Module 24450 (2011)

Syllabus page 2011/2012

06-24450
Parallel Programming

Level 3/H

Dan Ghica
10 credits in Semester 2

Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus


The Module Description is a strict subset of this Syllabus Page. (The University module description has not yet been checked against the School's.)

Changes and updates

New module for 2011/12.


Relevant Links

Module web page


Outline

This module covers the basics of programming massively parallel architectures such as graphics processing units (GPUs), multi-cores and field-programmable gate arrays (FPGAs). The module is focussed on the architecture of such devices and their use in speeding-up common computational tasks. Recent developments in such architectures made this task substantially easier and newly available programming tools allow for high-level straightforward programming of these systems. The module will provide a largely practical introduction to the topic. Lectures will address the basic architectural principles of modern parallel architectures and relevant algorithms and programming techniques.


Aims

The aims of this module are to:

  • understand GPU architecture
  • understand what applications areas are most suitable to parallel programming
  • practical understanding of parallel algorithms
  • practical understanding of parallel programming techniques
  • concrete skills in programming Nvidia GPUs using the CUDA framework
  • skills in using the software tools provided by the CUDA framework

Learning Outcomes

On successful completion of this module, the student should be able to: Assessed by:
1describe and explain modern parallel architectures Examination
2describe and explain applications of parallel programming Examination
3describe and explain parallel programming models Examination
4design simple parallel algorithms Examination and coursework
5implement more advanced parallel algorithms Coursework

Restrictions, Prerequisites and Corequisites

Restrictions:

May not be taken by anyone who has taken or is taking 06-22755 (Parallel Programming (Extended))

Prerequisites:

None. Some familiarity with the Haskell programming language would be helpful.

Co-requisites:

06-23636 (Operating Systems with C/C++) or equivalent.


Teaching

Teaching Methods:

2 hrs/week lectures; 2 hrs/week practical sessions

Contact Hours:

35


Assessment

  • Sessional: 1.5 hr examination (50%), coursework (50%). Both the examination and the coursework are internal hurdles: students must pass both in order to pass the module
  • Supplementary (where allowed): By examination only (100%)

Recommended Books

TitleAuthor(s)Publisher, Date
Multigrid Methods on GPUsPeter ThomanVDM Verlag,
GPU Gems 3: Programming Techniques for High-Performance Graphics and General-Purpose ComputationHubert NguyenAddison Wesley,

Detailed Syllabus

  1. Contrasting CPU and GPU architectures
  2. The CUDA programming model
  3. A first example: matrix multiplication
  4. The CUDA memory model
  5. GPU as part of the PC architecture
  6. Detailed threading model
  7. Detailed memory model
  8. Control flow on the GPU
  9. Floating-point aspects
  10. Parallel programming concepts
  11. Parallel algorithms
  12. Reduction
  13. Advanced features

Last updated: 20 July 2011

Source file: /internal/modules/COMSCI/2011/xml/24450.xml

Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus