2013,  January 29/30

Objectives

This course will make you able to develop portable parallel applications. It will expose you to the basis of OpenCL, making you able to easily write your own hybrid applications. Then it will introduce you to OpenCL device specific optimizations, making you able to fully exploit accelerators and achieve high performance.

Agenda

Day 1

Morning – OpenCL Basics

• Introduction to GPU computing
• GPU architecture
• OpenCL programming model
• OpenCL API

Afternoon – OpenCL Kernel Performance (1/3)

• OpenCL tools for compiling and debugging
• Performance measurement of OpenCL applications

Day 2

Morning – OpenCL Kernel Performance (2/3)

• Memory: image objects
• NDRange optimizations
• Using local memory

Afternoon – OpenCL Kernel Performance (3/3)

• Code optimizations and transformations
• Asynchronism and queue ordering
• Hardware-dependent optimizations

Prerequisites

Knowledge in C

Audience

Developers

OS

Linux

For further information or registration please contact training@caps-entreprise.com