Center for Advanced Computing Research

Similar documents
Compact Muon Solenoid: Cyberinfrastructure Solutions. Ken Bloom UNL Cyberinfrastructure Workshop -- August 15, 2005

Data Transfers Between LHC Grid Sites Dorian Kcira

Gigabyte Bandwidth Enables Global Co-Laboratories

The CMS Computing Model

Programmable Information Highway (with no Traffic Jams)

Scientific data processing at global scale The LHC Computing Grid. fabio hernandez

ACCI Recommendations on Long Term Cyberinfrastructure Issues: Building Future Development

Storage on the Lunatic Fringe. Thomas M. Ruwart University of Minnesota Digital Technology Center Intelligent Storage Consortium

A New NSF TeraGrid Resource for Data-Intensive Science

The LCG 3D Project. Maria Girone, CERN. The 23rd Open Grid Forum - OGF23 4th June 2008, Barcelona. CERN IT Department CH-1211 Genève 23 Switzerland

Netherlands Institute for Radio Astronomy. May 18th, 2009 Hanno Holties

UW-ATLAS Experiences with Condor

VIRTUAL OBSERVATORY TECHNOLOGIES

CERN s Business Computing

Scientific Computing at SLAC

Towards Network Awareness in LHC Computing

SAM at CCIN2P3 configuration issues

e-research Infrastructures for e-science Axel Berg SARA national HPC & e-science support center RAMIRI, June 15, 2011

Insight: that s for NSA Decision making: that s for Google, Facebook. so they find the best way to push out adds and products

To Compete You Must Compute

Distributed e-infrastructures for data intensive science

The LHC Computing Grid

Scientific Computing at SLAC. Chuck Boeheim Asst Director: Scientific Computing and Computing Services

Trends in Scientific Discovery Engines

Data Centres in the Virtual Observatory Age

Distributed File Systems Part IV. Hierarchical Mass Storage Systems

CSD3 The Cambridge Service for Data Driven Discovery. A New National HPC Service for Data Intensive science

SRB Logical Structure

irods at TACC: Secure Infrastructure for Open Science Chris Jordan

Deduplication Storage System

CERN and Scientific Computing

DYNES: DYnamic NEtwork System

November 1 st 2010, Internet2 Fall Member Mee5ng Jason Zurawski Research Liaison

HIGH SPEED CONNECTIVITY BETWEEN AN ID-1 TAPE RECORDER AND HIGH PERFORMANCE COMPUTERS THIC MEETING, JANUARY 22-24, DATATAPE Incorporated

N. Marusov, I. Semenov

Giovanni Lamanna LAPP - Laboratoire d'annecy-le-vieux de Physique des Particules, Université de Savoie, CNRS/IN2P3, Annecy-le-Vieux, France

Deep Storage for Exponential Data. Nathan Thompson CEO, Spectra Logic

The CEDA Archive: Data, Services and Infrastructure

Travelling securely on the Grid to the origin of the Universe

Data Intensive Computing SUBTITLE WITH TWO LINES OF TEXT IF NECESSARY PASIG June, 2009

ICN for Cloud Networking. Lotfi Benmohamed Advanced Network Technologies Division NIST Information Technology Laboratory

Status of the Lulin 2 m Telescope

APAC: A National Research Infrastructure Program

A Simulation Model for Large Scale Distributed Systems

Physics Computing at CERN. Helge Meinhard CERN, IT Department OpenLab Student Lecture 27 July 2010

STFC Cloud Developments. Ian Collier & Alex Dibbo STFC Rutherford Appleton Laboratory UK Research & Innovation HEPiX Spring, Madison, WI 17 May 2018

Introduction to Grid Computing

Benoit DELAUNAY Benoit DELAUNAY 1

TeraVoxel Annual Report

De BiG Grid e-infrastructuur digitaal onderzoek verbonden

Enterprise Network Test Strategies for Network Availability and Performance. A Sitaramaiah Director Fluke Networks India

The LHC Computing Grid. Slides mostly by: Dr Ian Bird LCG Project Leader 18 March 2008

CC-IN2P3: A High Performance Data Center for Research

Network Design Considerations for Grid Computing

Technical Specifications for High speed PIV and High speed PIV-PLIF system

Reliability Engineering Analysis of ATLAS Data Reprocessing Campaigns

Next Generation Integrated Architecture SDN Ecosystem for LHC and Exascale Science. Harvey Newman, Caltech

Table 9. ASCI Data Storage Requirements

IBM řešení pro větší efektivitu ve správě dat - Store more with less

The creation of a Tier-1 Data Center for the ALICE experiment in the UNAM. Lukas Nellen ICN-UNAM

Summary of Data Management Principles

AST3 Cameras, a Status Update

Database Services at CERN with Oracle 10g RAC and ASM on Commodity HW

Computing and Networking at Diamond Light Source. Mark Heron Head of Control Systems

High-Energy Physics Data-Storage Challenges

LHC and LSST Use Cases

Data Intensive Science Impact on Networks

The Computation and Data Needs of Canadian Astronomy

A PERSPECTIVE ON FACILITIES STEWARDSHIP

Copyright 2012 EMC Corporation. All rights reserved.

The Future of Interconnect Technology

Towards a Strategy for Data Sciences at UW

Q1. Briefly describe the characteristic features of input and output devices of a computer system.

Real Parallel Computers

Big Computing and the Mitchell Institute for Fundamental Physics and Astronomy. David Toback

Unified Management for Virtual Storage

Interconnect Your Future

SpectraTec X. Multi- λ Laser Light Source BLUE SKY RESEARCH WAVELENGTHS

RUSSIAN DATA INTENSIVE GRID (RDIG): CURRENT STATUS AND PERSPECTIVES TOWARD NATIONAL GRID INITIATIVE

SPINOSO Vincenzo. Optimization of the job submission and data access in a LHC Tier2

Tuning I/O Performance for Data Intensive Computing. Nicholas J. Wright. lbl.gov

The Faculty of Arts and Sciences High Performance Computing Core

HP visoko-performantna OLTP rješenja

Astronomy and Big Data challenge. Sandra Jaque, CTO, REUNA

HPC Technology Trends

ORIENT/ORIENTplus - Connecting Academic Networks in China and Europe. Jennifer(Jie) An CERNET Center/Tsinghua University 14 Feb.

BlueGene/L. Computer Science, University of Warwick. Source: IBM

Storage Supporting DOE Science

Grid Computing a new tool for science

CMS Grid Computing at TAMU Performance, Monitoring and Current Status of the Brazos Cluster

Scientific Workflow Tools. Daniel Crawl and Ilkay Altintas San Diego Supercomputer Center UC San Diego

High Performance, High Resolution Detector Solutions. Dr Colin Coates, Product Manager 2015

DATA MANAGEMENT SYSTEMS FOR SCIENTIFIC APPLICATIONS

Computing. Richard P. Mount, SLAC. Director, SLAC Computing Services Assistant Director, Research Division. DOE Review

Server Specifications

Laser Diagnostic for High-Energy, Laser Fusion Drivers

Overview of the Texas Advanced Computing Center. Bill Barth TACC September 12, 2011

Optical Sectioning. Bo Huang. Pharmaceutical Chemistry

The Center for Computational Research

A High-Performance Storage and Ultra- High-Speed File Transfer Solution for Collaborative Life Sciences Research

Transcription:

Center for Advanced Computing Research DANSE Kickoff Meeting Mark Stalzer stalzer@caltech.edu August 15, 2006

CACR Mission and Partners Creating advanced computing methods to accelerate scientific discovery Mark Stalzer stalzer@caltech.edu 2

CACR Competencies High Performance Computing Systems Facilities design, operation, and user support Physics Based Simulation Algorithm development Validation & Verification Data Intensive Science (Novel Instruments) Data transport, storage, and analysis Standards and community building Visualization Scientific Software Engineering Mark Stalzer stalzer@caltech.edu 3

Intel Touchstone Delta: World s Fastest Computer in 1991 (30 Gflops) Mark Stalzer stalzer@caltech.edu 4

Facilities NVO Powell-Booth Laboratory for Computational Science Machine room: shc & LIGO silo LHC/ CMS Tier2 Mark Stalzer stalzer@caltech.edu 5

Caltech ASC Center: Multi- Physics Multi-Scale Modeling time ns µs ms Void growth, colaescence Ductile fracture Damage localization Dislocation emission, nanovoid cavitation Vacancy clustering, nanovoid nucleation Vacancy generation nm µm mm Mark Stalzer stalzer@caltech.edu 6

Ductile Fracture Source: Dan Meiron Mark Stalzer stalzer@caltech.edu 7

Data Intensive Science: Knowledge Gap doubling t 1.5 yrs Large digital sky surveys are becoming the dominant source of data in astronomy: ~ 10-100 TB/survey, ~ 10 6-10 9 sources/survey, many wavelengths. 1970 1975 1980 1985 1990 1000 100 10 1 0.1 2000 1995 CCDs Glass An exponential growth in data quantity driven by detector technology; but our understanding of the universe increases much more slowly! Mark Stalzer stalzer@caltech.edu 8

Astronomical Virtual Observatories (www.us-vo.org) Mark Stalzer stalzer@caltech.edu 9

CERN LHC Cyberinfrastructure Tier 1 ~PByte/sec 10-40 Gbps Online System Tier 0 +1 IN2P3 Center INFN Center RAL Center CERN/Outside Resource Ratio ~1:2 Tier0/(Σ Tier1)/(Σ Tier2) ~1:1:1 ~100-1500 MBytes/sec CERN Center PBs of Disk; Tape Robot FNAL Center Tier 3 Physics data cache ~1-10 Gbps Tier 2 Institute Institute Institute Institute 1 to 10 Gbps ~10 Gbps Tier2 Center Tier2 Center Tier2 Center Tier2 Center Tier2 Center Tens of Petabytes by 2007-8 An Exabyte ~5-7 Years later Workstations Mark Stalzer stalzer@caltech.edu 10

Novel Instrument: TeraVoxel Observing Turbulent Mixing ~300 MB/s captured from KPS camera (laser illumination). Sent to local ~50TB DataWulfs. Transmitted to CACR for image correction, processing, and visualization Mark Stalzer stalzer@caltech.edu 11

TeraVoxel Operation Source: Santiago Lombeyda Mark Stalzer stalzer@caltech.edu 12

Turbulent Mixing Close-up Mark Stalzer stalzer@caltech.edu 13

Visualization: ShakeMovie.com Mark Stalzer stalzer@caltech.edu 14

CACR Initiative in Computational Biology Biology is >25% of research at Caltech Working with Biology Division, Beckman Inst., and E&AS Current efforts: Biological Network Modeling Center & ARO-ICB program Parallel stochastic simulation algorithm with tau leaping Center for the Integrative Study of Cell Regulation Funded by Moore foundation ($5.6M gift over 5 years) MCell tool chain Biological image processing Phylogenetic inferencing Mark Stalzer stalzer@caltech.edu 15

The Internet Hourglass Applications User Web FTP Mail News Video telnet ping napster TCP telnet protocol IP Ethernet ATM Power lines 802.11 Optical Satellite Bluetooth Link technologies Source: John Doyle Mark Stalzer stalzer@caltech.edu 16

Bridging the Semantic Gap e-science geo CIG astro NVO bio physics other Semantic Gap Simulation Data intensive Libs (LAPACK, PETSc, ) Assembly Languages (C++, MPI, XML, SQL, ) Scheduling (Time&Space) Computational Substrate Generalized fast (synthetic) frameworks? Mark Stalzer stalzer@caltech.edu 17

Software is the Secret Sauce Palomar-QUEST Image Filtering & Fusion Source: Roy Williams Mark Stalzer stalzer@caltech.edu 18

For more information: www.cacr.caltech.edu Mark Stalzer stalzer@caltech.edu 19