High Performance Computing & Society Ian Bird, CERN | 28-29th September 2013.

Slides:



Advertisements
Similar presentations
EGEE-III INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Why Grids Matter to Europe Bob Jones EGEE.
Advertisements

Particle physics – the computing challenge CERN Large Hadron Collider –2007 –the worlds most powerful particle accelerator –10 petabytes (10 million billion.
High Performance Computing Course Notes Grid Computing.
1 Cyberinfrastructure Framework for 21st Century Science & Engineering (CIF21) NSF-wide Cyberinfrastructure Vision People, Sustainability, Innovation,
T1 at LBL/NERSC/OAK RIDGE General principles. RAW data flow T0 disk buffer DAQ & HLT CERN Tape AliEn FC Raw data Condition & Calibration & data DB disk.
2012: Hurricane Sandy 125 dead, 60+ billion dollars damage.
The Earth System Analyzer: Using all of the Data to Improve NOAA’s Mission Capabilities Alexander E. MacDonald NOAA Earth System Research Laboratory.
The LHC Computing Grid – February 2008 The Worldwide LHC Computing Grid Dr Ian Bird LCG Project Leader 15 th April 2009 Visit of Spanish Royal Academy.
LHC’s Second Run Hyunseok Lee 1. 2 ■ Discovery of the Higgs particle.
Assessment of Core Services provided to USLHC by OSG.
CBP 2006MSc. Computing1 Modelling and Simulation.
Chapter 1- “Diversity” “In higher education they value diversity of everything except thought.” George Will.
Copyright © 2011, Oracle and/or its affiliates. All rights reserved.
18:15:32Service Oriented Cyberinfrastructure Lab, Grid Deployments Saul Rioja Link to presentation on wiki.
Forecasting and Numerical Weather Prediction (NWP) NOWcasting Description of atmospheric models Specific Models Types of variables and how to determine.
National Weather Service National Weather Service Central Computer System Backup System Brig. Gen. David L. Johnson, USAF (Ret.) National Oceanic and Atmospheric.
Engineering the future: universities and education Sir Keith O’Nions President & Rector June 2014.
Advanced Computing Services for Research Organisations Bob Jones Head of openlab IT dept CERN This document produced by Members of the Helix Nebula consortium.
Welcome to this presentation! We’re so glad you came. While you’re here, you can explore many questions: What is CERN and the Large Hadron Collider (LHC)?
Chapter 1 Intro to Computer Department of Computer Engineering Khon Kaen University.
ALICE Upgrade for Run3: Computing HL-LHC Trigger, Online and Offline Computing Working Group Topical Workshop Sep 5 th 2014.
The Future of the iPlant Cyberinfrastructure: Coming Attractions.
The LHC Computing Grid – February 2008 The Worldwide LHC Computing Grid Dr Ian Bird LCG Project Leader 25 th April 2012.
Introduction to Complexity Science Engineered Complexity.
TEKS 8C: Calculate percent composition and empirical and molecular formulas. Contemporary Technological Changes.
Genomes To Life Biology for 21 st Century A Joint Initiative of the Office of Advanced Scientific Computing Research and Office of Biological and Environmental.
NIST Data Science SymposiumMarch 4, 2014 NIST Data Science SymposiumMarch 4, Climate Archives in NOAA: Challenges and Opportunities March 4, 2014.
Experts in numerical algorithms and High Performance Computing services Challenges of the exponential increase in data Andrew Jones March 2010 SOS14.
Ian Bird LHC Computing Grid Project Leader LHC Grid Fest 3 rd October 2008 A worldwide collaboration.
Tim 18/09/2015 2Tim Bell - Australian Bureau of Meteorology Visit.
…building the next IT revolution From Web to Grid…
The LHC Computing Grid – February 2008 The Challenges of LHC Computing Dr Ian Bird LCG Project Leader 6 th October 2009 Telecom 2009 Youth Forum.
Les Les Robertson LCG Project Leader High Energy Physics using a worldwide computing grid Torino December 2005.
CERN IT Department CH-1211 Genève 23 Switzerland t Frédéric Hemmer IT Department Head - CERN 23 rd August 2010 Status of LHC Computing from.
Breakout # 1 – Data Collecting and Making It Available Data definition “ Any information that [environmental] researchers need to accomplish their tasks”
WLCG and the India-CERN Collaboration David Collados CERN - Information technology 27 February 2014.
| nectar.org.au NECTAR TRAINING Module 2 Virtual Laboratories and eResearch Tools.
Dr. Andreas Wagner Deputy Group Leader - Operating Systems and Infrastructure Services CERN IT Department The IT Department & The LHC Computing Grid –
Predrag Buncic Future IT challenges for ALICE Technical Workshop November 6, 2015.
1 Volunteer Computing at CERN past, present and future Ben Segal / CERN (describing the work of many people at CERN and elsewhere ) White Area lecture.
2. WP9 – Earth Observation Applications ESA DataGrid Review Frascati, 10 June Welcome and introduction (15m) 2.WP9 – Earth Observation Applications.
Computing for LHC Physics 7th March 2014 International Women's Day - CERN- GOOGLE Networking Event Maria Alandes Pradillo CERN IT Department.
LHC Computing, CERN, & Federated Identities
Forecasting systems WMO Atmospheric Research and Environment Programme David Burridge.
tons, 150 million sensors generating data 40 millions times per second producing 1 petabyte per second The ATLAS experiment.
Ian Bird Overview Board; CERN, 8 th March 2013 March 6, 2013
Support to scientific research on seasonal-to-decadal climate and air quality modelling Pierre-Antoine Bretonnière Francesco Benincasa IC3-BSC - Spain.
The Worldwide LHC Computing Grid Frédéric Hemmer IT Department Head Visit of INTEL ISEF CERN Special Award Winners 2012 Thursday, 21 st June 2012.
WLCG Status Report Ian Bird Austrian Tier 2 Workshop 22 nd June, 2010.
Meeting with University of Malta| CERN, May 18, 2015 | Predrag Buncic ALICE Computing in Run 2+ P. Buncic 1.
Big Data in Indian Agriculture D. Rama Rao Director, NAARM.
Dominique Boutigny December 12, 2006 CC-IN2P3 a Tier-1 for W-LCG 1 st Chinese – French Workshop on LHC Physics and associated Grid Computing IHEP - Beijing.
Grid technologies for large-scale projects N. S. Astakhov, A. S. Baginyan, S. D. Belov, A. G. Dolbilov, A. O. Golunov, I. N. Gorbunov, N. I. Gromova, I.
Computing infrastructures for the LHC: current status and challenges of the High Luminosity LHC future Worldwide LHC Computing Grid (WLCG): Distributed.
LHC collisions rate: Hz New PHYSICS rate: Hz Event selection: 1 in 10,000,000,000,000 Signal/Noise: Raw Data volumes produced.
ScotGRID is the Scottish prototype Tier 2 Centre for LHCb and ATLAS computing resources. It uses a novel distributed architecture and cutting-edge technology,
2nd GEO Data Providers workshop (20-21 April 2017, Florence, Italy)
Ian Bird WLCG Workshop San Francisco, 8th October 2016
e-Science using Grid infrastructure
Clouds , Grids and Clusters
Report from WLCG Workshop 2017: WLCG Network Requirements GDB - CERN 12th of July 2017
Grid site as a tool for data processing and data analysis
We enable Digitalization Thomas Hahn CERN Openlab, March 2016
The LHC Computing Grid Visit of Mtro. Enrique Agüera Ibañez
Dagmar Adamova, NPI AS CR Prague/Rez
The LHC Computing Grid Visit of Her Royal Highness
Dagmar Adamova (NPI AS CR Prague/Rez) and Maarten Litmaath (CERN)
EUChinaGRID Applications
The Technology and Future of Weather Forecasting ATMS 490
The LHC Computing Grid Visit of Professor Andreas Demetriou
Presentation transcript:

High Performance Computing & Society Ian Bird, CERN | 28-29th September 2013

High Performance Computing What is it? Why does CERN need it? What use is it in the real world? ? September 12, 2013

High Performance Computing What is it? ? Why does CERN need it? What use is it in the real world?

September 2013 What is High Performance Computing? HUGE VOLUMES OF DATA SPEED FAST NETWORK SCALE LARGE SCALE PROCESS COMPLEX SOPHISTICATED SOFTWARE COMPLEX PROBLEMS THAT REQUIRE

September 2013 What is High Performance Computing? BIG DATA Data volumes that present a challenge – different for different sciences SUPERCOMPUTERS Very large, fast, (expensive!), world-class machines: hundreds of thousands of interconnected processors GRIDS Supercomputers built using commodity components, distributed globally CLOUD COMPUTING Large, centralised data centres, providing computing and services over the network VOLUNTEER COMPUTING Huge scale using voluntarily contributed PCs

High Performance Computing What is it? Why does CERN need it? What use is it in the real world? ? September 12, 2013

September IBM 370/ CDC First computer Ferranti Mercury Already lots of data CERN CC 1988 Cray X/MP 1998 CC

Computing in High-Energy Physics  Demanding scienceDemanding computing Large scale computing & storage Innovation The Web Grid computing (LHC Computing Grid) September 12, 2013

CERN Computer Centre CERN COMPUTER CENTRE Built in the 70s on the CERN site (Meyrin-Geneva) ~3000 m2 (3 main machine rooms) 3.5 MW for equipment Est. PUE ~ 1.6 NEW EXTENSION Located at Wigner (Budapest) ~1000 m2 2.7 MW for equipment Connected to the Geneva CC with 2x100Gb links (21 and 24 ms RTT) September 2013

High Performance Computing What is it? Why does CERN need it? What use is it in the real world? ? September 12, 2013

LHCb Atlas Tools: LHC and Detectors Exploration of a new energy frontier in P-P and Pb-Pb collisions LHC ring: 27 km circumference CMS Alice

MB/sec Data flow to permanent storage: 4-6 GB/sec ~ 4 GB/sec 1-2 GB/sec

LHC Data LHC experiments generate 25 PB of data per year between them CERN scientific data archive is today 100 PB Requires huge amounts of processing power, storage, and network bandwidth September 2013

Just how much is that? LHC would need 30 million iPads to process all its data Stores 640 of these LHC would need 2 million iPads to store all the data LHC Data: 100 Petabytes (100 million Gigabytes)  21 million DVDs  125 million CDs  10 billion MP3 songs September 12, 2013

The Worldwide LHC Computing Grid Tier-1 permanent storage, re-processing, analysis Tier-0 (CERN) data recording, reconstruction and distribution Tier-2 Simulation, end-user analysis > 2 million jobs/day ~350’000 cores 200 PB of storage nearly 160 sites, 35 countries 10 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 September 12, 2013

September 12, 2013

Application of High Performance Computing High Performance computing is used across very many areas of science, engineering, medicine, … Addressing problems that can only be tackled by large scale simulations and computations, or manipulation of massive data sets September 12, 2013

Such as…. Materials and engineering New materials Simulation in place of physical models September 12, 2013 Science and … Energy and Modelling of wind and wave energy Health and Gene sequencing Drug discovery Disease diagnostics Modelling the brain and organs Environment and Weather and climate modelling and prediction Earth observation

September 12, 2013

Genomics Human Genome project 1989 – 2000: sequencing the Human Genome 1 individual Today Same data volume generated in 3 minutes in a current large scale centre Now practical to sequence entire populations of humans, other animals Only possible with High Performance computing and storage September 2013

3 big areas of impact for medicine Germ line Risk to disease “Precision” cancer medicine Pathogens + Hospital acquired infections September 2013

Germ Line impact Everyone has differential risk of disease But the shift in risk is small Perhaps 1 to 2% have a striking change in risk to a serious disease (>10 fold) which is “actionable” This goes up to 3-4% if you count some less clinically worrying diseases 1:500 people have HCM 1:500 people have FH September 2013

Precision cancer diagnosis Cancer is a genomic disease By sequencing a cancer you can understand its molecular form better Particular molecular forms respond to particular drugs September 2013

Pathogens Sequencing provides a clear cut diagnosis of pathogens Can also be used to sequence environments (eg, hospitals) Immune systems for hospitals

Designing better antibiotics This example: the antibiotic does not distinguish between the fungal and human cell membranes Molecular dynamics models (describe behaviour of atoms, molecules, and interactions) used to determine better varieties of drugs that interact with disease rather than human cells Such calculations require large scale computing – in this case using a grid Lung cells attacked by a fungal cryptococcosis infection (Image: CDC / wikicommons) 3-D model of the Amphotericin B molecule (Image: wikicommons) September 2013

September 2013

September 2013 New materials The Simulation of nanostructured materials requires high performance computers and modern calculation methods, for example density functional theory and molecular dynamics. Complementing experiment and theory, simulations help to understand observed phenomena and even predict properties and scenarios in complex systems. Especially challenging is the quest for new materials and phenomena for which an experimental exploration without the knowledge from simulations would be prohibitive.

Pollution? Today’s plastics are a serious problem and hazard Polyactide plastics are an alternative, but expensive to produce – do not use oil, but cheap raw materials Such PLA plastics production needs a catalyst for the reaction, and this must be cheap and non-toxic Molecular simulation on a computing grid has been used to calculate the entire reaction mechanism September 2013

September 2013

Meteorological input data September 2013

September 2013 Weather Satellites METEOSAT NOAA POES FENGYUN 3 FENGYUN 1D MODIS TERRA MODIS AQUA JPSS1 SUOMI NPP Higher resolution Color Visible channel by night METOP (EPS)

September 2013 Numerical weather prediction Observations Weather forecasts Product Generation now+1 hour +2 hours +3 hours+4 hours Products …

September 2013 Climate and weather forecasts Future Past Decade forecasts Seasonal forecasts Monthly forecasts 100 years 10 years 1 year 1 month today Climate monitoring Medium range forecasts ( hours) Short range forecasts (12-72 hours) Shortest range forecasts (2-12 hours) Nowcasting ( < 2 hours) Climate projections

DWD NWP model suite September 2013 Model output size per day ~2.5 TBytes ICON: Grid spacing: 20 km * 60 grid points Forecast range: 174 hours Runs per day: 2 COSMO-EU: Grid spacing: 7 km 665 * 657 * 40 grid points Forecast range: 78 hours Runs per day: 4 COSMO-DE: Grid spacing: 2.8 km 421 * 461 * 50 grid points Forecast range: 21 hours Runs per day: 8 ICON  x = 20 km COSMO-EU  x = 7 km COSMO-DE  x = 2.8 km

short range forecasts aviation briefings annually warnings annually expertises p.a. Data + model products Public weather service: basic warnings and forecasts, climate information Deliver the right data to the right people Efficient storage and access in time New analysis tasks: earlier storm tracking better climate analysis optimization problems in aviation and energy Privacy and security issues September 2013 What are the challenges?

short range forecasts aviation briefings annually warnings annually expertises p.a. Data + model products Public weather service basic warnings and forecasts, climate information September 2013

Environmental Modeling Bulgarian researchers have ported three applications to the grid. 1. Study the impact of climate change on air quality 2. Model atmospheric composition 3. Investigate emergency responses to the release of harmful substances into the atmosphere September 2013

Environmental Modeling Bulgarian researchers have ported three applications to the grid. 1. Study the impact of climate change on air quality 2. Model atmospheric composition 3. Investigate emergency responses to the release of harmful substances into the atmosphere September 2013

Use Case: ASTRA Ancient instruments Sound/Timbre Reconstruction Application Has recreated 4 instruments so far Held concerts using these instruments September 2013

Some advantages of using the grid: can meet high demand for network and computing requirements; high reliability; allow multi-disciplinary collaboration between researchers, musicians and historians; longevity: ASTRA running since September 2013 Use Case: ASTRA

Use Case: ITER Investigating viability of fusion as a power source Modelling and simulating the reactor Used 1 million CPU hours in the last 12 months September 2013

Use Case: DECIDE Diagnostic Enhancement of Confidence by an International Distributed Environment Diagnostic tools for the medical community Example: Their Statistical Parametric Mapping application can help doctors to diagnose Alzheimer’s disease in its early stages and track the progress of the symptoms over time September

Use Case: DECIDE Some advantages of using the grid: a single European-wide master database of images stored on the grid for doctors to use; can set up diagnostic tools with a dedicated grid infrastructure; customisable: dedicated software to track progression of the disease over time; sharing medical data securely. September 2013

Summary High Performance Computing – in all of its forms – is a vital tool in many areas of our everyday lives CERN, and other sciences, by pushing the boundaries of what is possible in computing helps to drive this forward September 2013