General-Purpose Computing on GPU

Lecturer:

Jaroslav Sloup (gar.)

Tutor:

Jaroslav Sloup (gar.)

Supervisor:

Department of Computer Graphics and Interaction

Synopsis:

The goal of the course is to introduce students to basic principles of General-Purpose Computing on Graphics Processing Units (GPGPU). Course gives an overview of architecture and capabilities of modern graphics processing units (GPUs) and covers elementary concepts in parallel programming on GPUs. Students will gain programming skills with the CUDA (or OpenCL) technology and become familiar with basic parallel algorithms (e.g. parallel prefix scan/reduction) that are building blocks for design and implementation of efficient parallel algorithms.

Requirements:

Programming in C/C++, linear algebra.

Syllabus of lectures:

1. Introduction to general-purpose computing on GPU (architectures, languages, GPU versus CPU).

2. Multithreaded programming.

3. Introduction to CUDA architecture and

basics of its programming.

4. Working with threads and memories in CUDA.

5. Programming for performance - optimizations.

6. Application Case Studies in CUDA.

7. Other high-level languages for GPGPU programming I - OpenCL (Open Computing Language)

8. Other high-level languages for GPGPU programming II - GLSL (OpenGL Shading Language)

Syllabus of tutorials:

1. Introduction - requirements, evaluation. Introduction to SSE programming.

2. Examples of simple multithreaded applications.

3. CUDA - compilation workflow, debugging, code examples.

Specification of the individual student projects.

4. CUDA - solution of given tasks I.

5. CUDA - solution of given tasks II.

6. Individual work on projects - consultations I.

7. Individual work on projects - consultations I.

8. Individual student projects checkpoint.

9. OpenCL - compilation workflow, debugging, code examples.

10. OpenCL - solution of given tasks.

11. Individual work on projects - consultations II.

12. Individual work on projects - consultations II.

13. Submitting of individual student projects.

14. Assessment.

Study Objective:

Study materials:

1. David B. Kirk, Wen-mei W. Hwu: Programming Massively Parallel Processors: A Hands-on Approach. Morgan Kaufmann, 1st edition, 2010, ISBN-13: 978-0123814722.

2. Jason Sanders, Edward Kandrot: CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Professional, 1st edition, 2010, ISBN-13: 978-0131387683.

3. Ryoji Tsuchiyama, Takashi Nakamura, Takuro Iizuka, Akihiro Asahara, Satoshi Miki: The OpenCL Programming Book. Fixstars Corporation, 2010.

Note:

Time-table for winter semester 2011/2012:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon
Tue
Fri	roomKN:E-128 Sloup J. 14:30–16:00 (lecture parallel1) Karlovo nám. Cvičebna K3
Thu	roomKN:E-311 Sloup J. 11:00–12:30 (lecture parallel1 parallel nr.101) Karlovo nám. Lab K311roomKN:E-311 Sloup J. 12:45–14:15 (lecture parallel1 parallel nr.102) Karlovo nám. Lab K311
Fri

Time-table for summer semester 2011/2012:

Time-table is not available yet

The course is a part of the following study plans: