informationBringing AI Into Your Existing HPC Environment,
Bringing AI Into Your Existing HPC Environment, and Scaling It Up Introduction 2 Today s advancements in high performance computing (HPC) present new opportunities to tackle exceedingly complex workflows.
More informationEconomic and management challenges and needs of computational resource providers and industry partners
Economic and management challenges and needs of computational resource providers and industry partners Chair: Dan Reed (Microsoft Research) Secretary: Jean François Lavignon (Bull) IESP Workshop 2, June
More informationH2020-FETHPC Coordination of the HPC strategy EXDCI. European extreme Data and Computing Initiative. Grant Agreement Number: FETHPC
H2020-FETHPC-2014 Coordination of the HPC strategy EXDCI European extreme Data and Computing Initiative Grant Agreement Number: FETHPC-671558 D2.2 ETP4HPC Strategic Research Agenda V3 Final Version: 0.3
More informationPerformance Optimisation and Productivity. EU H2020 Centre of Excellence (CoE) 1 October March 2018 Grant Agreement No
Performance Optimisation and Productivity Nick Dingle nick.dingle@nag.co.uk EU H2020 Centre of Excellence (CoE) 1 October 2015 31 March 2018 Grant Agreement No 676553 Motivation Why? Complexity of machines
More informationMont-Blanc work Past, present & future
montblanc-project.eu @MontBlanc_EU Mont-Blanc work Past, present & future Etienne WALTER, Project manager (Bull/Atos) Coordinator of Mont-Blanc phase 3 This project has received funding from the European
More informationresearch & development HPC & cloud project management innovations web & mobile solutions
HPC & cloud research & development project management web & mobile solutions innovations 4PM - more than just project management software Introducing 4PM 4PM brings the power of portfolio project management
More informationAddressing the I/O bottleneck of HPC workloads. Professor Mark Parsons NEXTGenIO Project Chairman Director, EPCC
Addressing the I/O bottleneck of HPC workloads Professor Mark Parsons NEXTGenIO Project Chairman Director, EPCC I/O is key Exascale challenge Parallelism beyond 100 million threads demands a new approach
More informationThe High Performance Computing strategy and the European Cloud Initiative HPC User Forum September 5-7, 2017 Milwaukee, USA
The High Performance Computing strategy and the European Cloud Initiative HPC User Forum September 5-7, 2017 Milwaukee, USA Leonardo Flores Añover Senior Expert - HPC and Quantum technologies DG CONNECT
More informationA2L2: an Application Aware Flexible HPC Scheduling Model for Low-Latency Allocation
A2L2: an Application Aware Flexible HPC Scheduling Model for Low-Latency Allocation Gonzalo P. Rodrigo - gonzalo@cs.umu.se P-O Östberg p-o@cs.umu.se Lavanya Ramakrishnan lramakrishnan@lbl.gov Erik Elmroth
More informationPeter Ungaro President and CEO
Peter Ungaro President and CEO We build the world s fastest supercomputers to help solve Grand Challenges in science and engineering Earth Sciences CLIMATE CHANGE & WEATHER PREDICTION Life Sciences PERSONALIZED
More informationIBM Accelerating Technical Computing
IBM Accelerating Jay Muelhoefer WW Marketing Executive, IBM Technical and Platform Computing September 2013 1 HPC and IBM have long history driving research and government innovation Traditional use cases
More informationPRACE Europe goes HPC. Achim Bachem, Forschungszentrum Jülich Amsterdam, September , Europe goes HPC
PRACE Europe goes HPC Achim Bachem, Forschungszentrum Jülich Amsterdam, September 3 2008, Europe goes HPC HPC is a Key Technology Supercomputers are the tool for solving most challenging problems through
More informationHigh-Performance Computing (HPC) Up-close
High-Performance Computing (HPC) Up-close What It Can Do For You In this InfoBrief, we examine what High-Performance Computing is, how industry is benefiting, why it equips business for the future, what
More informationDelivering High Performance for Financial Models and Risk Analytics
QuantCatalyst Delivering High Performance for Financial Models and Risk Analytics September 2008 Risk Breakfast London Dr D. Egloff daniel.egloff@quantcatalyst.com QuantCatalyst Inc. Technology and software
More informationEnergy Oriented Center of Excellence
Energy Oriented Center of Excellence Edouard Audit, EoCoE Project Coordinator SC18 conference, Dallas European HPC strategy PRACE ETP4HPC CoEs CEA s Scientific council November 30 & December 1 st, 2015
More informationIn-Memory Analytics: Get Faster, Better Insights from Big Data
Discussion Summary In-Memory Analytics: Get Faster, Better Insights from Big Data January 2015 Interview Featuring: Tapan Patel, SAS Institute, Inc. Introduction A successful analytics program should translate
More informationThingsExpo New York June 2016
Edge Computing: The Next Frontier for the IoT Business Landscape Edge/Persisted Storage, Governance, and Market Drivers Considerations and Limitations of Centralized Data Lakes ThingsExpo New York June
More informationDRAFT ENTERPRISE TECHNICAL REFERENCE FRAMEWORK ETRF WHITE PAPER
DRAFT ENTERPRISE TECHNICAL REFERENCE FRAMEWORK ETRF WHITE PAPER CONTENTS CONTENTS... 0 INTRODUCTION... 1 VISION AND OBJECTIVES... 1 ARCHITECTURE GUIDING PRINCIPLES... 1 ENTERPRISE TECHNICAL REFERENCE FRAMEWORK
More informationHLRS. The High Performance Computing. Center Stuttgart
Cloud Computing The best of both worlds: Conducting compute-intensive HPC applications in a highly flexible cloud environment with low access barriers. HLRS High Performance Computing Center Stuttgart
More informationSRA 2 and 3, EsD-status EXDCI technical workshop, 21 st September 2016, Barcelona
SRA 2 and 3, EsD-status EXDCI technical workshop, 21 st September 2016, Barcelona The EXDCI project has received funding from the European Unions Horizon 2020 research and innovation programmed under the
More informationFOR CSPs, IoT-ENABLEMENT SERVICES CAN ACCELERATE REVENUE GROWTH
NOVEMBER 2017 FOR CSPs, IoT-ENABLEMENT SERVICES CAN ACCELERATE REVENUE GROWTH 2017 TECHNOLOGY BUSINESS RESEARCH, INC. TABLE OF CONTENTS 3 Introduction Still early days 4 Early IoT adopters face challenges
More informationThe Canadian Digital Supercluster. Overview Presentation October 25, 2017
The Canadian Digital Supercluster Overview Presentation October 25, 2017 1 Data is absolutely the right opportunity at the right time for our ecosystem 2 1. Data is a Growing Resource 1011 0010 0.5% 2.5
More information2014 SAP SE or an SAP affiliate company. All rights reserved. 1
2014 SAP SE or an SAP affiliate company. All rights reserved. 1 Simplifying Digital Transformation Ameet Hundekari Program Manager (Innovations),GB&E, SAP MENA September 2015 We are entering into a new
More informationHandbook on Summaries of European Exascale Projects
Uhttps://exdci.eu/collaboration/coe Handbook on Summaries of European Exascale Projects EXDCI Summaries: 30TUhttps://exdci.eu/collaboration/fethpcU Uhttps://exdci.eu/collaboration/exascale-projects U 30TUhttp://cordis.europa.eu/search/result_en?q=contenttype=%27project%27%20AND%20/project/relations/associations/relatedCall/call/identifier=%27H2020-FETHPC-
More informationALCF SITE UPDATE IXPUG 2018 MIDDLE EAST MEETING. DAVID E. MARTIN Manager, Industry Partnerships and Outreach. MARK FAHEY Director of Operations
erhtjhtyhy IXPUG 2018 MIDDLE EAST MEETING ALCF SITE UPDATE DAVID E. MARTIN Manager, Industry Partnerships and Outreach Argonne Leadership Computing Facility MARK FAHEY Director of Operations Argonne Leadership
More informationSimplifying Hadoop. Sponsored by. July >> Computing View Point
Sponsored by >> Computing View Point Simplifying Hadoop July 2013 The gap between the potential power of Hadoop and the technical difficulties in its implementation are narrowing and about time too Contents
More informationAdvanced Information Systems Big Data Study for Earth Science
Advanced Information Systems Big Study for Earth Science Daniel Crichton, NASA Jet Propulsion Laboratory Michael Little, NASA Headquarters October 29, 2015 Background NASA has historically focused on systematic
More informationWebinar IMI2 Call 14 Development of a platform for federated and privacy-preserving machine learning in support of drug discovery
Webinar IMI2 Call 14 Development of a platform for federated and privacy-preserving machine learning in support of drug discovery 16 March 2018 Agenda How to use GoToWebinar Catherine Brett, IMI Introduction
More informationThe recipe for hyperfast DevOps instrumentation. An e-guide to infrastructure as code
The recipe for hyperfast DevOps instrumentation An e-guide to infrastructure as code Why take infrastructure out of the physical world? Up to now, setting up instrumentation for new projects was a time-consuming
More informationBuilding a Multi-Tenant Infrastructure for Diverse Application Workloads
Building a Multi-Tenant Infrastructure for Diverse Application Workloads Rick Janowski Marketing Manager IBM Platform Computing 1 The Why and What of Multi-Tenancy 2 Parallelizable problems demand fresh
More informationThe IoT Solutions Space: Edge-Computing IoT architecture, the FAR EDGE Project John Professor Athens Information
The IoT Solutions Space: Edge-Computing IoT architecture, the FAR EDGE Project John Soldatos (jsol@ait.gr, @jsoldatos), Professor Athens Information Technology Contributor: Solufy Blog (http://www.solufy.com/blog)
More informationDeliverable 1.2 Detailed risk management plan
Deliverable 1.2 Detailed risk management plan Date: November 2016 HORIZON 2020 - INFRADEV Implementation and operation of cross-cutting services and solutions for clusters of ESFRI Page 1 of 16 Grant agreement
More informationHPC Trends for Addison Snell
HPC Trends for 2015 Addison Snell addison@intersect360.com A New Era in HPC Supercomputing for U.S. Industry Report by U.S. Council on Competitiveness Justifications for new levels of supercomputing for
More informationHETEROGENEOUS SYSTEM ARCHITECTURE: FROM THE HPC USAGE PERSPECTIVE
HETEROGENEOUS SYSTEM ARCHITECTURE: FROM THE HPC USAGE PERSPECTIVE Haibo Xie, Ph.D. Chief HSA Evangelist AMD China AGENDA: GPGPU in HPC, what are the challenges Introducing Heterogeneous System Architecture
More informationDigitization in the Process Industries through the SPIRE PPP
Strengthening Leadership in Digital Technologies and in Digital Industrial Platforms Digitization in the Process Industries through the SPIRE PPP Most reports indicate that the process industry is about
More informationBusiness Insight at the Speed of Thought
BUSINESS BRIEF Business Insight at the Speed of Thought A paradigm shift in data processing that will change your business Advanced analytics and the efficiencies of Hybrid Cloud computing models are radically
More informationCenter for Scalable Application Development Software: Center Overview. John Mellor-Crummey (Rice)
Center for Scalable Application Development Software: Center Overview John Mellor-Crummey (Rice) CScADS Midterm Review April 22, 2009 1 Project Co-PIs and Senior Personnel John Mellor-Crummey, Keith Cooper
More informationInnovation Without Limits. Your Guide to High Performance Computing in the Cloud
Innovation Without Limits Your Guide to High Performance Computing in the Cloud 4 5 6 7 8 10 12 What Could You Accomplish with a Million Cores? Access Resources Quickly Leverage Latest Technology Collaborate
More informationCOMMISSION STAFF WORKING DOCUMENT IMPACT ASSESSMENT. Accompanying the document. Proposal for a Council Regulation
EUROPEAN COMMISSION Brussels, 11.1.2018 SWD(2018) 6 final PART 3/4 COMMISSION STAFF WORKING DOCUMENT IMPACT ASSESSMENT Accompanying the document Proposal for a Council Regulation on establishing the European
More informationDatametica. The Modern Data Platform Enterprise Data Hub Implementations. Why is workload moving to Cloud
Datametica The Modern Data Platform Enterprise Data Hub Implementations Why is workload moving to Cloud 1 What we used do Enterprise Data Hub & Analytics What is Changing Why it is Changing Enterprise
More informationAmsterdam. Accelerate digital transformation with the cloud for smarter business. Reimagining applications & data for growth and innovation
Accelerate digital transformation with the cloud for smarter business Amsterdam Reimagining applications & data for growth and innovation Andrew Brown Vice President IBM Cloud Software Europe @AndyBrown74
More informationPartnering with the business to create a successful self-service analytics framework
Partnering with the business to create a successful self-service analytics framework Times are changing; the evolution of an agile but controlled approach to BI It s widely known that the landscape of
More informationHPC in the Cloud: Gompute Support for LS-Dyna Simulations Bamberg, Germany
Gompute Turbo Pack HPC in the Cloud: Gompute Support for LS-Dyna Simulations Bamberg, Germany 11-10-2016 Iago Fernandez Cloud Sales Director Gompute Iago.fernandez@gompute.com What is Gompute? HPC since
More informationOil reservoir simulation in HPC
Oil reservoir simulation in HPC Pavlos Malakonakis, Konstantinos Georgopoulos, Aggelos Ioannou, Luciano Lavagno, Ioannis Papaefstathiou and Iakovos Mavroidis PRACEdays18 This project has received funding
More informationApplication Migration to Cloud Best Practices Guide
GUIDE JULY 2016 Application Migration to Cloud Best Practices Guide A phased approach to workload portability Table of contents Application Migration to Cloud 03 Cloud alternatives Best practices for cloud
More informationMaturing IoT solutions with Microsoft Azure. Glenn Colpaert Azure/IoT Domain
Maturing IoT solutions with Microsoft Azure Glenn Colpaert Azure/IoT Domain Lead @GlennColpaert Who we are 2000 Belgium 2004 France 2013 Portugal 2016 Switzerland 2016 UK 2016 The Netherlands 2017 Malta
More informationExascale Challenges. Dan Reed Corporate Vice President Extreme Computing Group &
Exascale Challenges reed@microsoft.com www.hpcdan.org Dan Reed Corporate Vice President Extreme Computing Group & Technology Strategy and Policy Roadmap For The Next 20 Minutes The challenges of exascale
More informationServices Guide April The following is a description of the services offered by PriorIT Consulting, LLC.
SERVICES OFFERED The following is a description of the services offered by PriorIT Consulting, LLC. Service Descriptions: Strategic Planning: An enterprise GIS implementation involves a considerable amount
More informationHEP Center for Computational Excellence
HEP Center for Computational Excellence Presented to JLAB Computing Round Table Salman Habib for Kerstin Kleese van Dam, Peter Nugent, and Rob Roser LSST CERN Data Center LHC DUNE HEP Computing Frontier
More informationENA-HPC. International Conference on Energy-Aware High Performance Computing September 07 09, 2011 Hamburg. Christian Bischof
Brainware for Green HPC ENA-HPC International Conference on Energy-Aware High Performance Computing September 07 09, 2011 Hamburg Christian Bischof christian.bischof@tu-darmstadt.de Dieter an Mey, Christian
More informationPlease note. The development, release, and timing of any future features or functionality described for our products remains at our sole discretion.
Please note IBM s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice and at IBM s sole discretion. Information regarding potential future products
More informationAgile Computing on Business Grids
C&C Research Laboratories NEC Europe Ltd Rathausallee 10 D-53757 St Augustin Germany Junwei Cao Agile Computing on Business Grids An Introduction to AgileGrid June 2003 Agile Computing on Business Grids
More informationCompliance digitalization The impact on the Compliance function. Deloitte Risk Services April 2016
Compliance digitalization The impact on the Compliance function Deloitte Risk Services April 2016 2 Contents Preface 5 Management summary 6 Effects of digitalization 7 Using data in the compliance function
More informationPower measurement at the exascale
Power measurement at the exascale Nick Johnson, James Perry & Michèle Weiland Nick Johnson Adept Project, EPCC nick.johnson@ed.ac.uk Motivation The current exascale targets are: One exaflop at a power
More informationTop 5 Challenges for Hadoop MapReduce in the Enterprise. Whitepaper - May /9/11
Top 5 Challenges for Hadoop MapReduce in the Enterprise Whitepaper - May 2011 http://platform.com/mapreduce 2 5/9/11 Table of Contents Introduction... 2 Current Market Conditions and Drivers. Customer
More informationTDWI Analytics Fundamentals. Course Outline. Module One: Concepts of Analytics
TDWI Analytics Fundamentals Module One: Concepts of Analytics Analytics Defined Data Analytics and Business Analytics o Variations of Purpose o Variations of Skills Why Analytics o Cause and Effect o Strategy
More informationBuilding Big Data Processing Systems under Scale-Out Computing Model
Keynote I Building Big Data Processing Systems under Scale-Out Computing Model Xiaodong Zhang Robert M. Critchfield Professor in Engineering Department of Computer Science and Engineering The Ohio State
More informationDigital Manufacturing Services
Digital Manufacturing Services Helping to steer your digital transformation journey to smart, connected products and plants, while keeping your mobility, connectivity, analytics and cloud solutions inherently
More informationBare-Metal High Performance Computing in the Cloud
Bare-Metal High Performance Computing in the Cloud On June 8, 2018, the world s fastest supercomputer, the IBM/NVIDIA Summit, began final testing at the Oak Ridge National Laboratory in Tennessee. Peak
More informationUpdate on SAP Leonardo IoT. 8 th June 2017
Update on SAP Leonardo IoT 8 th June 2017 Market Trends Digital Transformation New forms of Systems of Intelligence emerging Artificial Intelligence & Machine Learning, IoT, Insights By 2018, 75% of enterprise
More informationThe Agile IoT Project
WHAT IS AGILE IOT The Agile IoT Project AGILE is the acronym for Adaptive Gateways for diverse multiple Environments The main concept behind AGILE is to enable users to easily build IoT applications and
More informationSmart Manufacturing The Case for an Open Architecture Platform Energy Productivity Management
Smart Manufacturing The Case for an Open Architecture Platform Energy Productivity Management ACEEE 2014 Smart Manufacturing Leadership Coalition (SMLC) Jim Davis, Vice Provost IT & CTO, UCLA https://smartmanufacturingcoalition.org
More informationNIST Big Data Reference Architecture for Analytics and Beyond Wo Chang Digital Data Advisor December 8, 2017
NIST Big Data Reference Architecture for Analytics and Beyond Wo Chang Digital Data Advisor wchang@nist.gov December 8, 2017 1 Agenda Computing Trend Exascale HW available soon Computing Trend Current
More informationLeading a Successful DevOps Transition Lessons from the Trenches. Randy Shoup Consulting CTO
Leading a Successful DevOps Transition Lessons from the Trenches Randy Shoup Consulting CTO What Is DevOps? Continuous Delivery? Rapid cycle times Automated testing and Continuous Integration Deployment
More informationThe Modular Supercomputer Architecture and its application in HPC and HPDA
The Modular Supercomputer Architecture and its application in HPC and HPDA Damian Alvarez Jülich Supercomputing Centre, JSC (Germany) The DEEP Projects Research & innovation projects co-funded by the European
More informationApiOmat. Case Study. Challenge
Case Study SUSE CaaS Platform SUSE Cloud Application Platform In today s digital world, we expect to be able to do everything on our smartphones. makes it quicker and easier for enterprises to develop
More informationBuilding Intelligence: The New BI
Building Intelligence: The New BI Applying Business Intelligence/BI Best Practices to Multi-site Retail E360 Annual Conference Atlanta, Ga. April 11 & 12 Paul Hepperla Vice President, North American Solutions
More informationTech McKinsey Digital Labs
Tech Recruiting @ McKinsey Digital Labs Digital reinvention is an urgent need Digital is changing how customers behave, and these behaviors are changing the nature of businesses There is an opportunity
More informationNSF Future of High Performance Computing. Bill Kramer
NSF Future of High Performance Computing Bill Kramer Why Sustained Performance is the Critical Focus Memory Wall Limitation on computation speed caused by the growing disparity between processor speed
More informationAccelerating Your Big Data Analytics. Jeff Healey, Director Product Marketing, HPE Vertica
Accelerating Your Big Data Analytics Jeff Healey, Director Product Marketing, HPE Vertica Recent Waves of Disruption IT Infrastructu re for Analytics Data Warehouse Modernization Big Data/ Hadoop Cloud
More informationWhite paper A Reference Model for High Performance Data Analytics(HPDA) using an HPC infrastructure
White paper A Reference Model for High Performance Data Analytics(HPDA) using an HPC infrastructure Discover how to reshape an existing HPC infrastructure to run High Performance Data Analytics (HPDA)
More informationTHE CASE FOR CONNECTED MANUFACTURING
THE CASE FOR CONNECTED MANUFACTURING TABLE OF CONTENTS 1 Executive overview 2 A state of emerging opportunities 3 The infrastructure as-is and the infrastructure to-be 3 The transformational challenge
More informationCray Earth Sciences Update. Phil Brown Earth Sciences Segment Leader icas, 17 th September 2015, Annecy
Cray Earth Sciences Update Phil Brown philipb@cray.com Earth Sciences Segment Leader icas, 17 th September 2015, Annecy Topics Cray s Presence in Earth System Modelling Community Emerging Trends in Weather
More informationAbout
@_OpalPerry About Allstate @_OpalPerry We are the Good Hands. We restore customers lives after the unexpected happens @_OpalPerry We are the Good Hands: We help customers realize their hopes and dreams
More informationQuick Start with AI for Businesses
Quick Start with AI for Businesses ML Conference 2018, Dr. Ulrich Bodenhausen, AI Coach V1.0 2018-06-12 About me PhD in Machine Learning from KIT. Application of neural networks to speech and gesture recognition
More informationEMC2 Workshop: The S3P project. Paris, Sept, 28th, 2016
EMC2 Workshop: The S3P project Paris, Sept, 28th, 2016 1 2016 Embedded France 24 February 2016 2 2016 Embedded France 24 February 2016 Our Focus S3P Embedded Side Cloud/Analytics/Simulation Side Network
More informationDigitization within the Chemical Industry ECRN Event on Digitizing European Industry
Digitization within the Chemical Industry ECRN Event on Digitizing European Industry 22 March 2017 Martin Winter Profile of the EU Chemical Industry 29 000 companies, 96% SMEs 1.17 million of jobs 551
More informationDriven by Smart Data. The automotive industry and the cloud.
Driven by Smart Data The automotive industry and the cloud. Cloud survey report: Industry experts explore the current and planned cloud adoption strategies of senior IT professionals. Researched by 2 Introduction.
More informationCMS readiness for multi-core workload scheduling
CMS readiness for multi-core workload scheduling Antonio Pérez-Calero Yzquierdo, on behalf of the CMS Collaboration, Computing and Offline, Submission Infrastructure Group CHEP 2016 San Francisco, USA
More informationRESOLUTE project presentation
Co-funded by the European Union under H2020 DRS7 2014 Resilience management guidelines and Operationalization applied to Urban Transport Environment www.resolute-eu.org RESOLUTE project presentation Emanuele
More informationEngaging in Big Data Transformation in the GCC
Sponsored by: IBM Author: Megha Kumar December 2015 Engaging in Big Data Transformation in the GCC IDC Opinion In a rapidly evolving IT ecosystem, "transformation" and in some cases "disruption" is changing
More informationThe Manycore Shift. Microsoft Parallel Computing Initiative Ushers Computing into the Next Era
The Manycore Shift Microsoft Parallel Computing Initiative Ushers Computing into the Next Era Published: November 2007 Abstract When major qualitative shifts such as the emergence of the graphical user
More informationTETRACOM success story: technology transfer between ctuning foundation and ARM
TETRACOM success story: technology transfer between ctuning foundation and ARM Collective Knowledge: a framework for reproducible experimentation and optimization knowledge sharing We enable efficient,
More informationRealize Your Product Promise
Realize Your Product Promise ANSYS Enterprise Cloud is a complete simulation platform, delivered in your secure, dedicated environment on the public cloud. Complete and extensible, ANSYS Enterprise Cloud
More informationAIOTI ALLIANCE FOR INTERNET OF THINGS INNOVATION
Trends and opportunities for data-rich smart cities omar.elloumi@nokia.com WG08 Chairman 1 The development of the The Alliance for Internet of Things Innovation () was initiated by the European Commission
More information