OPENCL HMPP

Topics Covered

Day 1:

• OpenCL Basics (half-day)
  • Introduction to GPU computing
  • GPU architecture
  • OpenCL programming model
  • OpenCL API
  • OpenCL Tools for compiling and
    debugging
  • Lab session: getting information about
    OpenCL devices
  • Lab session: programming a simple
    addition

• OpenCL Kernel Performance (half-day)
  • Performance measure of OpenCL
    applications
  • Memory: Image Objects
  • Lab session: using Image objects
  • NDRange optimizations
  • Local Memory
  • Lab session: convolve using local memory
    (1/2)
  • Code optimizations & transformations
  • Lab session: optimizing the convolution
    kernel (2/2)
  • Asynchronism & queue ordering
  • Hardware-dependant optimizations
  • Kernel build options
  • Performance and portability study

Day 2

• HMPP Basics (half-day)
  • Introduction to parallel hybrid
    programming
  • HMPP overview
  • Lab session: HMPP Hello World!
  • Basis of HMPP programming
  • Lab session: offl oading a computation in
    to a GPU
  • HMPP compilation model
  • Lab session: compiling an HMPP
    application

• HMPP Transfers Optimizations (half-day)
  • Managing data transfers
  • Lab session: programming data transfers
  • Grouping GPU computations
  • Optimizing data movement
  • Local Memory
  • Driving the code generation & gridifi cation

Target Audience
This course is intended for software professionals and students who are responsible for or interested in developing high performance Hybrid computing applications.

Additional Information:
Students will receive a 'mini-PC' which will be pre-loaded with HW and SW suitable for this training course and will be entitled to take this unit with them after the training course is completed.