In Association with:
|
| Date Options: |
January 17-21, 2011
|
| Location: |
Colfax Intl.
Sunnyvale, CA
View in Google Maps
|
| Contact: |
Acceleware
403.249.9099 x 356, services@acceleware.com |
| Cost: |
$4000 USD |
| |
|
| Space is limited - Please register early to guarantee your spot |
Your Trainer
 |
Chris Mason - Acceleware Product Manager
Chris is the product manager for the linear algebra solver product line at Acceleware. He has been responsible for the successful launch of Acceleware products used by companies world-wide. His previous experience includes parallelization of algorithms on digital signal processors (DSPs) for cellular phones and base stations.
Chris has a Masters in Electrical Engineering from Stanford University. |
Schedule
Mon-Thu: 9:00AM – 5:00PM (incl. 1 hour lunch)
Fri: 9:00AM – 12:00PM
Agenda
- Day 1:
- Lecture: Overview of GPU Computing
- Hands-on-Exercise: Memory Allocation and Memory Transfers
- Lecture: Data-Parallel Architectures and the CUDA Programming Model
- Hands-on-Exercise: Simple Kernels
- Lecture: The CUDA Memory Model & Thread Cooperation
- Hands-on-Exercise: Shared Memory and Constant Memory
- Day 2:
- Lecture and Hands-on-Exercise: Textures
- Lecture and Hands-on-Exercise: Asynchronous Operations
- Lecture: Other GPU Features
- Lecture: Libraries
- Lecture: Debugging GPU Programs
- Hands-on-Exercise: Debugging Tools and Techniques
- Day 3:
- Lecture: Introduction to Optimization
- Hands-on-Exercise: Arithmetic Optimization
- Lecture: Resource Management, Latency and Occupancy
- Lecture and Hands-onExercise: Memory Performance Optimizations
- Day 4 & 5:
- More Hands-on-Exercises: Building GPU Prototypes and Specific client applications
- Running on servers and clusters
|
All lectures are a combination of teaching and hands-on tutorials
NVIDIA’s foundational training material is augmented with Acceleware’s experience over
the past 5.5 years and with examples specific to an HPC audience
