parallel computing with high performance computing clusters (hpcs) by jeremy cathey

22

Upload: gerald-glenn

Post on 14-Jan-2016

221 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey
Page 2: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Parallel Computing With High Performance

Computing Clusters (HPCs) 

By Jeremy Cathey

Page 3: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Super Computing

• Began as early as late 1950’s

• Compute large mathematical calculations

• Large scale task management

Page 4: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Advantages of Super Computing

• Power

• Configuration

• Administration

• Cost

• Scalability

• Diversity

Disadvantages of Super Computing

Page 5: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Alternatives

• Distributed Computing

- Uses queuing system to manage multiple

tasks on several computers serially

• Parallel Computing

- Uses several computers to work on one

task in parallel

Page 6: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Implementations of Alternatives

• Shared Processors (Multiple Processors)

• Shared Memory Pools

• Messaging Systems

Page 7: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Advantages of Parallel Computing• Cost

• Scalability

• Diversity

• Power

• Configuration

• Administration

Disadvantages of Parallel Computing

Page 8: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Parallelization Techniques

• Manual

- Parallelization implemented by the

programmer at creation of the program

• Automatic

- Parallelization implemented on the fly by

the operating system

Page 9: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Advantages of Manual Parallelization

• Specific Customization

• More Effective Parallelization

Disadvantages of Manual Parallelization

• Difficult to Implement

• Not Very Portable

Page 10: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Advantages of Automatic Parallelization

• Easier to Implement

• Portable Applications

Disadvantages of Automatic Parallelization

• Less Effective Parallelization

Page 11: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

• Reduce Disadvantages of Parallel Computing

• Learn more about Operating System development and parallel optimization

• Provide a solution for optimized parallel computing for Dr. Salazar’s research

Project Goals

Page 12: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Goal Techniques

• Reduce power issue of parallel computing machines by custom building an operating system kernel for optimization

• Research and Improve Open-Mosix Parallelization Technique

• Create a cluster that is easy to assemble and disassemble

• Create and/or implement an interface that simplifies cluster administration

Page 13: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Operating System Choice

• Windows Vs. Linux

• Live vs. Install

• Community Support

• Creation vs. Customization

• HARDWARE SUPPORT!!!!!!!!

Bill!!!!

Page 14: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Implementation

• Dr. Salazar: Professor of Chemistry

• Use cluster to reduce time for sophisticated mathematical computation

Page 15: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Simulation Details

• 2.6 GHz Computer - 2GB RAM

• 1.2 GHz Computer - 256MB RAM

• 5 Parallel 1.2GHz Computers – 1.28GB RAM

Page 16: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Computer Simulation Results

0.00

10.00

20.00

30.00

40.00

50.00

60.00

70.00

80.00

0 5000 10000 15000 20000 25000 30000 35000

Number of Atoms

Ho

urs

to

Co

mp

leti

on

Group 21.2GHz

Page 17: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Computer Simulation Results

0.00

10.00

20.00

30.00

40.00

50.00

60.00

70.00

80.00

0 5000 10000 15000 20000 25000 30000 35000

Number of Atoms

Ho

urs

to

Co

mp

leti

on

Group 1

Group 2

2.6GHz

1.2GHz

Page 18: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Parallel

Computer Simulation Results

0.00

10.00

20.00

30.00

40.00

50.00

60.00

70.00

80.00

0 5000 10000 15000 20000 25000 30000 35000

Number of Atoms

Ho

urs

to

Co

mp

leti

on

Group 1

Group 2

Group 3

1.2GHz

2.6GHz

Parallel

Page 19: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Hurdles

• HARDWARE DETECTION!!!!!!

• HARDWARE DETECTION!!!!!!

• HARDWARE DETECTION!!!!!!

Did I Mention:

• HARDWARE DETECTION!!!!!!

• HARDWARE DETECTION!!!!!!

• HARDWARE DETECTION!!!!!!

Page 20: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Improvements

• Redesign Operating System Kernel For More Advanced HARDWARE DETECTION

• Try Simulations on More Advanced Computers

• Create Custom Installer for Distribution

Page 21: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Special Thanks

• Dr. Kirk: For providing computers for experiment and for finding a place for me to store my project

• My Wife: For not killing me while I had to store my project at our home

• Dr. Wilms: for providing older versions of Red Hat, and for Operating Systems Class

• Dr. Salazar: For time and effort spent helping me understand a SMALL part of his research

Page 22: Parallel Computing With High Performance Computing Clusters (HPCs) By Jeremy Cathey

Questions? Comments? Derogatory Remarks?