Creating a Parallel Program to Compute Statistical Information Victoria Sensano Maui Scientific Research Center Research Supervisor: Douglas Hope.

Slides:



Advertisements
Similar presentations
Built-In Test Software for Deformable Mirror High Voltage Drivers Built-In Test Software for Deformable Mirror High Voltage Drivers Jianwei Zhou Home Institution:
Advertisements

Teaching Courses in Scientific Computing 30 September 2010 Roger Bielefeld Director, Advanced Research Computing.
CISC October Goals for today: Foster’s parallel algorithm design –Partitioning –Task dependency graph Granularity Concurrency Collective communication.
Darcy Bibb Oceanit Mentor: Tony Bartnicki Advisor: Curt Leonard Home Institution: Maui Community College Integration of a Small Telescope System for Space.
4/26/05Han: ELEC72501 Department of Electrical and Computer Engineering Auburn University, AL K.Han Development of Parallel Distributed Computing System.
1 Multi - Core fast Communication for SoPC Multi - Core fast Communication for SoPC Technion – Israel Institute of Technology Department of Electrical.
1 Built-In Test Software for Deformable Mirror High Voltage Drivers Jianwei Zhou Home Institution: University of Hawaii at Manoa CfAO Akaimai Intership.
Mirror Deformation Modeling for HANDS (High Accuracy Network Determination System) Jeremy Steel Mentors: Scott Gregory Curt Leonard.
Design and Implementation of a Single System Image Operating System for High Performance Computing on Clusters Christine MORIN PARIS project-team, IRISA/INRIA.
18.337: Image Median Filter Rafael Palacios Aeronautics and Astronautics department. Visiting professor (IIT-Institute for Research in Technology, University.
1 Mapping Maui’s Major Roads With Global Positioning System Devices Augustus Elias Center for Adaptive Optics Pacific Disaster Center Mentor: Pam Cowher.
Parallel Adaptive Mesh Refinement Combined With Multigrid for a Poisson Equation CRTI RD Project Review Meeting Canadian Meteorological Centre August.
‘Tis not folly to dream: Using Molecular Dynamics to Solve Problems in Chemistry Christopher Adam Hixson and Ralph A. Wheeler Dept. of Chemistry and Biochemistry,
Venkatram Ramanathan 1. Motivation Evolution of Multi-Core Machines and the challenges Background: MapReduce and FREERIDE Co-clustering on FREERIDE Experimental.
Yavor Todorov. Introduction How it works OS level checkpointing Application level checkpointing CPR for parallel programing CPR functionality References.
Testing and Fine-Tuning HANDS’ Automated Photometric Pipeline Austin Barnes Oceanit Mentor: Russell Knox Advisors: Rita Cognion and Curt Leonard Home Institution:
Increasing Image Transfer Speed In MSAT Through Image Compression David Elies Akimeka, LLC Advisor: Steve Schweibinz Mentor: Rob Reed.
A Parallelisation Approach for Multi-Resolution Grids Based Upon the Peano Space-Filling Curve Student: Adriana Bocoi Advisor: Dipl.-Inf.Tobias Weinzierl.
Characterization of Solar Cells Mary Liang Center for Adaptive Optics, Akamai Internship at Hnu Photonics Mentor: Dan O’Connell Home Institution: University.
ICOM 5995: Performance Instrumentation and Visualization for High Performance Computer Systems Lecture 7 October 16, 2002 Nayda G. Santiago.
Tools and Utilities for parallel and serial codes in ENEA-GRID environment CRESCO Project: Salvatore Raia SubProject I.2 C.R. ENEA-Portici. 11/12/2007.
1 Automated Installation Windows Unattended Client PC Setup Vahid Ajimine W.M. Keck Observatory Mentor: Jason Ward Home institution: University of Hawaii.
A Metadata Based Approach For Supporting Subsetting Queries Over Parallel HDF5 Datasets Vignesh Santhanagopalan Graduate Student Department Of CSE.
Appraisal and Data Mining of Large Size Complex Documents Rob Kooper, William McFadden and Peter Bajcsy National Center for Supercomputing Applications.
PET Summer Institute Kim Kido | Univ. Hawaii Manoa.
Proprietary Wireless Network for the Digital Bus Kianiwai Spangler CFAO Akamai Internship Advisor: Alisa Manangan Supervisor: Cynthia Fox Akimeka, LLC.
Avian Influenza Modeling By: John Fujita Research Institution: Pacific Disaster Center Research Supervisor: Mike Napier Home Institution: University of.
Characterization and Upgrading of Adaptive Optics Demonstrator Joseph Curamen Maui Community College Mark Hoffman & Mark Ammons MCC & UCSC-CfAO.
A Distributed Algorithm for 3D Radar Imaging PATRICK LI SIMON SCOTT CS 252 MAY 2012.
Vacuum System Vibration Analysis on the Keck Telescopes Michael Cooney W.M. Keck Observatory.
Designing a Portable Data Acquisition Unit: Increasing Efficiency and Maximizing Productivity by Use of Standards Dustyn Iwamoto Home Institution: Honolulu.
Patterns of Temperature and Avian Influenza Outbreaks Carol Matasci Pacific Disaster Center Supervisor: Pam Cowher.
Satellite Orbit Visualization Vladimir Ivanov Oceanit Project Supervisor: Frank Dachille Project Advisor: Dale Nahoolewa, Curt Leonard Home Institution:
Improving I/O with Compiler-Supported Parallelism Why Should We Care About I/O? Disk access speeds are much slower than processor and memory access speeds.
1 Inventory Management Database Development Conrad Corpuz Mentor: Alisa Manangan Advisor: Errol Gorospe Maui Community College.
Optimizing the Throughput of an Optical System Lisa Phillips Textron Systems Mentor: Robert Nolan Advisor: Robert Lercari R&D Team: Tim Georges, Curtis.
Cybikos: wireless handheld computers Cybikos specifications: 32-bit processor running at 11mhz 4mhz coprocessor for its radio transmitter 512k of RAM 512k.
Mobile Modular Command Center (M2C2): The Next Level in Military Communications Daniella Manansala CfAO Akimeka, LLC. July 22, 2005.
Survey of Program Compilation and Execution Bangor High School Ali Shareef 2/28/06.
Motivation: Sorting is among the fundamental problems of computer science. Sorting of different datasets is present in most applications, ranging from.
Thinking in Parallel – Implementing In Code New Mexico Supercomputing Challenge in partnership with Intel Corp. and NM EPSCoR.
CCD Camera Realignment 1. Northrop Grumman  Northrop Grumman is a global defense and technology company  Company does business around the world  Contracted.
Lecture 3 : Performance of Parallel Programs Courtesy : MIT Prof. Amarasinghe and Dr. Rabbah’s course note.
CS 471 Final Project 2d Advection/Wave Equation Using Fourier Methods December 10, 2003 Jose L. Rodriguez
Improved Imaging of Near Earth Objects Using Better Telescope Specifications Hazel Butler CfAO Akamai Internship Institute for Astronomy Advisors: Stuart.
Scheduling MPI Workflow Applications on Computing Grids Juemin Zhang, Waleed Meleis, and David Kaeli Electrical and Computer Engineering Department, Northeastern.
Image Processing A Study in Pixel Averaging Building a Resolution Pyramid With Parallel Computing Denise Runnels and Farnaz Zand.
Suzanne Burns Maui Community College Advisors Ben Wheeler and Kyle Erickson The R 0 Calculator.
Satellite Tracking Using a Mobile 8” Aperture Telescope June 26th, 2006 Justin O’Brien University of Colorado at Boulder.
NGS computation services: APIs and.
Thinking in Parallel - Introduction New Mexico Supercomputing Challenge in partnership with Intel Corp. and NM EPSCoR.
Capacity Planning in a Virtual Environment Chris Chesley, Sr. Systems Engineer
A New WAVE of ENERGY Jasmine Yoshimoto Mentor: Ned Davis Maui Akamai Internship Program Internship site: Trex Enterprises August 4,
INTRODUCTION TO HIGH PERFORMANCE COMPUTING AND TERMINOLOGY.
Introduction to Parallel Computing: MPI, OpenMP and Hybrid Programming
Mirror Alignment Using Dual Beam Laser
Parallel Programming By J. H. Wang May 2, 2017.
NGS computation services: APIs and Parallel Jobs
Parallel Programming in C with MPI and OpenMP
Department of Computer Science University of California, Santa Barbara
Aloha, my name is Ronald Magarin and I’ve been working with the institute for astronomy working under the guidance of Dr’s Doug Hope and Stuart Jefferies.
Web Development by Mark Mizubayashi Program Manager Tim Fahey
Parallelization of CPAIMD using Charm++
By Brandon, Ben, and Lee Parallel Computing.
Simulating Atmospheric Strehl
Dr.P.Chitra,Professor Department of Computer Science and Engineering
Load Balancing in File Systems
Department of Computer Science University of California, Santa Barbara
Image Database Catalog
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

Creating a Parallel Program to Compute Statistical Information Victoria Sensano Maui Scientific Research Center Research Supervisor: Douglas Hope

The Goal To Automate the process of rating images Where to start? Understand how to define information in an image. Benefits To test imaging systems Design and optimize imaging systems

How does one define information in an image l Based on the amount of information in the image l Information is computed using ensembles of object and image scenes l Based on how well one can associate an image with its object scene Images from : Object Ensemble of Spiral Galaxies Given Image Scene Associate “Statistical Comparison”

Object and Image Ensembles Object Ensemble Image Ensemble Image provided by Boeing

Important Question to Address... How many object and image scenes in the ensembles are required to make a good comparison? Constraints: Limited memory Solution: Break the problem up into pieces then combine

My Project Create a parallel program - adapt existing single processor code to run in a parallel environment Create two Matlab programs - divide the frequencies between processors - combine frequencies to form information maps Evaluate performance within parallel environment - Verify results obtained by the parallel program

How Programs Work Together Distributes frequency values Sets up parallel environment Computes the information Combines results Matlab Program 1 Parallel Program Existing Matlab Programs Matlab Program 2 Three existing external programs used to create image and object ensembles

Distributes frequency valuesMatlab Program 1 Parallel Program Existing Matlab Programs Matlab Program 2 Three existing external Program used to create image and object ensembles

Matlab Program 1 -- Divide the Workload Distributes the work load by allowing the user to select the amount of processors to be used. This program divides the frequency values between the amount of processors selected for computation. Select Amount of Processors Frequency values between 1 and 100 Frequency values between 101 and Processors Frequency values between 201 and 300 Processor 1 Processor 2 Processor 3

Distributes frequency values Sets up parallel environment Matlab Program 1 Parallel Program Existing Matlab Programs Matlab Program 2 Three existing external Program used to create image and object ensembles

Parallel Program Sets up the parallel environment using MPI and C to run the existing Matlab programs on the Huinalu Cluster at the Maui High Performance Computing Center. Sends a message to each processor to 1) Open files that contain frequency values 2) Begins to open existing Matlab Program Processor sends acknowledgment of receiving the message Each node begins to compute information at its assigned frequency values

Distributes frequency values Sets up parallel environment Computes the information Combines results Matlab Program 1 Parallel Program Existing Matlab Programs Matlab Program 2 Three existing external Program used to create image and object ensembles

Matlab Program 2 -- Combine Results l Combines results forming information maps l Information Map - is a combination of frequencies within its Fourier Domain SNR 5 SNR 10 SNR 15 SNR 20 Aperture 4cmAperture 3cm (4) Red color = more information at low frequencies (0) Blue color = less information at high frequencies

Evaluating Performance within the Parallel Environment Pros: Faster Results than using a single processor to do computations Cons: Data Dependencies - use of the same storage location Testing: 1) Design 2) Efficiency Approaching its limit

Conclusion Project Achievements: Used MPI and C to run existing Matlab programs in a parallel environment Created Matlab programs to distribute workload over the processors and combine results Confirmed that Matlab programs performed as expected Evaluated the parallel program for its design and efficiency Future Goals of Researchers: Use parallel implementation to compute information using large ensembles Numerically confirm theoretical predictions Use information to characterize the quality of an image

Acknowledgements National Science Foundation Center for Adaptive Optics Malika Bell, Lisa Hunter, Liz Esperanza and the CfAO instructors Maui Scientific and Research Center Douglas Hope and Stuart Jefferies Maui Community College Mark Hoffman and Wallette Pallegrino Maui Economic and Development Board Isla Yap and Leslie Wilkins Satellite images : Funding provided through a Research Experiences for Undergraduates (REU) Supplement to the Center for Adaptive Optics, a National Science Foundation Science and Technology Center (STC), AST