Adventures in Mastering the Use of Performance Evaluation Tools Manuel Ríos Morales ICOM 5995 December 4, 2002.

Slides:



Advertisements
Similar presentations
Performance Analysis Tools for High-Performance Computing Daniel Becker
Advertisements

.NET Technology. Introduction Overview of.NET What.NET means for Developers, Users and Businesses Two.NET Research Projects:.NET Generics AsmL.
Module 13: Performance Tuning. Overview Performance tuning methodologies Instance level Database level Application level Overview of tools and techniques.
IcePro Source Code Management Source code analysis Runtime analysis Application deployment Source code generation Multi sites Click ! IcePro.
Μπ A Scalable & Transparent System for Simulating MPI Programs Kalyan S. Perumalla, Ph.D. Senior R&D Manager Oak Ridge National Laboratory Adjunct Professor.
Module 7: Advanced Development  GEM only slides here  Started on page 38 in SC09 version Module 77-0.
Intel® performance analyze tools Nikita Panov Idrisov Renat.
Programming Mobile Applications with Android
Systems Analysis, Prototyping and Iteration Systems Analysis.
Seminar On “ OMNET++ Network Simulator” Presented By: Saurav K Bengani Guided By: Guided By: Dr. Andrew yang Dr. Andrew yang.
Automated Instrumentation and Monitoring System (AIMS)
Lecture 1 Introduction to the ABAP Workbench
The Path to Multi-core Tools Paul Petersen. Multi-coreToolsThePathTo 2 Outline Motivation Where are we now What is easy to do next What is missing.
Fundamentals of Information Systems, Second Edition
Supplement 02CASE Tools1 Supplement 02 - Case Tools And Franchise Colleges By MANSHA NAWAZ.
The shift from sequential to parallel and distributed computing is of fundamental importance for the advancement of computing practices. Unfortunately,
Intel Trace Collector and Trace Analyzer Evaluation Report Hans Sherburne, Adam Leko UPC Group HCS Research Laboratory University of Florida Color encoding.
1 The VAMPIR and PARAVER performance analysis tools applied to a wet chemical etching parallel algorithm S. Boeriu 1 and J.C. Bruch, Jr. 2 1 Center for.
Microsoft ® Official Course Monitoring and Troubleshooting Custom SharePoint Solutions SharePoint Practice Microsoft SharePoint 2013.
Chapter 2-Introduction to Making Multimedia
OpenTS for Windows Compute Cluster Server. Overview  Introduction  OpenTS (academic) for Windows CCS  T-converter  T-microkernel  OpenTS installer.
“SEMI-AUTOMATED PARALLELISM USING STAR-P " “SEMI-AUTOMATED PARALLELISM USING STAR-P " Dana Schaa 1, David Kaeli 1 and Alan Edelman 2 2 Interactive Supercomputing.
 2002 Prentice Hall. All rights reserved. 1 Introduction to Visual Basic.NET,.NET Framework and Visual Studio.NET Outline 1.7Introduction to Visual Basic.NET.
SUSE Linux Enterprise Server Administration (Course 3037) Chapter 4 Manage Software for SUSE Linux Enterprise Server.
1 Performance Analysis with Vampir DKRZ Tutorial – 7 August, Hamburg Matthias Weber, Frank Winkler, Andreas Knüpfer ZIH, Technische Universität.
Paradyn Week – April 14, 2004 – Madison, WI DPOMP: A DPCL Based Infrastructure for Performance Monitoring of OpenMP Applications Bernd Mohr Forschungszentrum.
WORK ON CLUSTER HYBRILIT E. Aleksandrov 1, D. Belyakov 1, M. Matveev 1, M. Vala 1,2 1 Joint Institute for nuclear research, LIT, Russia 2 Institute for.
ICOM 5995: Performance Instrumentation and Visualization for High Performance Computer Systems Lecture 7 October 16, 2002 Nayda G. Santiago.
Chapter 11: Introduction to the Visual Basic Environment Spreadsheet-Based Decision Support Systems Prof. Name Position (123) University.
DIFFERENCE BETWEEN ORCAD AND LABVIEW
Lecture 8. Profiling - for Performance Analysis - Prof. Taeweon Suh Computer Science Education Korea University COM503 Parallel Computer Architecture &
Analyzing parallel programs with Pin Moshe Bach, Mark Charney, Robert Cohn, Elena Demikhovsky, Tevi Devor, Kim Hazelwood, Aamer Jaleel, Chi- Keung Luk,
TRACEREP: GATEWAY FOR SHARING AND COLLECTING TRACES IN HPC SYSTEMS Iván Pérez Enrique Vallejo José Luis Bosque University of Cantabria TraceRep IWSG'15.
FotoGazmic Software (From left to right: Chad Zbinden, Josey Baker, Rob Mills, Myra Bergman, Tinate Dejtiranukul)
The Vampir Performance Analysis Tool Hans–Christian Hoppe Gesellschaft für Parallele Anwendungen und Systeme mbH Pallas GmbH Hermülheimer Straße 10 D
VAMPIR. Visualization and Analysis of MPI Resources Commercial tool from PALLAS GmbH VAMPIRtrace - MPI profiling library VAMPIR - trace visualization.
CS 584. Performance Analysis Remember: In measuring, we change what we are measuring. 3 Basic Steps Data Collection Data Transformation Data Visualization.
1 Chapter 13 Understanding Computers, 11 th Edition 13 Program Development and Programming Languages TODAY AND TOMORROW 11 th Edition CHAPTER.
Interfaces to External EDA Tools Debussy Denali SWIFT™ Course 12.
Martin Schulz Center for Applied Scientific Computing Lawrence Livermore National Laboratory Lawrence Livermore National Laboratory, P. O. Box 808, Livermore,
1 Performance Analysis with Vampir ZIH, Technische Universität Dresden.
Developing software and hardware in parallel Vladimir Rubanov ISP RAS.
Profiling, Tracing, Debugging and Monitoring Frameworks Sathish Vadhiyar Courtesy: Dr. Shirley Moore (University of Tennessee)
Fundamentals of Information Systems, Second Edition 1 Systems Development.
ASC Tri-Lab Code Development Tools Workshop Thursday, July 29, 2010 Lawrence Livermore National Laboratory, P. O. Box 808, Livermore, CA This work.
Portable Parallel Performance Tools Shirley Browne, UTK Clay Breshears, CEWES MSRC Jan 27-28, 1998.
Belgrade, 25 September 2014 George S. Markomanolis, Oriol Jorba, Kim Serradell Performance analysis Tools: a case study of NMMB on Marenostrum.
Debugging parallel programs. Breakpoint debugging Probably the most widely familiar method of debugging programs is breakpoint debugging. In this method,
3 Copyright © 2004, Oracle. All rights reserved. Working in the Forms Developer Environment.
A record and replay mechanism using programmable network interface cards Laurent Lefèvre INRIA / LIP (UMR CNRS, INRIA, ENS, UCB)
Comparative Study of Parallel Performance Visualization Tools By J. Ramphis Castro December 4, 2002.
Tool Visualizations, Metrics, and Profiled Entities Overview [Brief Version] Adam Leko HCS Research Laboratory University of Florida.
The shift from sequential to parallel and distributed computing is of fundamental importance for the advancement of computing practices. Unfortunately,
Chapter 11: Introduction to VBA Spreadsheet-Based Decision Support Systems Prof. Name Position (123) University Name.
Overview of AIMS Hans Sherburne UPC Group HCS Research Laboratory University of Florida Color encoding key: Blue: Information Red: Negative note Green:
Click to add text Systems Analysis, Prototyping and Iteration.
SAP DEVELOPMENT BASICS Bohuslav Tesar. TRAINING OVERVIEW Amazing life of ABAP developer ;) SAP introduction ABAP basics ABAP Reporting.
Chapter – 8 Software Tools.
15 Copyright © 2004, Oracle. All rights reserved. Debugging Triggers.
Projections - A Step by Step Tutorial By Chee Wai Lee For the 2004 Charm++ Workshop.
BROADCAST MASTER APPLICATION OVERVIEW. Overview Broadcast Master is a complete Channel Management and Ad Sales system providing the ability to manage.
Parallel Performance Wizard: A Generalized Performance Analysis Tool Hung-Hsun Su, Max Billingsley III, Seth Koehler, John Curreri, Alan D. George PPW.
Introduction to Visual Basic. NET,. NET Framework and Visual Studio
Chapter 2-Introduction to Making Multimedia
J. Michael, M. Shing M. Miklaski, J. Babbitt Naval Postgraduate School
Performance Analysis, Tools and Optimization
Chapter 7 –Implementation Issues
Chapter 2-Introduction to Making Multimedia
Presentation transcript:

Adventures in Mastering the Use of Performance Evaluation Tools Manuel Ríos Morales ICOM 5995 December 4, 2002

Overview  Project Proposal Original Goals Problems Encountered  Project Changes Revised Goals New Problems  Final Revision

Project Proposal  Original Goals Master a performance evaluation tool and use it to evaluate the performance of an existing benchmark. Tool selected: AIMS Benchmark: FT kernel of the NPB  Why AIMS? Provides tools for measurement and analysis of performance of parallel programs. Can be used to highlight problem areas that can be modified to improve program execution.

Problems Encountered  Installation Quite challenging Required modification of makefiles and debugging of some modules  Instrumentation Couldn’t be achieved due to bugs in the software.

Problems Encountered (cont.)

Project Changes  Revised Goals Performance evaluation tool changed to Vampir.  New Problems Compilation of the FT benchmark Installation of VampirTrace

Final Revision  Project goals Understanding basic features of Vampir with the use of an example provided in the Vampir package.

Vampir Analysis Tool  Vampir consists of two packages: Vampir: Tracefile visualization program with a graphical user interface for XWindows desktops. VampirTrace: Instrumented MPI library to link with the user code for automatic tracefile generation on a parallel platform.

VampirTrace  Tool for MPI applications that produces tracefiles that can be analyzed with Vampir.  Records all calls to the MPI library and all transmitted messages.  Allows defining and recording arbitrary user defined events.  Using it requires relinking the application with the VampirTrace profiling library.

VampirTrace (cont.)  mpicc -o test test.c -L/$HOME/VampirTrace/lib/libVT.a –lVT  patch_mpicc Modifies mpicc command to include the –vt option  Mpicc –vt –o test test.c

Vampir  Tool for visualization and analysis of MPI programs  Understand the application behavior  Analyze the performance of subroutines or code blocks  Learn about communication patterns, parameters and performance  Identify communication hotspots

Vampir (cont.)  Basics Loading Tracefiles Displays

Global Timeline Display

Global Timeline Display (cont.)  It will automatically open when paused or finished loading a tracefile.  Shows all analyzed state changes for each process over the complete period of time in one display.  Zoom ability allows getting detailed information of the runtime behavior of the traced program.

Activity Chart Display  Shows a statistic about the time spent in each activity individually for each process defined in the tracefile.

Summary Chart Display  Displays the sum of the time consumed by all instrumented activities over all selected processes.

Final Thoughts  Tools that facilitate the instrumentation and visualization of parallel program execution are invaluable.  Programmers can benefit from using these tools since the help highlight any problem areas that can be modified to improve program execution.