Tutorial on Distributed High Performance Computing 14:30 – 19:00 (2:30 pm – 7:00 pm) Wednesday November 17, 2010 Jornadas Chilenas de Computación 2010.

Slides:



Advertisements
Similar presentations
Distributed Data Processing
Advertisements

High Performance Computing Course Notes Grid Computing.
1-1.1 Introduction to Grid Computing Slides for Grid Computing: Techniques and Applications by Barry Wilkinson, Chapman & Hall/CRC, © Chapter 1,
1.1 Introduction to Grid Computing ITCS 4010 Grid Computing, 2005, UNC-Charlotte, B. Wilkinson.
1 Short Course on Grid Computing Jornadas Chilenas de Computación 2010 INFONOR-CHILE 2010 November 15th - 19th, 2010 Antofagasta, Chile Dr. Barry Wilkinson.
1 Teaching Grid Computing across North Carolina and Beyond Dr. Clayton Ferner University of North Carolina Wilmington Dr. Barry Wilkinson University of.
DataGrid Kimmo Soikkeli Ilkka Sormunen. What is DataGrid? DataGrid is a project that aims to enable access to geographically distributed computing power.
Milos Kobliha Alejandro Cimadevilla Luis de Alba Parallel Computing Seminar GROUP 12.
1 Workshop 20: Teaching a Hands-on Undergraduate Grid Computing Course SIGCSE The 41st ACM Technical Symposium on Computer Science Education Friday.
Outline.1 Grid Computing Spring 2007 Tuesday/Thursday 11:00 am - 12:15 pm Instructors Dr. Barry Wilkinson University of North Carolina, Charlotte and Dr.
1 GRID D. Royo, O. Ardaiz, L. Díaz de Cerio, R. Meseguer, A. Gallardo, K. Sanjeevan Computer Architecture Department Universitat Politècnica de Catalunya.
1 Short Course on Grid Computing Jornadas Chilenas de Computación 2010 INFONOR-CHILE 2010 November 15th - 19th, 2010 Antofagasta, Chile Dr. Barry Wilkinson.
April 2009 OSG Grid School - RDU 1 Open Science Grid John McGee – Renaissance Computing Institute University of North Carolina, Chapel.
SICSA student induction day, 2009Slide 1 Social Simulation Tutorial Session 6: Introduction to grids and cloud computing International Symposium on Grid.
Welcome to CW 2007!!!. The Condor Project (Established ‘85) Distributed Computing research performed by.
The Internet in Education Objectives Introduction Overview –The World Wide Web –Web Page v. Web Site v. Portal Unique and Compelling Characteristics Navigation.
Open Science Grid For CI-Days Internet2: Fall Member Meeting, 2007 John McGee – OSG Engagement Manager Renaissance Computing Institute.
Executive summary Grid computing has become an important concept for high performance computing. By taking advantage of the Internet, geographically distributed.
What is OMII-Europe? Qin Li Beihang University. EU project: RIO31844-OMII-EUROPE 1 What is OMII-Europe? Open Middleware Infrastructure Institute for Europe.
1 Grid Computing Barry Wilkinson Department of Computer Science University of North Carolina at Charlotte.
DISTRIBUTED COMPUTING
Networks QUME 185 Introduction to Computer Applications.
1 “The grid virtualizes heterogeneous geographically disperse resources” "Introduction to Grid Computing with Globus," IBM Redbooks  Using geographically.
INFSO-RI Enabling Grids for E-sciencE The US Federation Miron Livny Computer Sciences Department University of Wisconsin – Madison.
The Cluster Computing Project Robert L. Tureman Paul D. Camp Community College.
1 What is the history of the Internet? ARPANET (Advanced Research Projects Agency Network) TCP/IP (Transmission Control Protocol/Internet Protocol) NSFNET.
Jarek Nabrzyski, Ariel Oleksiak Comparison of Grid Middleware in European Grid Projects Jarek Nabrzyski, Ariel Oleksiak Poznań Supercomputing and Networking.
Loosely Coupled Parallelism: Clusters. Context We have studied older archictures for loosely coupled parallelism, such as mesh’s, hypercubes etc, which.
1-1.1 Sample Grid Computing Projects. NSF Network for Earthquake Engineering Simulation (NEES) 2004 – to date‏ Transform our ability to carry out research.
Evaluation of Agent Teamwork High Performance Distributed Computing Middleware. Solomon Lane Agent Teamwork Research Assistant October 2006 – March 2007.
10/24/2015OSG at CANS1 Open Science Grid Ruth Pordes Fermilab
Russ Hobby Program Manager Internet2 Cyberinfrastructure Architect UC Davis.
Service - Oriented Middleware for Distributed Data Mining on the Grid ,劉妘鑏 Antonio C., Domenico T., and Paolo T. Journal of Parallel and Distributed.
Interoperability Grids, Clouds and Collaboratories Ruth Pordes Executive Director Open Science Grid, Fermilab.
1a-1.1 Introduction to Grid Computing ITCS 4146/5146, UNC-Charlotte, B. Wilkinson, 2008 Aug 27, 2008.
Tools for collaboration How to share your duck tales…
Authors: Ronnie Julio Cole David
1 Barry Wilkinson University of North Carolina, Charlotte Clayton Ferner University of North Carolina, Wilmington NSF CCLI Showcase SIGCSE 2007 Friday,
SURAGrid Project Meeting Washington, DC Wednesday, February 22, 2006 Barry Wilkinson Department of Computer Science UNC-Charlotte SURAGrid and Grid Computing.
GRID Overview Internet2 Member Meeting Spring 2003 Sandra Redman Information Technology and Systems Center and Information Technology Research Center National.
Ruth Pordes November 2004TeraGrid GIG Site Review1 TeraGrid and Open Science Grid Ruth Pordes, Fermilab representing the Open Science.
NEES Cyberinfrastructure Center at the San Diego Supercomputer Center, UCSD George E. Brown, Jr. Network for Earthquake Engineering Simulation NEES TeraGrid.
1-1.1 Introduction to Grid Computing © 2011 B. Wilkinson/Clayton Ferner. Modification date: June 20, 2011.
Introduction to Grids By: Fetahi Z. Wuhib [CSD2004-Team19]
A scalable and flexible platform to run various types of resource intensive applications on clouds ISWG June 2015 Budapest, Hungary Tamas Kiss,
1 "Workshop 31: Developing a Hands-on Undergraduate Parallel Programming Course with Pattern Programming SIGCSE The 44 th ACM Technical Symposium.
Project Overview Dr Fredrik Hedman Royal Institute of Technology (PDC/KTH)
7. Grid Computing Systems and Resource Management
2005 GRIDS Community Workshop1 Learning From Cyberinfrastructure Initiatives Grid Research Integration Development & Support
Future Grid Future Grid Overview. Future Grid Future GridFutureGridFutureGrid The goal of FutureGrid is to support the research that will invent the future.
3/12/2013Computer Engg, IIT(BHU)1 PARALLEL COMPUTERS- 1.
Cloud Computing. new buzz word driven largely by marketing and service offerings Provided by big corporate players Google IBM Amazon Apple.
1 TCS Confidential. 2 Objective : In this session we will be able to learn:  What is Cloud Computing?  Characteristics  Cloud Flavors  Cloud Deployment.
1 Porting applications to the NGS, using the P-GRADE portal and GEMLCA Peter Kacsuk MTA SZTAKI Hungarian Academy of Sciences Centre for.
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
Northwest Indiana Computational Grid Preston Smith Rosen Center for Advanced Computing Purdue University - West Lafayette West Lafayette Calumet.
1 Open Science Grid: Project Statement & Vision Transform compute and data intensive science through a cross- domain self-managed national distributed.
A Brief history of the Internet Name:Ziyun Wang. Introduction Internet history revolves around four distinct aspects. 1. the technological evolution that.
Building on virtualization capabilities for ExTENCI Carol Song and Preston Smith Rosen Center for Advanced Computing Purdue University ExTENCI Kickoff.
Ian Bird, CERN WLCG Project Leader Amsterdam, 24 th January 2012.
Accessing the VI-SEEM infrastructure
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING CLOUD COMPUTING
Clouds , Grids and Clusters
Recap: introduction to e-science
Study course: “Computing clusters, grids and clouds” Andrey Y. Shevel
Grid Computing Course Development team: Barry Wilkinson and Clayton Ferner (Instructors), and Mark Holliday Student assistants: Jeff House and Sam Daoud.
Introduction to Grid Computing
eInfrastructure the international dimension
Defining the Grid Fabrizio Gagliardi EMEA Director Technical Computing
Presentation transcript:

Tutorial on Distributed High Performance Computing 14:30 – 19:00 (2:30 pm – 7:00 pm) Wednesday November 17, 2010 Jornadas Chilenas de Computación 2010 INFONOR-CHILE 2010 November 15th - 19th, 2010 Antofagasta, Chile Dr. Barry Wilkinson University of North Carolina Charlotte Oct 23, 2010 © Barry Wilkinson

2 Agenda Part – (2:30 pm – 4:30 pm) Review of distributed high performance computing landscape, cluster computing, grid computing, cloud computing, grid portals and toolkits, GPU computing for HPC, CUDA – (4:30 pm – 5:00 pm) Coffee Break Part – (5:00 pm – 7:00 pm) Grid computing infrastructure design, portal design, higher-level interfaces challenge of porting applications to a Grid. (Hands-one experience in Grid computing workshop)

Part – (2:30 pm – 4:30 pm) Distributed high performance computing landscape

4 Some Highlights of High Performance Computing Packet switched networks ARPNET Internet TCP TCP/IP Ethernet WWW Parallel Computers Cluster computing MPIPVM Condor Geographically distributed computing Grid computing HPC Cloud computing GPGPU cluster CUDA Globus Future HPC 1950 Term “Parallel Programming” (title of 1958 paper by Gill)

“The grid virtualizes heterogeneous geographically disperse resources” from "Introduction to Grid Computing with Globus," IBM Redbooks Using geographically distributed and interconnected computers together for computing and for resource sharing. Grid Computing

Grid Computing History Began in mid 1990s with experiments using computers at geographically dispersed sites. Seminal experiment – “I-way” experiment at 1995 Supercomputing conference (SC’95), using 17 sites across US running: – 60+ applications. – Existing networks (10 networks).

Need to harness computers Original driving force behind Grid computing same as behind the early development of networks that became the Internet: – Connecting computers at distributed sites for high performance computing.

However, Grid computing is about collaborating and resource sharing as much as it is about high performance computing.

Virtual Organizations Grid computing offers potential of virtual organizations: – groups of people, both geographically and organizationally distributed, working together on a problem, sharing computers AND other resources such as databases and experimental equipment.

Crosses multiple administrative domains. Hallmark of larger Grid computing projects. Resources being shared owned either by members of virtual organization or donated by others. Introduces challenging technical and social- political challenges. Requires true collaboration.

Key concepts in the history of Grid computing

Led by Ian Foster, a co- developer of I-Way demonstration, and founder of Grid computing concept. Globus -- middleware software Grid computing toolkit. Evolved through several implementation versions although basic components remained essentially same : Security, Data management Execution management Information services Run time environment) Globus Project 2010 home page

Although Globus widely adopted, there are other software infrastructure projects. Europe UNICORE (UNiform Interface to COmputing REsources) Initially funded by German Ministry for Education and Research. Continued with other European funding. Basis of several European efforts in Grid computing and elsewhere. Many similarities to Globus EGEE project (Enabling Grids for E-Science) Series of projects funded by European Commission, now ended Developed gLite, a middleware stack for Grid computing Other grid computing middleware software

14 Follow-on from EGEE Enabling Grids for E-sciencE ( )

Applications Originally e-Science applications – Computational intensive Traditional high performance computing addressing large problems Not necessarily one big problem but a problem that has to be solved repeatedly with different parameters. – Data intensive Computational but emphasis on large amounts of data to store and process – Experimental collaborative projects Now also e-Business applications – To improve business models and practices. – Sharing corporate computing resources and databases – On-demand Grid computing … indirectly led to cloud computing.

Grid Computing verse Cluster Computing Grid computing NOT simply a large cluster Potential and challenges different. Cluster Computing Message passing programming using tools such as MPI. Network security is not a big issue. Usually an ssh connection to front node of cluster sufficient. Computers under one administrative domain Grid computing Running jobs of remote machines, distributed workflow Internet technologies, web services,... Security is a big issue.

Grid Computing verse Cluster Computing Of course, there are things in common Both use multiple computers Both require job scheduler to place jobs.

Cloud computing Lot of hype on Cloud computing at the moment. Business model in which services provided on servers that can be accessed through Internet. Lineage of cloud computing can be traced back to on-demand Grid computing in the early 2000s.

Cloud computing using virtualized resources

Common thread between Grid computing and cloud computing is use of Internet to access resources. Cloud computing driven by widespread access that Internet provides and Internet technologies. However cloud computing quite distinct from original purpose of Grid computing. Cloud Computing

Grid Computing verse Cloud Computing Whereas Grid computing focuses on collaborative and distributed shared resources, Cloud computing concentrates upon placing services for users to pay to use. Technology for cloud computing emphases: – use of software as a service (SaaS)‏ – virtualization (process of separating particular user’s software environment from underlying hardware).

Sample Grid Computing Projects

NSF Network for Earthquake Engineering Simulation (NEES)‏ Sample projects in 2000 – 2010 period --- Environment/Earth

24

25

1a.27 ox.ac.uk/ Medicine/Biology Project period:

Project period: …

Large Hadron Collider experimental facility for complex particle experiments at CERN (European Center for Nuclear Research, near Geneva Switzerland). Development of grid started in 2002 and continuing Touted as the “World’s biggest computing grid” Physics CERN LCH Computing grid (LCG)‏

31

LCG depends on two major science grid infrastructures …. EGEE - Enabling Grids for E-Science OSG - US Open Science Grid From: LCG Overview - May Les Robertson,

Grid computing infrastructure projects Not tied to one specific application

TeraGrid circa 2004

TeraGrid (As of )

Open Science Grid (OSG) Started around 2005, received $30 million funding from NSF and DOE, 2006: Boston University Brookhaven National Laboratory California Institute of Technology Columbia University Cornell University Fermi National Accelerator Laboratory Indiana University Lawrence Berkeley National Laboratory Stanford Linear Accelerator Center University of California, San Diego University of Chicago University of Florida University of Iowa University of North Carolina/RENCI University of Wisconsin-Madison

37

Sept 2010

Southeastern Universities Research Association, SURAGrid

DEISA (Distributed European Infrastructure for Supercomputing Applications) DEISA – 2011 DEISA-2 1a.40 European centered multi-national Grid Example

Vision of a single universal international Grid such as the Internet/World Wide Web May never be achieved though. More likely - Grids will connect to other Grids but will maintain their identity. 1a.41

42 Our Grid Computing Course (University of North Carolina-Charlotte and University of North Carolina-Wilmington ) Taught on North Carolina Research and Education Network (NCREN) that connects all 16 state campuses and also private institutions  Fall 2004: 8 sites  Fall 2005: 12 sites  Spring 2007:3 sites  Fall 2008:5 sites  Spring 2010:8 sites Spring 2010 has 70+ students Figure 3 NCREN televideo classroom at the University of North Carolina Charlotte. 42

43

Break/questions