strategies for developing visualizations of parallel algorithms for dense matrix operations on...

12
Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Upload: ruth-barnett

Post on 17-Jan-2016

224 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected

SIMD Computers

by : Justin C. Miller

1/12

Page 2: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Who am I ?

Justin Miller

Computer Science Major

Mathematics Minor

Goals:

Receive PhD

Become College Professor

2/12

Page 3: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Why’d I choose this topic?

Wanted to combine topics…

1.Computer Science

2.Mathematics

3.Education/Teaching

Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers

3/12

Page 4: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Outline of Talk

1. Teach you the General Concepts needed to understand what I’ve done.

2. Quick overlook of what I’ve done.

4/12

Page 5: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Matrices and Matrix Operations

What is a matrix?

What are matrix operations?

eg. (multiplication, transposition)

What is a dense matrix? (as opposed to sparse)

5/12

Page 6: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Performing matrix operations on Parallel Computers

The concept of parallel computing.

What does it mean to be SIMD?

Subclasses of SIMD computers.

eg. (shared memory, interconnected)

Types of Interconnected Networks.

6/12

Page 7: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

How did I make the visualizations?

2 Step Process to animate the algorithms…1. Understand it using JCSP library

2. Animate it using Animal

public void run(){

int data = getStartingData() ;

while(counter < 10){

ToLeft.pass(data) ;

data = FromRight.get();

calculate(data) ;

}//while

writeFinalAnswer(data) ;

}//run

square “square1” (10, 10) 40 color blue

text “title” “Justin’s Demo” (40,40) centered color black font Serif size 14 bold

7/12

Page 8: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Why design visualizations for these algorithms?

Lots of motion & passing of data

Difficult to draw, lots of mistakes

Quicker preparation time for lectures

Attracts student attention

8/12

Page 9: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Strategies for developing animations for these algorithms.

Some general techniques mentioned in other papers.eg. Quiz Questions, Descriptive Text, High Contrast, Step-Thru & Play

Several specific techniques for parallel matrix algorithms on Interconnected SIMD computers.eg. show channels, pass data along channels, show register contents

Example: abstract delays by making certain events appear exactly in parallel.

Actually in my Thesis paper.

9/12

Page 10: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Case Study

General results of prior research.

Had to see it to believe it.

Mostly for feedback.

10/12

Page 11: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Summation

Like to idea of visualizations in the classroom.

Future possibility of conducting a more controlled scientific study

Thank you, Questions?

11/12

Most importantly, preparation for graduate research

Page 12: Strategies for Developing Visualizations of Parallel Algorithms for Dense Matrix Operations on Interconnected SIMD Computers by : Justin C. Miller 1/12

Further interest? Here’s some free downloads.

Download Animal

http://www.animal.ahrgr.de/

Download JCSP library

http://www.cs.ukc.ac.uk/projects/ofa/jcsp/

Download Java

http://java.sun.com/j2se/1.4/download.html

12/12