October 19th - 23rd, 2009 - Calgary - Acceleware HQ

Space is limited - Please register early to guarantee your spot

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: CUDA Textures Hands-on-Exercise: Textures Lecture and Hands-on-Exercise: Asynchronous Operations Lecture: More CUDA Features Lecture: Debugging CUDA Programs Hands-on-Exercise: Debugging Day 3: Lecture: Introduction to Optimization Hands-on-Exercise: Arithmetic Optimization Lecture: Resource Management, Latency and Occupancy Hands-on-Exercise: CUDA Occupancy Calculator Lecture: 3D Finite Difference Hands-on-Exercise: Memory Performance Optimizations Lecture: Profiling CUDA applications Hands-on-Exercise: CUDA Visual Profiler Day 4 & 5: More Hands-on-Exercises: Building GPU Prototypes and Specific client applications

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

“The Acceleware trainer did a great job while he was here.  Actually, he was awesome.  The class was well prepared and well delivered.  The trainer’s depth of knowledge exceeded everyone’s expectations.  He has obviously been immersed in the GPU development environment for years.  I had the pleasure of attending the second week of training.” Mark McFarlane, Saudi Aramco

“The 10x-100x performance benefit from using NVIDIA’s GPUs has companies in a broad selection of industries clamouring to port their applications to the massively parallel programming model of the GPU. These companies, in fields such as seismic exploration, financial simulation or medical imaging can now augment their staff with Acceleware’s seasoned team of CUDA software developers to more rapidly bring their applications to market” Andy Keane, General Manager, GPU Computing at NVIDIA