Jf lavignon

Extreme Computing cooperation, standpoint of an industrial

JF Lavignon, Strategy & Cooperation, Innovative Products

2©Bull, 2011 Cooperation in extreme computing

Introduction

Sorry not to be present, hope to meet you soon

Agenda :

- HPC challenges as seen by a HPC supplier- Cooperation example and idea for

Latin America – Europe cooperation

3©Bull, 2011 Cooperation in extreme computing

HPC, strategic foundation for competitiveness, innovation and defense

Performance &Competitivity

Imagery - HealthArts & Sciences

InternetMultimedia & Virtual

HPC computing technologyHPC computing technology

Offering capabilities to design new products faster, to increase human and environmental knowledge faster and to overcome security complexity

Defense – GeospaceGeo-Web

4©Bull, 2011 Cooperation in extreme computing

Challenge (1/4) : concurrency and parallelism

History- Gigaflops 1985 Cray 2 : 4 cores @ 1.5 ops/cycle- Teraflops 1997 Asci Red : 4,500 cores @ 2 ops/cycle- Petaflops 2008 Jaguar : 180,000 cores @ 4ops/cycle- 10 petaflops 2011 K system : 700,000 cores @ 4ops/cycle

Next generation of systems- Million to billion threads- 16 ops/cycle for each threads

5©Bull, 2011 Cooperation in extreme computing

Challenge (2/4) energy and power

Today general purpose computer - 200 Mflops/W- Petaflops 5MW- 10 Petaflops in 2011 : 12,5 MW

Trend- Use of accelerators (GPU, MIC) with better ratio flops/W than

standard processor but more difficult to program- Use of low frequency standard processors - Reduction of the amount of memory per core

Most the large centers do not plan more than 20MW for a HPC system

6©Bull, 2011 Cooperation in extreme computing

Challenge (3/4) data in HPC

Data inside the HPC system- Memory access time - Amount of memory- Power cost of moving data

Storage of data (disk)- Capacity still growing- Bandwidth and seek time not progressing at the same pace- Increasing parallelism

Data for scientists- pre and post processing of huge volume of data- Quality of data produced by large simulation (uncertainty

quantification)- Semantic attached to data

7©Bull, 2011 Cooperation in extreme computing

Challenge (4/4) : Resiliency

Next generation system- Huge number of components : 106 to 108 memory chips- Interface at high clock rate increasing bit error rates

MTBF will be low- 10,000 components with a MTBF of > 10 years leads to a combined

MTBF of 10 hours

Robustness must be addressed at different levels- System hardware- System software- Application

8©Bull, 2011 Cooperation in extreme computing

Conclusion technological challenges

Important challenges for next generations of HPC systems

No one has the complete solution

Cooperation is a must

9©Bull, 2011 Cooperation in extreme computing

Bull’s experience in R&D cooperation

Common laboratory

Technology partners Intel, Xyratex, Caps Entreprise…

One-to-one cooperation

Development of large infrastructures

Research institutions / campus

Project with local ecosystem

Projects at European level

International vision sharing

10©Bull, 2011 Cooperation in extreme computing

Cooperation eco-system

Global for best of breed, standardization

Customer cooperation for co-design and connection of market demands- supplier offerings

Technology partners for complete and innovative offering

Local for fertilization, reactiveness and

teaming

11©Bull, 2011 Cooperation in extreme computing

Example of instruments in Europe Systematic, Eureka, FP7

Systematic- “World class” French Cluster, 142 enterprises, 311 SMB 92 research

centers & universities. - Cooperation between SMEs, Large Companies, Research Centres and

higher educational establishments- Supported by local authorities, economic development agencies, the

French Government and its partners.- Leverage on Teratec for HPCEUREKA- 39 member countries plus the European Union.- The EUREKA label gives participants a competitive edge in their

dealings with financial, technical and commercial partners.FP7- EU's main instrument for funding research in Europe - Grants are determined on the basis of calls for proposals- Activities funded from FP7 must have a “European added value”.

National level

European level

12©Bull, 2011 Cooperation in extreme computing

Systematic, FP7 & ITEA figures

Systematic FP7 ITEA

Type Cluster R&D program Eureka R&D program for IT

Time scale 2007-2013 2006-2012

Projects € 200 m / year 20,000 PY

o/w fundings € 60 m / year € 54 B o/w € 9 B for IT € 600 m

Area France Europe Europe

13©Bull, 2011 Cooperation in extreme computing

Example of a project : ParMa, Itea Gold Award 2010

A European project that gathers users, software providers, HPC system supplierObjective: help the HPC community take full advantage of multi-core architecturesDeliver substantial performance improvements for:- conventional HPC applications - mainstream applications- embedded systems

Facilitate the emergence of power-intensive innovative applications by:- Developing advanced

technologies for exploiting parallel computing

- Exploring commonalities between HPC, Multi-Core and MPSoC programming environments

- Leveraging relevant technology and methodology between these domains

Blast-furnace: €125,000 savings plus 16,000 tons of CO2 emission/year

Parallel Programming for Multi-core Architectures

14©Bull, 2011 Cooperation in extreme computing

To conclude

Latin America – Europe cooperation is what I call “a global cooperation”- Need to focus on global topics

- Ie programming models- Scientific methods…

- Need to find mutual interest- Economic system- Educational system

- Need to involve “regional champions”

Cooperation at International level could be boosted by new instruments- Why not a "Eureka-like" program at

International level

15©Bull, 2011 Cooperation in extreme computing