SlideShare a Scribd company logo
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
ESCAPE - The European Science Cluster of Astronomy & Particle Physics ESFRI Research Infrastructures has received funding from the European Union’s Horizon 2020
research and innovation programme under the Grant Agreement n° 824064.
HL-LHC ESFRI Landmark
Ian Bird
CERN, Geneva, Switzerland
Annecy, 7 January 2019
CERN: founded in 1954 by 12 European States
Under UNESCO “Science for Peace” programme
Today 22 member states and supports a global community of 15,000 researchers.
Associate member states
Observers
Associate member states in the pre-stage to membership
Member states
Cooperation agreements
A world-wide endeavour
Budget (2017)
1100 MCHF
Probing the fundamental structure of the Universe.
Understanding the very first
moments of our Universe after the
Big Bang
Understanding Dark Matter
Looking for
Antimatter
The Large Hadron Collider (LHC)
A new frontier in Energy & Data volumes:
LHC experiments generate 50 PB/year in Run 2
CentOS; 19 Oct 2018 Ian.Bird@cern.ch 4
~700 MB/s
~10 GB/s
>1 GB/s
>1 GB/s
ESCAPE Kick-off meeting - HL-LHC ESFRI Landmark (Feb 2019)
CentOS; 19 Oct 2018 Ian.Bird@cern.ch 6
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
CentOS; 19 Oct 2018 Ian.Bird@cern.ch
Tier-1: permanent
storage, re-processing,
analysis
Tier-0
(CERN and Hungary):
data recording,
reconstruction and
distribution
Tier-2: Simulation,
end-user analysis
> 2 million jobs/day
~1M CPU cores
~1 EB of storage
~170 sites,
42 countries
10-100 Gb links
WLCG:
An International collaboration to distribute and analyse LHC data
Integrates computer centres worldwide that provide computing and storage
resource into a single infrastructure accessible by all LHC physicists
The Worldwide LHC Computing Grid
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
HL-LHC
• HL-LHC is the Phase 2 upgrade of
the LHC to higher luminosity (more
interactions/s)
 On-line in 2027
• Upgrade of the 2 large detectors
(ATLAS & CMS)
 LHCb and ALICE upgrades are now
• Increases the discovery potential of
the LHC significantly,
 expected lifetime to ~2035
• Implications for computing:
 5 EB of data per year per
experiment
 Huge increase in compute needs
7 Feb 2019 Ian.Bird@cern.ch
8
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
The HL-LHC computing challenge
• HL-LHC needs for ATLAS and CMS are above the expected hardware technology evolution (15% to 20%/yr) and
funding (flat)
• The main challenge is storage, but computing requirements grow 20-50x
OBELICS, 25 October 2018 Ian.Bird@cern.ch 9
Google
searches
98 PB
LHC Science
data
~200 PB
SKA Phase 1 –
2023
~300 PB/year
science data
HL-LHC – 2026
~600 PB Raw data
HL-LHC – 2026
~1 EB Physics data
SKA Phase 2 – mid-2020’s
~1 EB science data
LHC – 2016
50 PB raw data
Facebook
uploads
180 PB
Google
Internet archive
~15 EB
Yearly data volumes
10 Billion of theseCape Town, 19 Nov 2018 Ian.Bird@cern.ch 10
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
Collaboration CERN – SKA
• Recognition on both sides of potential synergies and
requirements
 Various ad-hoc interactions between communities
 Reviews and panels etc.
 Held a CERN-SKA “Big data”
workshop in the UK Alan Turing Inst.
• In July 2017 CERN and SKAO signed a
collaboration agreement on computing, data
management, etc.
 Recognizing that both HL-LHC and SKA will be
Exabyte-scale scientific experiments on a
10-year timescale
1
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
Evolution of WLCG
• Community White Paper
 1 year – bottom up review of LHC computing topics
 13 working groups on all aspects
 Outlines how HEP computing could evolve to address computing challenges
 https://arxiv.org/abs/1712.06982
• WLCG Strategy Document
 Prioritisation of topics in the CWP from the point of view of the HL-LHC
challenges
 Set out a number of R&D projects for the next 5 years
• Running global system should evolve towards HL-LHC
 http://cern.ch/go/Tg79
7 Feb 2019 Ian.Bird@cern.ch 12
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
HL-LHC Computing Strategy – main themes
• Software performance – embodied in HEP Software Foundation (HSF)
 application level: algorithmic changes & improvements, re-engineering
 system level: overall performance, efficiency, strategies for performance
 Skills building and training
• Data management – overall project “DOMA”
 Data organization – data lakes (or data cloud), and associated technologies
 Data management – high level management workflows, policies, etc
 Data access - streaming, caching, protocols, SDN, etc.
• Use of compute resources – pledged and opportunistic
 Use of cluster, HPC, clouds, and others, permanent resource or time-limited
 Delivery of data to these – (DOMA – streaming, caching, placement)
• Data preservation and re-use – “FAIR”
 Open data portal
 Integration of main workflows and re-use,
 Delivery of open data sets (data lake as mechanism)
• Evolving AAI model – towards token-based away from old “grid” model
7 Feb 2019 Ian.Bird@cern.ch 13
Addressed in
ESCAPE
Funded by the European Union’s
Horizon 2020 - Grant N° 824064
CERN-WLCG-EOSC-ESCAPE …
• Believe that technologies that address the HL-LHC (and ESCAPE
partner) problems will be generally useful for EOSC to manage and
deliver large-scale open data
• ESCAPE will be a testbed for these technology ideas and a
mechanism to ensure they are suited to a broad range of use cases
• Architecture is open to inclusion of public and commercial resources
• Pathways to collaborate with other EC actions:
 GEANT, PRACE,
 XDC, Indigo-next, HNSciCloud/OCRE, ARCHIVER
• CERN/WLCG technologies potentially interesting in EOSC:
 FTS, EOS, Rucio, Zenodo, SWAN, REANA, Open Data portal, …
7 Feb 2019 Ian.Bird@cern.ch 14

More Related Content

ESCAPE Kick-off meeting - HL-LHC ESFRI Landmark (Feb 2019)

  • 1. Funded by the European Union’s Horizon 2020 - Grant N° 824064 ESCAPE - The European Science Cluster of Astronomy & Particle Physics ESFRI Research Infrastructures has received funding from the European Union’s Horizon 2020 research and innovation programme under the Grant Agreement n° 824064. HL-LHC ESFRI Landmark Ian Bird CERN, Geneva, Switzerland Annecy, 7 January 2019
  • 2. CERN: founded in 1954 by 12 European States Under UNESCO “Science for Peace” programme Today 22 member states and supports a global community of 15,000 researchers. Associate member states Observers Associate member states in the pre-stage to membership Member states Cooperation agreements A world-wide endeavour Budget (2017) 1100 MCHF
  • 3. Probing the fundamental structure of the Universe. Understanding the very first moments of our Universe after the Big Bang Understanding Dark Matter Looking for Antimatter
  • 4. The Large Hadron Collider (LHC) A new frontier in Energy & Data volumes: LHC experiments generate 50 PB/year in Run 2 CentOS; 19 Oct 2018 Ian.Bird@cern.ch 4 ~700 MB/s ~10 GB/s >1 GB/s >1 GB/s
  • 6. CentOS; 19 Oct 2018 Ian.Bird@cern.ch 6
  • 7. Funded by the European Union’s Horizon 2020 - Grant N° 824064 CentOS; 19 Oct 2018 Ian.Bird@cern.ch Tier-1: permanent storage, re-processing, analysis Tier-0 (CERN and Hungary): data recording, reconstruction and distribution Tier-2: Simulation, end-user analysis > 2 million jobs/day ~1M CPU cores ~1 EB of storage ~170 sites, 42 countries 10-100 Gb links WLCG: An International collaboration to distribute and analyse LHC data Integrates computer centres worldwide that provide computing and storage resource into a single infrastructure accessible by all LHC physicists The Worldwide LHC Computing Grid
  • 8. Funded by the European Union’s Horizon 2020 - Grant N° 824064 HL-LHC • HL-LHC is the Phase 2 upgrade of the LHC to higher luminosity (more interactions/s)  On-line in 2027 • Upgrade of the 2 large detectors (ATLAS & CMS)  LHCb and ALICE upgrades are now • Increases the discovery potential of the LHC significantly,  expected lifetime to ~2035 • Implications for computing:  5 EB of data per year per experiment  Huge increase in compute needs 7 Feb 2019 Ian.Bird@cern.ch 8
  • 9. Funded by the European Union’s Horizon 2020 - Grant N° 824064 The HL-LHC computing challenge • HL-LHC needs for ATLAS and CMS are above the expected hardware technology evolution (15% to 20%/yr) and funding (flat) • The main challenge is storage, but computing requirements grow 20-50x OBELICS, 25 October 2018 Ian.Bird@cern.ch 9
  • 10. Google searches 98 PB LHC Science data ~200 PB SKA Phase 1 – 2023 ~300 PB/year science data HL-LHC – 2026 ~600 PB Raw data HL-LHC – 2026 ~1 EB Physics data SKA Phase 2 – mid-2020’s ~1 EB science data LHC – 2016 50 PB raw data Facebook uploads 180 PB Google Internet archive ~15 EB Yearly data volumes 10 Billion of theseCape Town, 19 Nov 2018 Ian.Bird@cern.ch 10
  • 11. Funded by the European Union’s Horizon 2020 - Grant N° 824064 Collaboration CERN – SKA • Recognition on both sides of potential synergies and requirements  Various ad-hoc interactions between communities  Reviews and panels etc.  Held a CERN-SKA “Big data” workshop in the UK Alan Turing Inst. • In July 2017 CERN and SKAO signed a collaboration agreement on computing, data management, etc.  Recognizing that both HL-LHC and SKA will be Exabyte-scale scientific experiments on a 10-year timescale 1
  • 12. Funded by the European Union’s Horizon 2020 - Grant N° 824064 Evolution of WLCG • Community White Paper  1 year – bottom up review of LHC computing topics  13 working groups on all aspects  Outlines how HEP computing could evolve to address computing challenges  https://arxiv.org/abs/1712.06982 • WLCG Strategy Document  Prioritisation of topics in the CWP from the point of view of the HL-LHC challenges  Set out a number of R&D projects for the next 5 years • Running global system should evolve towards HL-LHC  http://cern.ch/go/Tg79 7 Feb 2019 Ian.Bird@cern.ch 12
  • 13. Funded by the European Union’s Horizon 2020 - Grant N° 824064 HL-LHC Computing Strategy – main themes • Software performance – embodied in HEP Software Foundation (HSF)  application level: algorithmic changes & improvements, re-engineering  system level: overall performance, efficiency, strategies for performance  Skills building and training • Data management – overall project “DOMA”  Data organization – data lakes (or data cloud), and associated technologies  Data management – high level management workflows, policies, etc  Data access - streaming, caching, protocols, SDN, etc. • Use of compute resources – pledged and opportunistic  Use of cluster, HPC, clouds, and others, permanent resource or time-limited  Delivery of data to these – (DOMA – streaming, caching, placement) • Data preservation and re-use – “FAIR”  Open data portal  Integration of main workflows and re-use,  Delivery of open data sets (data lake as mechanism) • Evolving AAI model – towards token-based away from old “grid” model 7 Feb 2019 Ian.Bird@cern.ch 13 Addressed in ESCAPE
  • 14. Funded by the European Union’s Horizon 2020 - Grant N° 824064 CERN-WLCG-EOSC-ESCAPE … • Believe that technologies that address the HL-LHC (and ESCAPE partner) problems will be generally useful for EOSC to manage and deliver large-scale open data • ESCAPE will be a testbed for these technology ideas and a mechanism to ensure they are suited to a broad range of use cases • Architecture is open to inclusion of public and commercial resources • Pathways to collaborate with other EC actions:  GEANT, PRACE,  XDC, Indigo-next, HNSciCloud/OCRE, ARCHIVER • CERN/WLCG technologies potentially interesting in EOSC:  FTS, EOS, Rucio, Zenodo, SWAN, REANA, Open Data portal, … 7 Feb 2019 Ian.Bird@cern.ch 14

Editor's Notes

  1. From 12 funding member states it has grown to 22 member states plus associates and observers. It has got a budget of 1B/year and and supports a community of 15000 researchers located world-wide.
  2. At CERN, physicists are probing the fundamental structure of the universe. They use accelerators to study the basic constituents of matter — the fundamental particles, their interactions and the fundamental laws of nature. By reproducing the conditions of the first instants of the Universe liife, we want to get insights on fondamental questions on why matter has won over antimatter and shading light on dark matter.
  3. Largest scientific apparatus ever build 27km around 2 general purpose detectors: Huge microscopes – to explore the very small – using a long lever arm 2 specialized detectors