Last Updated:
04
/
14
/
2009
NVIDIA Developer Newsletter 47: April 2009
Welcome to April's "Post-GDC" Newsletter!
Just a few weeks ago, we concluded a very successful GDC 2009 event in San Francisco, CA. In spite of the global economic turndown, the GDC remained a busy, vibrant event, with thousands of attendees stopping by the NVIDIA booth or listening to one of our many sessions. We'd like to thank all those that attended, and a special thanks goes out to all of you that offered feedback on how we can improve in the following years. We take all that feedback seriously, and you can rest assured that you will see some interesting changes next year.
This newsletter contains links to all the slides and videos that were created for or at the GDC by NVIDIA. Not only that, we have several new or updated tool announcements that are sure to catch your interest!
| NVIDIA APEX: From Mirror’s Edge to Pervasive Cinematic Destruction to Real-Time Fluid Simulation |
Presentation Video, Slide Deck (PDF)
Speakers: Anders Caspersson, EA DICE, and Jean Pierre Bordes & Monier Maher, NVIDIA Corporation |
In this talk, we discuss the process of integrating physics in Mirror’s Edge, highlight some of the challenges that occur when using traditional physics middleware to create eye-catching content, and introduce a new technology that empowers artists to quickly create pervasive cinematic quality destructible environments and high definition smoke. |
| The In and Out: Making Games Play Right with 3D Stereoscopic Technologies |
Presentation Video, Slide Deck (PDF)
Speakers: Samuel Gateau, NVIDIA Corporation |
| This session will present an overview of Stereoscopic graphic technology, and cover the common pitfalls and solutions a developer needs to be aware of to ensure that their content will create a compelling 3D experience. Topics to be covered include: achieving out of screen effects, displaying 3D video content, and how to design a 3D friendly user interface. |
| CUDA and Multi-Core Gaming: Lessons from the Trenches |
Presentation Video, Slide Deck (PDF), White Paper, Slide Deck Videos(Zip), Supplemental Videos (Zip)
Speakers: Dan Amerson (Emergent Game Technologies), Dermot Gallacher (Instinct Technology), and Avi Bleiweiss (NVIDIA Corporation) |
This session will present real-world case studies of using GPU Computing to accelerate general game algorithms. Highlights will include prototyping a general computing system that leverages the GPU in Emergent’s Gamebryo engine, and leveraging GPU Computing to turbocharge AI algorithms. |
| NVIDIA APEX: High-Definition Physics with Clothing and Vegetation |
Presentation Video, Slide Deck (PDF)
Speakers: Michael Sechrest, Interactive Data Visualization, Inc. (Speedtree), Jean Pierre Bordes & Monier Maher, NVIDIA Corporation |
| In this talk, we introduce a new technology that empowers artists to quickly create fully interactive in-game clothing and vegetation. We show how you can dress your game characters with high-definition interactive simulated clothing using APEX tools, and provide a real world example in an MMOG engine. Next we show how you can breathe life into your SpeedTree's by creating physically interactive leaves, branches, trees, and forests using APEX |
| Platform-independent Shader Development with mental mill: The Making of Dead Rising 2 |
Presentation Video, Slide Deck (PDF)
Speakers: Izmeth Siddeek, Blue Castle Games and Laura Scholl, mental images |
| Up until now shaders that describe complex and life-like looks have been left to those with computer science degrees and extensive programming experience. mental mill®, puts the artist in the driver’s seat. The artist has complete creative control to write and debug MetaSL™ shaders, build shader graphs and Phenomena™, preview render in mental ray® and export to 3D DCC applications and GPU shading languages. In this session we will demonstrate mental mill and discuss how it revolutionized the look development pipeline for the making of the game, Dead Rising 2. |
Other Sessions Featuring NVIDIA
| Math/Physics for Programmers |
Please visit the GDC Vault page and search for "Math for Programmers/Physics for Programmers"
NVIDIA Speaker: Jim Van Verth |
As co-author of the book "Essential Mathematics for Games and Interactive Applications", Jim will present a portion of this two-day event focused on teaching students the fundamentals of math and physics for game development. Please see the following link for more details. |
| Advanced Visual Effects with Direct3D for PC |
D3D11 Tessellation (PDF)
DirectX 10/11Visual Effects (PDF)
NVIDIA Speakers: Cem Cebenoyan, Sarah Tariq, and Simon Green |
| This full-day session will highlight techniques for using the latest version of DirectX to create cutting-edge visuals for games. New features of the API, algorithms for lighting and shadowing, and performance optimization will be covered. |
| Khronos Developer University |
OpenGL 3.0/3.1 Overview (PDF)
Introduction to OpenCL (PDF)
NVIDIA Speakers: Neil Trevett, Barthold Lichtenbelt, and Cyril Zeller |
| This full-day tutorial will focus on Khronos open standards for media and compute acceleration, including OpenGL, OpenCL, OpenGL ES and OpenKODE. |
The formal release of NVSG 5 and Cg 2.2 will go live within the next week. Look for updates on the NVSG and Cg pages, or watch for the release announcement on our RSS and Twitter feeds.
NVSG Version 5 features include:
- Faster Performance – twice as many frames per second in many cases.
- Cg 2.2 support
- Distributed GPU Rendering– enabling scene size to scale across Quadro Plex GPUs
- MetaSL support – for leveraging shaders created within mental mill.
- 10-bit/component color support – for superior image quality on compatible hardware.
- Stencil Buffer support – enabling stencil buffer operations to occur per drawable object.
The award-winning Cg Toolkit enables software developers to add the latest interactive effects to real-time applications with a comprehensive solution that works across platforms and graphics API containing:
- Compiler for the Cg 2.2 language
- Cg/CgFX Runtime libraries for OpenGL and Direct3D
- User’s Manual and documentation on the Cg Language, Runtime APIs, Cg Library, CgFX States, and Cg Profiles
- Numerous Cg examples
Most applications these days (games included) have their own, unique ways of storing internal parameters and of running benchmarks. OpenAutomate-enabled applications, on the other hand, are automated externally via a common, standardized C-based plug-in. With virtually zero overhead and no complex files to parse or write, the OpenAutomate plug-in can query/set application parameters, run internal benchmarks and measure the resulting performance. Not only will this reduce the possibility for error in benchmarking, but it will also facilitate hundreds of times more automated testing for those applications which integrate OpenAutomate – in the end benefiting the IHV, ISV and end-user alike. OpenAutomate, and the companion UI tool oaMan, can be downloaded here.
We're pretty excited about all the cool stuff we've packed into the CUDA 2.2 beta, and invite you to try it out by signing up for it here.
Here's a short list of some of the new features we've added to the beta (read the full list here).
- Improved OpenGL interop performance
- Texture from pitch linear memory
- Zero-copy support for direct access to system memory
- Pinned shared system memory allows compute kernels to share system memory
- Asynchronous memcopy on Vista
- CUDA-GDC for 64-bit Linux
- Updated Visual Profile (now works with Windows Vista too!)
This free webinar series will be offered live with two different sessions at two different times. In the event that you cannot attend during those times, we will also offer recorded copies of those sessions.
This series will cover the basics of data parallel computing on GPU’s leveraging NVIDIA’s CUDA architecture . Tutorials will cover many topics including C for CUDA, programming to the OpenCL API , using Direct X Compute, and performance optimization techniques. These sessions will be presented by NVIDIA Developer Technology Engineering team.
Pre-registration is required if you wish to attend the live event. Please follow the links provided and registration details will be emailed back if your registration is successful.
Session 1: GPU Computing – An Introduction, 1.5 Hours + Q&A
Ideal for developers new to GPU computing, this will cover an introduction to the basics of GPU computing using the NVIDIA CUDA technology.
Concepts will be illustrated with step-by-step walkthroughs of code samples, which can be readily compiled and run. Little or no prior GPU Computing experience is required. Topics covered include:
- Writing a small GPU computing program in C from scratch
- Data transfers
- Executing functions on the GPU
- Taking advantage of on-chip shared memory
- Coordinating CPU and GPU execution
Session Dates for "GPU Computing – An Introduction" (follow links to register)
Session 2: Performance Considerations for CUDA Programming 1.5 hour + Q&A
This is a more advance session on GPU computing and optimization considerations. Concepts will be illustrated using real code examples together with actual performance gains. Attendance of the “GPU Computing – An introduction” tutorial or some experience programming using CUDA Technology is a recommended preparation for this session. Topics covered include:
- Basic optimization techniques
- Performance measurement
- Getting the most out of CUDA’s memory system
- Execution configurations.
Session Dates for "Performance Considerations for CUDA Programming" (follow links to register)
- Curious about previous NVIDIA Developer Newsletters? Try these:
- Issue 46: February "31st" 2009
- Issue 45: January 2009
- Issue 44: NVISION 2008 Followup
NVIDIA® Corporation (Nasdaq: NVDA) is the worldwide leader in graphics
processors and media communications devices. For more information about
NVIDIA please visit our website: www.nvidia.com.
© 2009 NVIDIA Corporation
