UHD Grid Computing Team Department of Computer and Mathematical - PowerPoint PPT Presentation

UHD Grid Computing Team Department of Computer and Mathematical Sciences University of Houston-Downtown 1

2 � Application Projects � Grid Laboratory � Architecture � Interface � Clusters Outline

Historical Review � An Integrated Lab Package for Introductory Computer Science Course – CSI � The Design of Phil2000 � Java Application � Hierarchical Design � Labs -> Tasks -> Activities � Explorer � Plug-ins to run applications 3

Grid Infrastructure for Laboratory � an interface that is extensible to incorporate more lab modules and customizable to different course structures � Solution: a lab explorer � an computational backbone that provides services for various lab activities � Solution: an array of servers that run on a computational grid 4

The pyramid model of the project Interface of functional units Multi-agent Client/server model system Module language Lab modules Design theme Architecture specification Application theme 5

Labs to implement � Topology : Circuiting messages in a ring � Collective communications : Matrix transpose � Group management : Matrix multiplication with Fox’s algorithm � Scientific computation : Solving linear systems with Jacobi’s algorithm � Combinatorial search : Traveling salesman problem � Parallel I/O : Vector processing - Summation � Performance analysis : Visualization with Upshot – Trapezoidal rule problem � Parallel library : Solving linear system with ScaLapack � Scalability analysis: Bitonic sorting � LAN configuration : The use of NICs and hubs � Network analysis : Monitoring a chat room � Address resolution : Experiment with ARP burst � IP masquerading : Clustered web servers � WAN configuration : The use of routers � Performance tuning : Deal with congestion � Service configuration: The configuration of a networked file system: 6

The Main Menu Frame Upper Toolbar Tree Panel Lower Toolbar Open Next Save Previous Screens Print Last Cards Help First End The Lab Layout 7

Frame Screen Upper title & icon menu ToolBar Screen panel Tree ScrollPane Button Lower The Main Menu ToolBar 8

9 The file *.mla Save lab Massage Open or Open and Close Menus

10 Dialog Print Table Print Print layout Dialog Print frame Scroll Pane Data Table Print

11 Frame Help Help Menu

12 JumpShot Other Software used MPICH Visual C++

Node Calling and Services Menu Services menu Node Calling Menu Text Text Scroll area field pane Radio Button Scroll Menu 13

14 � Performance evaluation of parallel programs An Example

15 Performance Analysis - Activities c. Profiling b. Compilation and execution a. Performance Prediction

Khoi Nguyen o Construct small cluster/NOW. o CMS lab cluster (16 nodes) o Linux Beowulf Cluster functional o Successfully run all sorting algorithms with expected results. o Create a GUI interface as an overlay using JAVA. http://www.netlib.org/utk/papers/mpi-book/node2.html 16

� 16 Nodes � RedHat 9.0 as Operating System � Configure rsh in root and user directories � Install MPICH ver. 1.2.6 (Unix- all flavors) � Test with MPICH test programs & sorting program 17

18 The Cluster

Test results – Quick sort Q u i c k s o r t f o r 1 0 , 0 0 0 e l e me n t s Q u i c k s o r t f o r 1 , 0 0 0 , 0 0 0 e l e me n t s 0 . 0 5 2 0 . 0 4 1 . 5 0 . 0 3 1 0 . 0 2 0 . 5 0 . 0 1 0 0 1 p 2 p 4 p 8 p 1 6 p 1 p 2 p 4 p 8 p 1 6 p 0 . 0 4 2 0 . 0 1 4 5 0 . 0 1 2 9 0 . 0 1 5 8 0 . 0 1 9 1 . 4 9 1 . 6 2 1 . 5 1 1 . 3 4 1 . 3 4 P r o c e s s o r s P r o c e s s o r s Q u i c k s o r t f o r 1 0 , 0 0 0 , 0 0 0 e l e me n t s Q u i c k s o r t f o r 1 0 0 , 0 0 0 e l e me n t s 2 0 0 . 2 5 0 . 2 1 5 0 . 1 5 1 0 0 . 1 5 0 . 0 5 0 0 1 p 2 p 4 p 8 p 1 6 p 1 p 2 p 4 p 8 p 1 6 p 1 6 . 0 8 5 1 4 . 6 8 1 4 . 5 8 1 4 . 1 5 1 2 . 4 9 0 . 1 6 2 0 . 1 8 1 0 . 1 9 8 0 . 1 8 9 0 . 2 2 4 P r o c e s s o r s P r o c e s s o r s 19

Test results – Merge sort M e r g e So r t - 1 0 , 0 0 0 e l e me n t s M e r g e s o r t - 1 0 , 0 0 0 , 0 0 0 e l e me n t s 0 . 0 6 4 0 0 . 0 5 3 0 0 . 0 4 2 0 0 . 0 3 0 . 0 2 1 0 0 . 0 1 0 1 p 2 p 4 p 8 p 1 6 p 0 1 p 2 p 4 p 8 p 1 6 p 3 1 . 7 5 2 5 . 7 2 1 7 . 8 9 1 3 . 8 5 1 2 . 1 4 0 . 0 4 9 1 0 . 0 4 3 4 0 . 0 3 0 2 0 . 0 3 1 0 . 0 2 9 P r o c e s s o r s P r o c e s s o r s M e r g e s o r t P e r f o r ma n c e I n c r e a s e f o r 1 , 0 0 0 , 0 0 0 e l e me n t s M e r g e So r t - 1 0 0 , 0 0 0 e l e me n t s 1 . 4 0 . 3 1 . 2 0 . 2 5 1 0 . 2 0 . 8 0 . 1 5 0 . 6 0 . 1 0 . 4 0 . 0 5 0 . 2 0 0 1 p 2 p 4 p 8 p 1 6 p 1 p 2 . 6 7 2 p 4 p 8 p 1 6 p 0 . 2 4 8 0 . 2 2 3 0 . 1 7 9 0 . 1 4 7 0 . 1 5 5 1 6 . 5 9 % 5 1 . 7 0 % 9 9 . 2 5 % 1 1 8 . 8 5 % P r o c e s s o r s P r o c e s s o r s 20

� GUI will be basic window applet � Action buttons � Introduction � Run your MPI program � Run Demo programs � Sorting Programs � Distribution sample programs � Help � Output Window 21

22 Finished GUI - Introduction

23 Open your MPI file!

24 Compile & Build your MPI Program!

25 Running your MPI program!

26 Program Running in Console…