1. The Mapper project receives funding from the EC's Seventh Framework Programme (FP7/2007-2013) under grant agreement n° RI-261507. Distributed Multiscale Computing, the MAPPER project Alfons Hoekstra, Krzysztof Kurowski, Carles Bona

2. 2 Our Vision Distributed Multiscale Computing... Strongly science driven, application pull...on existing and emerging European e- Infrastructures,...... and exploiting as much as possible services and software developed in earlier (EU-funded) projects. Strongly technology driven, technology push

3. 3 Nature is Multiscale Natural processes are multiscale 1 H 2 O molecule A large collection of H 2 O molecules, forming H-bonds A fluid called water, and, in solid form, ice.

4. 4 Multi-Scale modeling Scale Separation Map Nature acts on all the scales We set the scales And then decompose the multiscale system in single scale sub-systems And their mutual coupling temporal scale spatial scale ΔxΔx L ΔtΔt T

5. 5 From a Multi-Scale System to many Single-Scale Systems Identify the relevant scales Design specific models which solve each scale Couple the subsystems using a coupling method temporal scale spatial scale ΔxΔx L ΔtΔt T

6. 6 Why multiscale models? There is simply no hope to computationally track complex natural processes at their finest spatio-temporal scales. Even with the ongoing growth in computational power.

7. 7 Minimal demand for multiscale methods

8. 8 But what about multiscale computing? Inherently hybrid models are best serviced by different types of computing environments When simulated in three dimensions, they usually require large scale computing capabilities. Such large scale hybrid models require a distributed computing ecosystem, where parts of the multiscale model are executed on the most appropriate computing resource. Distributed Multiscale Computing

9. 9 Two Multiscale Computing paradigms Loosely Coupled One single scale model provides input to another Single scale models are executed once workflows Tightly Coupled Single scale models call each other in an iterative loop Single scale models may execute many times Dedicated coupling libraries are needed temporal scale spatial scale ΔxΔx L ΔtΔt T temporal scale spatial scale ΔxΔx L ΔtΔt T

10. 10 MAPPER Multiscale APPlications on European e-infRastructures (proposal number 261507) Project Overview University of Amsterdam Max-Planck Gesellschaft zur Foerderung der Wissenschaften E.V. University of Ulster Poznan Supercomputing and Networking Centre Akademia Gorniczo-Hutnicza im. Stanislawa Staszica w Krakowie Ludwig-Maximilians-Universität München University of Geneva Chalmers Tekniska Högskola University College London

11. 11 Motivation: user needs VPHFusionComputional Biology Material Science Engineering Distributed Multiscale Computing Needs

12. 12 Ambition Develop computational strategies, software and services for distributed multiscale simulations across disciplines exploiting existing and evolving European e-infrastructure Deploy a computational science infrastructure Deliver high quality components aiming at large-scale, heterogeneous, high performance multi-disciplinary multiscale computing. Advance state-of-the-art in high performance computing on e- infrastructures enable distributed execution of multiscale models across e-Infrastructures,

13. 13 MAPPER Roadmap October 1, 2010 – start of project Fast track deployment – first year of project Loosely and tightly coupled distributed multiscale simulations can be executed. Deep track deployment – second and third year More demanding loosely and tightly coupled distributed multiscale simulation can be executed Programming and access tools available Interoperability available

14. 14 Highlights year 1 7 applications from 5 scientific domains...... brought under a common generic multiscale computing framework virtual physiological human fusion hydrology nano material science computational biology SSMCoupling topology (x)MML Task graph Scheduling

15. 15 Highlights year 1 Application composition: from MML to executable experiment Application composition: from MML to executable experiment Registration of MML metadata: submodules and scales Result Management Result Management Execution of experiment using interoperability layer on e-infrastructure Execution of experiment using interoperability layer on e-infrastructure

16. 16 …… 20110609201220130811 MoU signed Taskforce established 1 st evaluation 05 1 st EU review selected two apps on MAPPER e-Infrastructure (EGI and PRACE resources) Tier - 2 Tier - 1 Tier - 0 MAPPER Taskforce Joint Taskforce between EGI, MAPPER, and PRACE Collaborate with EGI and PRACE to introduce new capabilities and policies onto e-Infrastructures thanks to QosCosGrid (QCG) and interoperability tools Deliver new application tools, problem solving environments and services to meet end-users needs Work closely with various end-users communities (involved directly in MAPPER) to perform distributed multiscale simulations and complex experiments

17. 17 e-Infrastructure Services Offered (Unicore, gLite): Interactive access Data management Job execution Post-processing, e.g. visualization New capabilities (will be hopefully around thanks to MAPPER): Advance reservation Co-allocation Cross-cluster coupling library and services – MUSCLE Cross-cluster MPI (QCG-OMPI) Workflow management and execution (parallel jobs are part of workflows), ongoing discussions with SHIWA

18. 18 Fast vs. Deep tracks components

19. 19 MAPPER software integration

20. 20 Interoperability and standards

21. 21 Interoperability and efficiency Example benchmarks of remote job submissions using the OGF SAGA testsuit and OGF BES interfaces supported by different middleware Note that QCG middleware supports also additional features, in particular Advance Reservation and co- allocation to synchronize in time access to distributed computing resources

22. 22 MAPPER e-Infrastructure (1 st review, November 2011) UCL Cyfronet SARA 10k + 10k +… 512 (no limit ;-) 124 (no limit ;-) CINECA PSNC LRZ/LMU

23. 23 DMC demonstrations Two applications scenarios operational loosely coupled DMC tightly coupled DMC

24. 24 Monitoring Provide information about availability and functionality of MAPPER services Nagios Hosted at LRZ Real-time service status Failure notification Statistics Integration with EGI and PRACE monitoring

25. 25 Policy documents Policy document, and dissemination of its content. Grid Computing – The Next Decade www.gridlab.orgGrid Computing – The Next Decade www.gridlab.org

26. 26 Invitation MAPPER Live Demonstration 15:30 – 16:00 Today Ground Floor FMI Next to EGI (MNM – Team)