© 2008 The MathWorks, Inc. ® ® Parallel Computing with MATLAB ® Silvina Grad-Freilich Manager, Parallel Computing Marketing

Slides:



Advertisements
Similar presentations
Lean Powertrain Development Sam Akehurst, University of Bath, Powertrain & Vehicle Research Centre Funded Under EPSRC Project Codes EP/C540883/1 & EP/C540891/1EP/C540883/1EP/C540891/1.
Advertisements

Issues of HPC software From the experience of TH-1A Lu Yutong NUDT.
SkewReduce YongChul Kwon Magdalena Balazinska, Bill Howe, Jerome Rolia* University of Washington, *HP Labs Skew-Resistant Parallel Processing of Feature-Extracting.
SLA-Oriented Resource Provisioning for Cloud Computing
VoipNow Core Solution capabilities and business value.
Information Technology Center Introduction to High Performance Computing at KFUPM.
RCAC Research Computing Presents: DiaGird Overview Tuesday, September 24, 2013.
Presented by Scalable Systems Software Project Al Geist Computer Science Research Group Computer Science and Mathematics Division Research supported by.
Introduction CS 524 – High-Performance Computing.
6/2/20071 Grid Computing Sun Grid Engine (SGE) Manoj Katwal.
HPC Technical Workshop Björn Tromsdorf Product & Solutions Manager, Microsoft EMEA London
High Performance Computing (HPC) at Center for Information Communication and Technology in UTM.
Anne Mascarin DSP Marketing The MathWorks
© 2011 Xilinx, Inc. All Rights Reserved Intro to System Generator This material exempt per Department of Commerce license exception TSU.
1 Down Place Hammersmith London UK 530 Lytton Ave. Palo Alto CA USA.
Parallelization with the Matlab® Distributed Computing Server CBI cluster December 3, Matlab Parallelization with the Matlab Distributed.
1 1 Hybrid Cloud Solutions (Private with Public Burst) Accelerate and Orchestrate Enterprise Applications.
Venkatram Ramanathan 1. Motivation Evolution of Multi-Core Machines and the challenges Background: MapReduce and FREERIDE Co-clustering on FREERIDE Experimental.
4.x Performance Technology drivers – Exascale systems will consist of complex configurations with a huge number of potentially heterogeneous components.
1 Advanced Storage Technologies for High Performance Computing Sorin, Faibish EMC NAS Senior Technologist IDC HPC User Forum, April 14-16, Norfolk, VA.
© 2005 The MathWorks December 2 nd, 2005 MATLAB ® and HDF Accelerating Engineering Productivity and Scientific Discovery.
Introduction to M ATLAB EE 100 – EE Dept. - JUST.
© 2002 The MathWorks, Inc. September 2002 Advanced Embedded Tool capabilities for Texas Instruments DSPs © 2002 The MathWorks, Inc. David Hilf Third Party.
Windows 2000 Advanced Server and Clustering Prepared by: Tetsu Nagayama Russ Smith Dale Pena.
Hussein Suleman University of Cape Town Department of Computer Science Advanced Information Management Laboratory High Performance.
1 © 2014 The MathWorks, Inc. HPC with MATLAB Making parallel programming simple Jos Martin, Principal Architect, Parallel Computing Tools
BalticGrid-II Project MATLAB implementation and application in Grid Ilmars Slaidins, Lauris Cikovskis Riga Technical University AHM Riga May 12-14, 2009.
March 3rd, 2006 Chen Peng, Lilly System Biology1 Cluster and SGE.
material assembled from the web pages at
f ACT s  Data intensive applications with Petabytes of data  Web pages billion web pages x 20KB = 400+ terabytes  One computer can read
Cluster Workstations. Recently the distinction between parallel and distributed computers has become blurred with the advent of the network of workstations.
Parallel Computing with Matlab CBI Lab Parallel Computing Toolbox TM An Introduction Oct. 27, 2011 By: CBI Development Team.
1 © 2012 The MathWorks, Inc. Parallel computing with MATLAB.
Taking the Complexity out of Cluster Computing Vendor Update HPC User Forum Arend Dittmer Director Product Management HPC April,
Loosely Coupled Parallelism: Clusters. Context We have studied older archictures for loosely coupled parallelism, such as mesh’s, hypercubes etc, which.
4.2.1 Programming Models Technology drivers – Node count, scale of parallelism within the node – Heterogeneity – Complex memory hierarchies – Failure rates.
HeuristicLab Hive An Open Source Environment for Parallel and Distributed Execution of Heuristic Optimization Algorithms S. Wagner, C. Neumüller, A. Scheibenpflug.
High Performance Computing on Virtualized Environments Ganesh Thiagarajan Fall 2014 Instructor: Yuzhe(Richard) Tang Syracuse University.
Grid Computing at The Hartford Condor Week 2008 Robert Nordlund
BOF: Megajobs Gracie: Grid Resource Virtualization and Customization Infrastructure How to execute hundreds of thousands tasks concurrently on distributed.
GVis: Grid-enabled Interactive Visualization State Key Laboratory. of CAD&CG Zhejiang University, Hangzhou
Scalable Systems Software for Terascale Computer Centers Coordinator: Al Geist Participating Organizations ORNL ANL LBNL.
A scalable and flexible platform to run various types of resource intensive applications on clouds ISWG June 2015 Budapest, Hungary Tamas Kiss,
Software Development in HPC environments: A SE perspective Rakan Alseghayer.
EGEE-III INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Enabling the use of e-Infrastructures with.
International Symposium on Grid Computing (ISGC-07), Taipei - March 26-29, 2007 Of 16 1 A Novel Grid Resource Broker Cum Meta Scheduler - Asvija B System.
+ Clusters Alternative to SMP as an approach to providing high performance and high availability Particularly attractive for server applications Defined.
Copyright © 2012, SAS Institute Inc. All rights reserved. SAS ® GRID AT PHAC SAS OTTAWA PLATFORM USERS SOCIETY, NOVEMBER 2012.
Interconnect Trends in High Productivity Computing Actionable Market Intelligence for High Productivity Computing Addison Snell, VP/GM,
1 © 2014 The MathWorks, Inc. Scaling MATLAB applications to the bwHPC project Dr. Marek Dynowski – HPC Manager, Tübingen University Head of HPC-Competence.
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
EGEE-III INFSO-RI Enabling Grids for E-sciencE Nov. 18, EGEE and gLite are registered trademarks High-End Computing - Clusters.
Multicore Applications in Physics and Biochemical Research Hristo Iliev Faculty of Physics Sofia University “St. Kliment Ohridski” 3 rd Balkan Conference.
Implementation of Classifier Tool in Twister Magesh khanna Vadivelu Shivaraman Janakiraman.
Leverage Big Data With Hadoop Analytics Presentation by Ravi Namboori Visit
EMC: Redefining ERP and ROI with a Virtualized SAP HANA® Deployment
Productive Performance Tools for Heterogeneous Parallel Computing
Organizations Are Embracing New Opportunities
Big Data is a Big Deal!.
Early Results of Deep Learning on the Stampede2 Supercomputer
Structural Simulation Toolkit / Gem5 Integration
Grid Computing Colton Lewis.
Grid Services For Virtual Organizations
NGS computation services: APIs and Parallel Jobs
Overview of the Course Copyright 2003, Keith D. Cooper, Ken Kennedy & Linda Torczon, all rights reserved. Students enrolled in Comp 412 at Rice University.
Cray Announces Cray Inc.
Learn about MATLAB Engineers – not sales!
SCALABLE OPEN ACCESS Hussein Suleman
Early Results of Deep Learning on the Stampede2 Supercomputer
Building and running HPC apps in Windows Azure
Presentation transcript:

© 2008 The MathWorks, Inc. ® ® Parallel Computing with MATLAB ® Silvina Grad-Freilich Manager, Parallel Computing Marketing

© 2007 IDC Some Customer Pain Points Clusters are still hard to use and manage  Power, cooling and floor space are major issues  Third party software costs  Weak interconnect performance at all levels  Applications & programming — Hard to scale beyond a node  RAS is a growing issue  Storage and data management  Multi-processor type support and accelerator support Requirements are diverging  High-end — need more, but is a shrinking segment  Mid and lower end – the mainstream will look more for complete solutions  New entrants – ease-of-use will drive them, plus need applications Parallel software is missing for most users  And will get weaker in the near future—Software will be the #1 roadblock  Multi-core will cause many issues to “hit-the-wall” Hard to scale beyond a node Parallel software is missing for most users …. Software will be the #1 roadblock

3 ® ® TM Headquarters: Natick, Massachusetts US Revenues ~$450M in 2007 Privately held Over 1,800 employees worldwide More than 1,000,000 users in 175+ countries The MathWorks at a Glance Earth’s topography on an equidistant cylindrical projection, created with MATLAB ® and Mapping Toolbox ™.

4 ® ® TM MathWorks Product Family Overview MATLAB Product Family View full product list Simulink Product FamilyApplication-Specific Products

5 ® ® TM Three User Communities Easier programming C Fortran Higher data volumes & compute intensity Technical Computing User PERSONAL SUPERCOMPUTING WITH MATLAB Cluster Administrator Optimal Hardware and License Use HPC User

6 ® ® Using Fortran and MPI Using MATLAB and MPI Using Distributed Arrays P>> D = distributed(A) P>> E = D’ Easier Parallel Programming Example: Transposing a Distributed Matrix

7 ® ® Parallel Computing with MATLAB ® Parallel Computing Toolbox™ T OOLBOXES B LOCKSETS Computer Cluster CPU MATLAB Distributed Computing Server Scheduler Worker

8 ® ® Toolbox Support: Optimization Toolbox™ Genetic Algorithm and Direct Search Toolbox™ SystemTest™ parfor job and tasks No code changes Trivial changes Extensive changes Task Parallel Data Parallel darray MATLAB and MPI Parallel Computing with MATLAB ®

9 ® ® Support in Optimization Toolbox

10 ® ® Distributing Tasks (Task Parallel) Time Processes

11 ® ®

12 Argonne National Laboratory Develops Powertrain Systems Analysis Toolkit with MathWorks ™ Tools Challenge To evaluate designs and technologies for hybrid and fuel cell vehicles Solution Use MathWorks tools to model advanced vehicle powertrains and accelerate the simulation of hundreds of vehicle configurations Results  Distributed simulation environment developed in one hour  Simulation time reduced from two weeks to one day  Simulation results validated using vehicle test data “We developed an advanced framework and scalable powertrain components in Simulink ®, designed controllers with Stateflow ®, automated the assembly of models with MATLAB ® scripts, and then distributed the complex simulation runs on a computing cluster – all within a single environment." Sylvain Pagerit Argonne National Laboratory “We developed an advanced framework and scalable powertrain components in Simulink ®, designed controllers with Stateflow ®, automated the assembly of models with MATLAB ® scripts, and then distributed the complex simulation runs on a computing cluster – all within a single environment." Sylvain Pagerit Argonne National Laboratory Vehicle model created with PSAT.

13 ® ® Large Data Sets (Data Parallel)

14 ® ®

15 ® ® Batch Execution >> createMatlabPoolJob

16 ® ® Run Four Local Workers with a Parallel Computing Toolbox License  Easily experiment with explicit parallelism on multicore machines  Rapidly develop parallel applications on local computer Parallel Computing Toolbox

17 ® ® Scale Up to Cluster Configuration with No Code Changes Parallel Computing Toolbox Computer Cluster MATLAB Distributed Computing Server Scheduler CPU Worker

18 ® ® Computer Cluster Scheduler Dynamic Licensing CPU Worker

19 ® ® Computer Cluster Scheduler CPU Worker Dynamic Licensing

20 ® ® Computer Cluster Scheduler CPU Worker Dynamic Licensing

21 ® ® Computer Cluster Scheduler CPU Worker Dynamic Licensing

22 ® ® Open API for generic schedulers Support for Third-Party Schedulers

23 ® ® Summary  Back to the pains…  Hard to scale beyond a node  Parallel software is missing for most users  The power of supercomputing is now accessible to thousands of engineers and scientists  MATLAB users - delivering the power of HPC  HPC users - delivering the benefits of MATLAB

© 2008 The MathWorks, Inc. ® ® Thank you! Silvina Grad-Freilich