9:00 - 10:15
Title: Languages, APIs and Development Tools for GPU Computing

William Ramey, Sr. Product Manager, NVIDIA Corporation

This session will provide an introduction to key technologies for GPU computing. This tutorial session will cover the key features and differences between the major programming languages, APIs and development tools available today. Attendees will also learn several high level design patterns for consumer, professional and HPC applications, with practical programming considerations for each.

10:15 - 11:15
Title: Programming for the CUDA Architecture

Tianyun Ni, Developer Technology Engineer, NVIDIA Corporation

This presentation teaches the fundamentals of programming GPUs, covering data transfers, kernel execution, memory model, synchronization, etc. These concepts and more are introduced progressively and illustrated using step-by-step walkthroughs with CUDA C source code examples.

11:15 - 12:00
Title: Programming in OpenCL

Timo Stitch, Developer Technology Engineer, NVIDIA Corporation

Building on the previous session, learn how to leverage the OpenCL programming interface and how it is used to program GPUs. This talk describes the OpenCL API, memory management, programming and execution models, and illustrates these concepts with some simple source code examples.

1:00 - 1:45
Title: CUDA in the VFX Pipeline

Wil Braithwaite, Applied Engineer, Digital Film Group, NVIDIA Corporation

This presentation will help you determine how to efficiently integrate GPU computing into your VFX pipeline, as well as providing an overview of some useful 3rd party libraries.

1:45 - 2:45
Title: Development Tools

Takayuki Kazama, Developer Technology Engineer, NVIDIA Corporation

Learn about the latest development tools for GPU computing. This talk covers GPU hardware debuggers and performance profiling tools available today, including cuda-gdb and the Visual Profiler for both CUDA C and OpenCL, as well as NVIDIA's new Visual Studio-based Nexus development environment for Windows. Nexus introduces native GPU debugging and platform-wide performance analysis tools for both computing and graphics developers, fully integrated into Visual Studio 2008.

2:45 - 4:00
Title: The Art of Performance Optimization

Wil Braithwaite, Applied Engineer, Digital Film Group, NVIDIA Corporation

Learn how to optimize your applications to take full advantage of the massively parallel processing capabilities of modern GPUs. Topics will include kernel launch configuration, using shared memory, maximizing memory throughput using asynchronous data transfers and copy/compute overlap.  We will also describe how the CUDA Visual Profiler and code instrumentation can be used to assess performance and identify bottlenecks.  While CUDA C is used for illustration, the concepts covered will apply equally to programs written with OpenCL and DirectCompute APIs as well.

4:00 - 5:00
Title: GPU Computing Application Showcase

Don’t just take our word for it! Come listen to two companies that leveraged the CUDA architecture to accelerate their applications. Understand the real ROI from their experts, learn tips and tricks of the trade, and ask questions from developers that have seen significant gains.

4:00 - 4:30
Title: CFD Applications - From Single GPU to Multiple GPUs

Dr. Takayuki Aoki, Tokyo Institute of Technology, Global Scientific Information and Computing Center

In CFD (Computational Fluid Dynamics) applications, a single GPU achieved from 10x to more than 100x speed up when compared to a single core of a CPU. However, the use of multi GPUs is desirable because it will provide a solution to the limitation of memory on the Tesla card. The importance of circumventing the communication lag between GPUs and the case-study of its application on TSUBAME will be addressed.

4:30 - 5:00
Title: "NATURAL EXPRESSION" and "WORLD"

SQUARE ENIX Co., LTD, Mr. Eiji Fujii, Development Director, Research and Development Division

I (SquareEnix Development Director, Eiji Fujii) will explain the philosophy of “NATURAL EXPRESSION”, which will be the foundation of the future generation of games, as well as a collection of 3D Game development modules called “WORLD”, which we are currently developing. The key topics that will be covered will be, CUDA and GPU accelerated High Speed Global Illumination Renderer and its peripheral modules, including Non-Key Frame Animation Module, Cloud Animation Module, Facial Animation Module, as well as prospects for the future.

5:00 - 5:30
Future Directions in GPU Computing

William Ramey, Sr. Product Manager, NVIDIA Corporation

Learn what the future holds when as discuss NVIDIA's next-generation graphics and compute architecture, codenamed: Fermi. In addition, hear what NVIDIA believes will be the next breakthroughs in GPU computing and how GPUs are helping to change the world.