C++ AMP in Seattle, WA
C++ Accelerated Massive Parallelism (C++ AMP) is a programming model that can accelerate the execution of your C++ code by taking advantage of the data-parallel hardware that is commonly present as a GPU and multi-core CPU.
Your fee includes
- Hands-on exercises developed by our experts
- Individual laptops with compute capable GPUs for student use
- Printed manual of all lectures
- Electronic copy of lab exercises
- C++ AMP Quick Reference Guide
- Certificate of completion
Space is limited - Please register early to guarantee your spot
Your Instructor
|
|
Kelly Goss - Training Program ManagerSchedule
Tue-Fri: 9:00AM – 5:00PM (includes a 1 hour break for lunch)
4 Day Course Syllabus
- Day 1: Introduction to GPU Programming and GPU Architectures
- Overview of GPU Computing
- C++ 11 Lambda Syntax
- Data-Parallel Architectures and C++ AMP Programming Model
- AMPed Up! (AKA More C++ AMP Features)
- Hands-on Exercises: Lambda Functions and Templates, Intro to C++ AMP and Mini Exercises exploring AMP Features
- Day 2: Lower Level API, Debugging and Graphics
- Lower Level API (Tiles)
- Debugging C++ AMP Programs & Understanding Numerical Differences
- Textures & DirectX Interoperability
- Hands-on Exercises: Debugging Demo and Moving Average Filter, C++ AMP Support in the Visual Studio 11 Debugger, Graphics Interoperability
- Day 3: Intro to Optimization
- Asynchronous Operations and Efficient Copy Operations
- Accelerator Architectures/Latency
- Performance Optimizations
- Hands-on Exercises: Asynchronous Operations, Latency Exercise, Arithmetic and Memory Performance Optimization
- Day 4: Profiling and Case Studies
- Profiling Applications
- Case Study 1: Finite Difference Stencil Algorithm
- Case Study 2: Monte Carlo Simulations
- Hands-on Exercises: C++ AMP Features in Concurrency Visualiser for Visual Studio 11, Finite Difference Exercise and Monte Carlo Exercise
All lectures are a combination of teaching and hands-on tutorials