Sponsored by
|
|
A two day class that covers the basics of GPU programming and developing code for efficient parallel processing. The class is instructed by an Acceleware developer with industry experience in creating OpenCL commercial applications and is developed and presented in cooperation with AMD.
|
| Date: |
June 28th - 29th, 2011 |
|
| Location: |
750 Palomar Avenue
Sunnyvale, CA 94085, United States
(view in Google Maps)
|
| Contact: |
Acceleware
403.249.9099 x 356, services@acceleware.com |
| Cost: |
$2,000 USD
Enter AXTEB2011 as Coupon Code to receive $200 off the registration fee(valid until June 17th, 2011)
Your fee includes:
- Use of a laptop equipped with AMD Fusion APU
- Manual of all lectures
- CD copy of lab exercises
- Certificate of Completion
|
|
|
| |
|
Your Instructor
|
Dan Cyca - Director of Engineering
Dan joined Acceleware's software development team in 2004 to implement the company's first product and now manages the development group. His previous experience includes developing 'C-to-hardware' compilers, and implementing digital signal processing and encryption algorithms on FPGAs.
Dan has a M. Sc. in Electrical Engineering from the University of Calgary.
|
Schedule
Tue and Wed: 9:00AM – 5:00PM (incl. 1 hour lunch)
Agenda
- Day 1:
- Lecture: Overview of GPU Computing
- Hands-on-Exercise: Buffer Allocation and Buffer Transfers
- Lecture: Data-Parallel Architectures and the GPU Programming Model
- Hands-on-Exercise: Simple Kernels
- Lecture: The GPU Memory Model and Work-item Cooperation
- Hands-on-Exercise: Local and Constant Memory
- Day 2:
- Lecture: Introduction to Optimizations
- Hands-on-Exercise: Arithmetic Optimizations
- Lecture: Resource Management and Hiding Memory/ALU Latency
- Hands-on-Exercise: Wavefront/Compute Unit Calculations
- Lecture: Memory Optimizations
- Hands-on-Exercise: Correcting memory access pattern transfers and local memory bank conflicts
|
Space is limited - Please register early to guarantee your spot
