Problem Solving Environements WebPDELab Online Problem Solving Environment for Partial Differential Equations Applications: a Web Server for the PELLPACK.

Slides:



Advertisements
Similar presentations
Introduction To Java Objectives For Today â Introduction To Java â The Java Platform & The (JVM) Java Virtual Machine â Core Java (API) Application Programming.
Advertisements

RCAC Research Computing Presents: DiaGird Overview Tuesday, September 24, 2013.
Client Side Programming Using Java Applet Outcomes: You will be expected to know: – Java Applets and HTML file; –bytecode and platform independent programs;
1 Frameworks. 2 Framework Set of cooperating classes/interfaces –Structure essential mechanisms of a problem domain –Programmer can extend framework classes,
INTERNET DATABASE Chapter 9. u Basics of Internet, Web, HTTP, HTML, URLs. u Advantages and disadvantages of Web as a database platform. u Approaches for.
Interpret Application Specifications
Jun Peng Stanford University – Department of Civil and Environmental Engineering Nov 17, 2000 DISSERTATION PROPOSAL A Software Framework for Collaborative.
Slide 18-1 Copyright © 2004 Pearson Education, Inc. Operating Systems: A Modern Perspective, Chapter 18.
Web-based Portal for Discovery, Retrieval and Visualization of Earth Science Datasets in Grid Environment Zhenping (Jane) Liu.
Understanding and Managing WebSphere V5
1 Application Specific Module for P-GRADE Portal 2.7 Application Specific Module overview Akos Balasko MTA-SZTAKI LPDS
M. Taimoor Khan * Java Server Pages (JSP) is a server-side programming technology that enables the creation of dynamic,
FALL 2005CSI 4118 – UNIVERSITY OF OTTAWA1 Part 4 Web technologies: HTTP, CGI, PHP,Java applets)
Beyond DHTML So far we have seen and used: CGI programs (using Perl ) and SSI on server side Java Script, VB Script, CSS and DOM on client side. For some.
Introduction to ASP.NET. Prehistory of ASP.NET Original Internet – text based WWW – static graphical content  HTML (client-side) Need for interactive.
Meir Botner David Ben-David. Project Goal Build a messenger that allows a customer to communicate with a service provider for a fee.
ASP.NET  ASP.NET is a web development platform, which provides a programming model, a comprehensive software infrastructure and various services required.
Remote OMNeT++ v2.0 Introduction What is Remote OMNeT++? Remote environment for OMNeT++ Remote simulation execution Remote data storage.
@2011 Mihail L. Sichitiu1 Android Introduction Platform Overview.
Zhonghua Qu and Ovidiu Daescu December 24, 2009 University of Texas at Dallas.
The Old World Meets the New: Utilizing Java Technology to Revitalize and Enhance NASA Scientific Legacy Code Michael D. Elder Furman University Hayden.
Holding slide prior to starting show. A Grid-based Problem Solving Environment for GECEM Maria Lin and David Walker Cardiff University Yu Chen and Jason.
What is Android NDK ● A toolset that lets you embed in you app native source code ● C, C++(recently supported December 2010) and assembly(?) ● It is supported.
ASP.NET Web Application and Development Digital Media Department Unit Credit Value : 4 Essential Learning time : 120 hours Digital.
Company Overview for GDF Suez December 29, Enthought’s Business Enthought provides products and consulting services for scientific software solutions.
OpenSees on NEEShub Frank McKenna UC Berkeley. Bell’s Law Bell's Law of Computer Class formation was discovered about It states that technology.
Chapter 34 Java Technology for Active Web Documents methods used to provide continuous Web updates to browser – Server push – Active documents.
Java Introduction to JNI Prepared by Humaira Siddiqui.
SUMA: A Scientific Metacomputer Cardinale, Yudith Figueira, Carlos Hernández, Emilio Baquero, Eduardo Berbín, Luis Bouza, Roberto Gamess, Eric García,
Basic Security: Java vs.NET Master Seminar Advanced Software Engineering Topics Prof. Jacques Pasquier-Rocha Software Engineering Group Department of Informatics.
ITPA/IMAGE 7-10 May 2007 Software and Hardware Infrastructure for the ITM B.Guillerminet, on behalf of the ITM & ISIP teams (P Strand, F Imbeaux, G Huysmans,
1 Programming Fundamentals AITI-GP. 2 Introduction to Programming.
1 MSCS 237 Overview of web technologies (A specific type of distributed systems)
CSE S. Tanimoto Java Introduction 1 Java A Programming Language for Web-based Computing with Graphics.
Holding slide prior to starting show. A Portlet Interface for Computational Electromagnetics on the Grid Maria Lin and David Walker Cardiff University.
Framework for MDO Studies Amitay Isaacs Center for Aerospace System Design and Engineering IIT Bombay.
ICCS WSES BOF Discussion. Possible Topics Scientific workflows and Grid infrastructure Utilization of computing resources in scientific workflows; Virtual.
1 1 What does Performance Across the Software Stack mean?  High level view: Providing performance for physics simulations meaningful to applications 
Debugging parallel programs. Breakpoint debugging Probably the most widely familiar method of debugging programs is breakpoint debugging. In this method,
Web Pages with Features. Features on Web Pages Interactive Pages –Shows current date, get server’s IP, interactive quizzes Processing Forms –Serach a.
NEES Cyberinfrastructure Center at the San Diego Supercomputer Center, UCSD George E. Brown, Jr. Network for Earthquake Engineering Simulation NEES TeraGrid.
BOĞAZİÇİ UNIVERSITY DEPARTMENT OF MANAGEMENT INFORMATION SYSTEMS MATLAB AS A DATA MINING ENVIRONMENT.
Cracow Grid Workshop, November 5-6, 2001 Concepts for implementing adaptive finite element codes for grid computing Krzysztof Banaś, Joanna Płażek Cracow.
9-Nov-97Tri-Ada '971 TASH An Alternative to the Windows API TRI-Ada ‘97 Terry J. Westley
Connections to Other Packages The Cactus Team Albert Einstein Institute
Dispatching Java agents to user for data extraction from third party web sites Alex Roque F.I.U. HPDRC.
Satisfying Requirements BPF for DRA shall address: –DAQ Environment (Eclipse RCP): Gumtree ISEE workbench integration; –Design Composing and Configurability,
Application Specific Module Tutorial Zoltán Farkas, Ákos Balaskó 03/27/
Holding slide prior to starting show. Lessons Learned from the GECEM Portal David Walker Cardiff University
Grid Execution Management for Legacy Code Architecture Exposing legacy applications as Grid services: the GEMLCA approach Centre.
World Wide Web has been created to share the text document across the world. In static web pages the requesting user has no ability to interact with the.
1 Chapter 2: Operating-System Structures Services Interface provided to users & programmers –System calls (programmer access) –User level access to system.
A S P. Outline  The introduction of ASP  Why we choose ASP  How ASP works  Basic syntax rule of ASP  ASP’S object model  Limitations of ASP  Summary.
Hongbin Li 11/13/2014 A Debugger of Parallel Mutli- Agent Spatial Simulation.
Fermilab Scientific Computing Division Fermi National Accelerator Laboratory, Batavia, Illinois, USA. Off-the-Shelf Hardware and Software DAQ Performance.
CSE S. Tanimoto Java Introduction 1 Java A Programming Language for Web-based Computing.
Towards a High Performance Extensible Grid Architecture Klaus Krauter Muthucumaru Maheswaran {krauter,
January 26, Ann Wollrath Copyright 1999 Sun Microsystems, Inc., all rights reserved. Java ™ RMI Overview Ann Wollrath Senior Staff Engineer Sun Microsystems,
Chapter 5 Operating Systems.
VisIt Project Overview
A Programming Language for Web-based Computing with Graphics
Alternatives to Mobile Agents
Introduction to Operating System (OS)
University of Technology
Survey Paper & Manuscript
Web App vs Mobile App.
CS-0401 INTERMEDIATE PROGRAMMING USING JAVA
The Arabica Project A distributed scientific computing project based on a cluster computer and Java technologies. Daniel D. Warner Dept. of Mathematical.
A Programming Language for
MPJ: A Java-based Parallel Computing System
Presentation transcript:

Problem Solving Environements WebPDELab Online Problem Solving Environment for Partial Differential Equations Applications: a Web Server for the PELLPACK PSE GasTurbnLab Multidisciplinary Agent-based Problem Solving Environment for the Distributed Network Simulation of Gas Turbine Engines

PELLPACK A Problem Solving Environment for PDE Applications Sophisticated, comprehensive system for modeling physical objects described by Partial Differential Equations Used by hundreds of students and faculty at Purdue University, nationally and internationally over the past decade Applications include physics, liquid crystal droplets, proton flux propagation, thermal field analysis, fluid dynamics, semiconductors, geophysical research, electromagnetic field analysis, thermo-elasticity, structural analysis, and many other scientific and engineering areas

PELLPACK The Layered Structure

PELLPACK The Complexity of System Installation X-Windows & OSF/Motif libraries, Fortran/C compilers, Tcl/Tk, PERL, f2c variousSystem Software Maxima,Cadsol,Fidisol, Vecfem,Linpack,Pdecol, Nsc2ke, Pdeone,Nspcg, Sparskit, Geompack, Qmg, mpi, pvm ~1.5 million C, C++, Fortran, Lisp, Mac Public Domain & Copyrighted Software Language processing, PELLPACK solvers, “foreign” interfaces sequential: 3MB parallel : 8MB 255,000Fortran, C, custom parser Infrastructure & Numerical Libraries programs for building, executing & visualizing PDE problems non-static: 6.3MB static: 22.3MB 172,000C, C++, Tcl/Tk, Mac, Flex, Bison Graphical User Interface DescriptionSize Lines of Code Programming Languages PELLPACK Component

WebPDELab Online PELLPACK Problem Solving Environment Complete Internet-based support for sequential & parallel PDE computing from any Java-enabled browser Backed by 16 CPU Intel cluster connected through an Intel Express510t switch with Intel Ether Express Pro 100NICs at 100MB Users define, solve and analyze PDE problems supported by an interactive GUI for problem definition & visualization, with full access to the PELLPACK libraries of PDE solvers Implemented using VNC remote display for the PELLPACK X- windows programs compiled on an i86pc SunOS 5.6 machine

WebPDELab Usage Statistics for Server Access

WebPDELab Implementation of an Online PDE PSE PELLPACK PELLPACK Security Wrapper VNC Server WebPDELab Manager WebPDELab - VNC interface USER VNC viewer Java enabled browser HTTP CGI Two 16 CPU i86pc Clusters Server Security Wrapper

WebPDELab The Network Scenario Start with user PDE Problem Upload: geometry data Interactively: define & solve problem Download: solution & graphics files User’s Web Browser data file handler on server machine PDELab GUI sequential & parallel computing across the grid File Download VNC server WebPDELab server Intel cluster for sequential and parallel program execution secure cross-network File Upload

Gas Turbine Engine Simulation

GasTurbnLab Multi-disciplinary Problem Solving Environment Geometric decomposition of target simulation object defines a network of PDE problems Specialized PDE solvers (legacy code) model the physics on each geometric domain Domain interfaces are handled by mediators Goal: generalize framework & templates for an agent- based distributed network implementation of an MPSE

GasTurbnLab The Network Scenario Region Registry ControlAgent : socket:// :7020/Agency1 LegacyAgent : socket:// :7020/Agency2 MediatorAgent: socket:// :7020/Agency3 … Region ControlAgent at Agency1 LegacyAgent at Agency8 LegacyAgent at Agency2 MediatorAgent at Agency3 Agencies distributed across the Computational Grid Mobile FileAgent Mediated Data Object Mobile FileAgent Mediated Data Object Mediated Data Object Cross-network

GasTurbnLab The Agent-based Infrastructure Grasshopper Platform ModelingAgent Simulation ControlAgent LegacyAgent MediatorAgent LegacyAgent VisualizerAgent Iris Explorer Platform ResourceAgentDatabaseAgent Graphical User Interface Computational Agents Service Agents

GasTurbnLab Prototype Results from the VisualizerAgent

GasTurbnLab Framework for Implementing the LegacyAgent Java data object to/from network simulation controller C data Java Agent Wrapper C Wrapper Fortran Legacy Code Fortran --- C I/O Transfer across JNI interface Fortran-C data transfer for mediated data Java-C data transfer for mediated data

GasTurbnLab Template for the Java Agent Wrapper // TEMPLATE: Java Agent Wrapper for C-wrapped Legacy Code public class LegacyAgent extends MobileAgent implements ILegacyAgent { int startup, ret, render; SerialData sData; // Load library containing legacy code, C wrapper, legacy-wrapper data interface static { System.loadLibrary(“LegacyWrapper”); ) public native int LegacyWrapper(int startup, int render, ); // IO iteration Java-To-C interface public SerialData requestConfirmation( int domain, SerialData sd, int Render, ) throws agentException { int startup=1; ret=1; Render=0; if (startup > 1) { copyData (sd); } // create Java data object at every IO iteration ret=LegacyWrapper(startup,Render, ); // call C wrapper dp {} while (ret==1); startup++; } public void CopyData( SerialData sd) { } // C data -> Java object }

GasTurbnLab C Wrapper Template for the Legacy Code // TEMPLATE: C Wrapper for Legacy Code struct {int wrapperSleep; int legacySleep; } // execution control struct { } // legacy mediator data static void CopyData(jenv, this, start, type, render) // C struct to Java object at return to agent { } // Java object to C struct on return from agent JNIEXPORT jint JNICALL Java_LegacyAgent_LegacyWrapper (JNIEnv *env, jobject this, jint startup, jint render, ) {}}} { int i, ret; thread_t thr; if (startup == 1) { if ( ret == thr_create( NULL, 0, thread, NULL, THR_DETACHED, &thr)) != 0) // start legacy thread exit(1); } else { CopyData(jenv, this JavaToC ); } // copy mediated data from Java to C control.wrapperSleep=1; control.legacySleep=0; // wrapper sleeps while legacy code executes while (control.wrapperSleep) (sleep(1)); CopyData (jenv, this, startup, CToJava, render); // copy mediated data from C to Java and return(0); // return to agent }

// TEMPLATE: C code for transfer of I/O data from Fortran to C extern struct {int wrapperSleep; int legacySleep; } // execution control extern struct { } // legacy mediator data /* called from inside Fortran legacy code at I/O iteration location where mediated data is needed */ void legacyDataIO ( ) { CopyFortran2C ( ); // copy Fortran data to C struct control.legacySleep=1; control.wrapperSleep=0; // wake wrapper and while (control.legacySleep) {sleep(1) } // resume at return from agent CopyC2Fortran ( ); // copy C struct to Fortran } GasTurbnLab Template for the Data Transfer: Fortran C

GasTurbnLab Template for Legacy Code Modifications  From a Fortran executable… The Fortran “main” is changed to a subroutine with arguments passed as parameters This subroutine is started as a “thread” from the C wrapper A call to the I/O data transfer routine is inserted into the Fortran iteration loop The Fortran code, C routine for I/O transfer, and the C wrapper are compiled together as a library & loaded into the Java agent  To a C-wrapped Legacy Code Library

GasTurbnLab Agents and the MPSE Simulation Completed: AleAgent for simulating rotor and stator domains, KivaAgent for simulating combustor domain & two MediatorAgents for interface data interpolation of rotor-stator and stator-combustor Completed: SCA to control total simulation process for any number and type of domains & VisualizerAgent to view intermediate and final results Verified: mediated stator-rotor simulation, mediated stator-combustor simulation