SLI Zone
NVIDIA.com Developer Home

Last Updated: 07 / 17 / 2008

NVIDIA Developer Newsletter #41, July 2008

NVIDIA Developer Newsletter 41, July 2008

In This Issue:

NVISION 2008 is almost upon us, heralding NVIDIA's first North American developer event in over two years and with a spectacular special offer on next generation hardware.

We're also excited to report new developments that you can already use in the realms of GPU-enhanced game physics (with a competition!), GPU-based High Powered Computing with CUDA, a new trio of 3D Software Development Tools, presentations on Interactive Ray Tracing, and more -- including our monthly developer survey and GPU giveaway.


NVIDIA Developer Conference at NVISION 2008

Developer Conference at NVISION 2008

NVISION 2008 is coming to San Jose, California, August 25-27 -- a 55-hour, jaw-dropping, soul-jolting, visual feast that will overwhelm your senses and leave you wanting more.

Aside from amazing keynotes from industry luminaries and an expo hall featuring leading visual computing companies, the Professional Developer Program will bring together 77 Hours of sessions on new technologies -- some never presented before anywhere -- into a single unified venue for the first time.

NVISION 2008
NVIDIA Quadro Board
and Shader Debugger
Special Offer

Register for a Full Conference registration package (US$995) at NVISION 08 before August 18, 2008 and qualify to receive a complimentary next-generation NVIDIA® Quadro® FX high-end professional graphics board, valued at US$1999 MSRP -- and a 50% discount on our new NVIDIA Shader Debugger.

Click here for all the details -- and yes: if you've previously registered at the early bird discount, you've already won!

URL: http://www.nvision2008.com/promo.cfm

Technical Session Invitation and Program Listing (PDF, ~300kb).

Besides the Developer Conference itself, while in your "off duty" hours at NVISION you can also compete for hundreds of thousands of dollars in cash and prizes at the GeForce LAN, the legendary LAN party five years in the making; or enjoy NVScene, an unprecedented largest-ever gathering of creative minds in demoscene, machinima, game modding, and digital art on US soil.

The NVIDIA Developer Conference features numerous technical sessions. Here's a list of those we've chosen with special interest to game developers. For a full list, click here.

Mobile Visual Computing
Mike Rayfield, NVIDIA
The Future of Rendering
Rolf Herken, mental images
Game Physics: The Next Frontier
Manju Hegde, NVIDIA
High Performance Computing
David Kirk, NVIDIA
Unreal Engine 3: Features and Tools Demo
Tim Sweeney, Epic Games
Developer Tools Showcase
Randy Fernando, NVIDIA
The New "X" Factor: An Introduction to NVIDIA PhysX
James Dolan, Adam Moravansky, and Bob Whitecotton, NVIDIA
mental mill & MetaSL: Advances in GPU Shader Authoring
Rolf Berteig, mental images
The Art of PhysX: A Guide to Game Creativity
Dane Johnson, Monier Maher, and David Schoemehl, NVIDIA
Beautiful Women of the Future
Kevin Bjorke, NVIDIA
Shape of Things to Come: Next-Gen Physics Deep Dive
Bruno Heidelberger, Simon Schirm, NVIDIA
Introduction to DirectX 11
Kev Gee, Microsoft
Life on the Bleeding Edge: More Secrets of the NVIDIA Demo Team
Eugene d'Eon, NVIDIA
Advances in Shader Writing with mental ray
Andy Kopra, mental images
mental images 3D Web Services Platform: RealityServer
Ludwig von Reiche, mental images
Easy Immersion with NVIDIA 3D Stereo
Slava Gostrenko, NVIDIA
Interactive Raytracing with CUDA (New Addition!)
David Leubke and Steven Parker, NVIDIA

Follow this link for registration and schedule info.

URL: http://www.nvision2008.com/Professionals/game.cfm

It's Here! GPU Acceleration for PhysX: Now Available

NVIDIA PhysXThe latest NVIDIA PhysX System Software is now available for download -- this new version adds support for NVIDIA PhysX on GeForce 9800 GTX, GeForce GTX 280, and GeForce GTX 260 GPUs, including SLI configurations. The new system software is now also automatically included in the NVIDIA GeForce driver package as of version 177.39.

For a list of NVIDIA PhysX features, click here.

URLs:
http://www.nvidia.com/object/physx_8.06.12_whql.html
http://www.nvidia.com/Download/Find.aspx
http://developer.nvidia.com/object/physx_features.html

NVIDIA and The Game Creators PhysX Demo Contest

http://physxcomp.thegamecreators.com/ is the address you'll need to try your hand at the Game Creators/PhysX demo competition. Software and assets are provided free and prizes are to be supplied by ASUS and EVGA.

The new competetion is really two contests in one: both a challenge to create new demos for specific features of the NVIDIA PhysX toolkit running within The Game Creator's Dark Physics software, and also a challenge to create an "Über demo" with the simple criterion: knock our socks off!

Initial proposal deadline for entry is July 20th, 2008 -- with a closing deadline for finished demos: August 31st. See here for all the details, and here for downloadable software (including a complete Dark Physics package) and freely-available media files that you may use (or not) to build your winning demo!


Video: A Quick Dark Physics How-To

URLs:
http://physxcomp.thegamecreators.com/
http://physxcomp.thegamecreators.com/details.html
http://physxcomp.thegamecreators.com/downloads.html
http://www.youtube.com/v/8uTBHyC4f94

CUDA: Hardware Acceleration for High Performance Computing Webiniar

Hardware acceleration is gaining momentum as a disruptive technology that brings the power of high performance computing to the desktop. But what about its application in the data centre and performance compared to traditional CPU clusters?

This webinar presented by NVIDIA and Acceleware examines recent developments in GPU-based hardware accelerated clusters, including compelling performance, economic benefits and examples of their commercial viability.

To Find out more, listen to the archive:

URL: http://www.acceleware.com/newsEvents/webinars.cfm#HAC

NVIDIA CUDA Coding ContestCUDA Coding Contest Continues - Write Some Code, Win Some Cash!

Encoding MP3s always seem to take longer than it should. Do you wish you could find a way to make the process run faster?

Now there is a way -- you can compete to write a simple code that will speed up MP3 encoding on a CUDA-enabled GPU, and the winner will receive a US$5,000.00 cash prize.

Check out the current CUDA Coding Contest featuring a modified MP3 LAME Encoder (NVIDIA supplies the initial "starting gate" code). Sign up and show us your coding skills, and you can enter for a chance to win some cash.

Contest Deadline: July 25th!

URL: http://cudacontest.nvidia.com/

Three New and Updated 3D Software Development Tools from NVIDIA

If spring is beta season, then summer must be time for full bloom. With this newsletter we're please to announce the full release of three of NVIDIA's most popular 3D software development tools: PerfHUD 6, the NVIDIA Shader Debugger, and FX Composer 2.5.

NVIDIA Shader debuggerNVIDIA Shader Debugger Released

We are proud to announce the release of the NVIDIA Shader Debugger, a full-featured pixel shader debugger that allows shaders to be debugged just like CPU code.

The Shader Debugger offers:

  • Cross-Language, Cross-API Support
    • Microsoft DirectX 9 & 10 (HLSL)
    • OpenGL (CgFX & COLLADA FX Cg)
  • Debugger Run Control
    • Single Step, Run to Cursor, Run to Bookmark
  • Variable Inspection
    • View Globals, Parameters, and Local Variables
    • Technique, Pass, and Function selection
    • Watch Expressions
  • Visual Debugging
    • Value Visualization (Map variables to colors)
    • Conditional Pixel Kill

You can download a 30-day evaluation of the NVIDIA Shader Debugger here. A free license for non-commercial use is also available.

NVIDIA Shader Debugger Sample

The NVIDIA Shader Debugger is the first product in the NVIDIA Professional Developer Tools lineup. These are new tools directed at professional developers who need more industrial-strength capabilities and support. For example, the NVIDIA Shader Debugger will run on leading GPUs from all vendors.

In addition to the free versions available for non-commercial use, some of the new tools will be subject to a license fee, but they will be priced to be accessible to developers. Our existing free tools (such as FX Composer, PerfHUD, Texture Tools, and our SDKs) will not be affected -- they will continue to be available to all developers at no cost.

URL: http://developer.nvidia.com/object/nv_shader_debugger_home.html

FX Composer 2.5FX Composer 2.5 Final Release Now Available

FX Composer 2.5, the latest version of NVIDIA's powerful shader development environment, has been released.

FX Composer supports DirectX, OpenGL, HLSL, Collada FX, and CgFX, as well as the .fbx, .x, .3ds, .obj, and .dae file formats for importing geometry.

Version 2.5 adds:

  • DirectX 10 support, including geometry shaders and stream out
  • Particle Systems
  • Visual Styles
  • Major User Interface Improvements
  • Remote Control over TCP/IP
  • Support for the NVIDIA Shader Debugger
  • New Sample Projects

Check out our new FX Composer 2.5 Overview video, or to start working with it yourself, Download it now!

FX Composer 2.5 in action

URLs:
http://developer.nvidia.com/object/fx_composer_home.html
href="http://developer.download.nvidia.com/tools/FX_Composer/2.5/Videos/FXComposer2.5-Overview.wmv">http://developer.download.nvidia.com/tools/FX_Composer/2.5/Videos/FXComposer2.5-Overview.wmv
http://developer.nvidia.com/object/fxc_sample_projects.html

NVIDIA PerfHUD 6.0 Final ReleaseNVIDIA PerfHUD 6.0 Final Release Now Available

NVIDIA PerfHUD is a powerful real-time performance analysis tool for Direct3D applications, and it is widely used by the world's best game developers.   

Major new features in PerfHUD 6.0 include:

  • No longer requires an instrumented driver on Vista!
  • Supports GeForce 8 and 9 GPUs
  • SLI Support [Youtube] [MOV] [WMV]
  • Texture Visualization and Overrides [Youtube] [MOV] [WMV]
  • API Call List
  • Dependency View
  • New CPU/GPU Timing graph
  • And much more!

Also, don't miss our video screencasts for PerfHUD 6:

URL: http://developer.nvidia.com/object/perfhud_home.html

NVIDIA & Natural Motion at XNA Gamefest 2008

NVIDIA will be presenting talks, and co-exhibiting with Natural Motion Ltd., at the upcoming XNA Gamefest in Seattle, running July 22 and 23. Visit the NVIDIA PhysX team and Natural Motion in the Exhibitors Hall, or arrange to discuss privately in Suite #310 (you can set up a meeting online, via the Gamefest web site).

Be sure to catch these NVIDIA conference presentations:

Water-Tight, Textured, Displaced Subdivision Surface Tessellation Using Direct3D 11
Ignacio Castano, NVIDIA
In this talk, we discuss using the Direct3D 11 pipeline to tessellate displacement mapped subdivision surfaces. We cover motivation for use of tessellation in games. We also discuss various issues related to water-tight approximation of surfaces. Finally, we cover content creation issues, tools, and model quality.
Graphics Performance and Authoring Tools for Direct3D 10
Daniel Horowitz and Jeff Kiel, NVIDIA
In this fast-paced, one-hour talk, attendees learn all about NVIDIA's latest debugging, performance analysis, and content creation tools. It includes several recently-released products such as PerfHUD 6, FX Composer 2.5, and the NVIDIA Shader Debugger. For each product, key features for DirectX developers are demonstrated with the goal of helping attendees to rapidly increase their productivity.

URLs:
http://www.xnagamefest.com/
http://www.naturalmotion.com/

GPU Gems 2 OnlineGPU Gems 2 Continues in Online Serialization

As we announced in the May Newsletter, NVIDIA, in conjunction with publisher Addison-Wesley, has been making some of the very best GPU information and documentation available online -- for free!

In the weeks since our last update, we've serialized even more of GPU Gems 2:

Prefer a printed copy for your desk? Newsletter readers can purchase beautifully printed versions of all our books at a 30% discount, courtesy of InformIT and Addison-Wesley. Just follow this link.

URLs:
http://http.developer.nvidia.com/GPUGems2/gpugems2_part01.html
http://www.informit.com/promotion/136275

NVIDIA at SIGGRAPH 2008

NVIDIA GPU Hair Physics NVIDIA Interactive Ray Tracing NVIDIA GPU Tesselation in Direct3D 11

This year's SIGGRAPH will again see NVIDIA presenting leading-edge development work on topics ranging from character animation, rendering, CUDA High-Performance Computing, Interactive ray tracing, and more. NVIDIA will be presenting a special full day of technical talks on Wednesday, August 13th, 2008 in Room 405 of the Los Angeles Convention Center, two separate talks as part of the standard SIGGRAPH programming, and we'll be involved throughout SIGGRAPH and the associated graphics symposia.

This year's NVIDIA SIGGRAPH talks on Wednesday are:

Next-Generation Hardware Rendering of Displaced Subdivision Surfaces
9:00 – 10:00 am, Wednesday, August 13, Room 405
Ignacio Castaño, NVIDIA Corporation
In this talk we will provide an overview of the next-generation tessellation pipeline and its motivation. Our focus will be on one of the primary applications: rendering of displaced subdivision surfaces, which dramatically increases the realism of animated characters. We will also show how to adapt your production pipelines in order to create compelling content that takes advantage of this innovative rendering model.
Real-Time Rendering of Realistic Hair
10:15 – 10:45 am, Wednesday, August 13, Room 405
Sarah Tariq, NVIDIA Corporation
Simulating and rendering realistic hair with tens of thousands of strands is something that until recently was prohibitively expensive for real-time use. In this session, we will discuss how to render realistic hair with high geometric complexity in real-time on the GPU. Amongst other things we will cover efficient creation and rendering of high amounts of geometry for hair (essential for creating realistic hair especially when in motion), shading, self-shadowing, level of detail, and important performance optimizations. We will also talk about how to use next-generation hardware tessellation to make creating and rendering hair much more intuitive and efficient.
Adaptive Terrain Tessellation on the GPU
10:45 – 11:15 am, Wednesday, August 13, Room 405
Iain Cantlay, NVIDIA Corporation
Next-generation techniques implement highly-programmable tessellation entirely on the GPU. We explain how tessellation can be applied to terrain rendering with displacement mapping. Our tessellation scheme is adaptive, with the polygon LOD varying as a function of terrain roughness and also with view-dependent silhouette detection.
Getting Physical:
  Solutions and Case Studies for Creating Scalable PhysX Content

11:30 am – 12:30 pm, Wednesday, August 13, Room 405
Monier Maher, NVIDIA Corporation
Using physical simulation in applications takes their level of immersion to new heights. NVIDIA’s PhysX enables developers to add an unprecedented number of physical objects into scenes while maintaining high performance. This talk will feature the latest PhysX features and tools as well as real case studies that highlight common challenges and solutions.
A New Generation of Performance Analysis and Shader Authoring Tools
2:00 – 3:00 pm, Wednesday, August 13, Room 405
Jeffrey Kiel and Christopher Maughan, NVIDIA Corporation
This talk covers the latest releases of NVIDIA's popular PerfKit and FX Composer software products, as well as the brand-new NVIDIA Shader Debugger. First, learn how to extract maximum GPU performance using PerfHUD 6.0 (for real-time debugging and profiling - with tons of powerful new features), GLExpert (for OpenGL debugging), and PerfSDK (an API for accessing GPU performance counters).
Next, see how FX Composer 2.5 and the Shader Debugger can make shader authoring, profiling, and debugging a breeze for programmers, artists, and technical directors. This session showcases new features such as a source-level shader debugging for Cg and HLSL10 shaders, Direct3D 10 support (including geometry shaders, stream out, and texture arrays), visual models & styles, particle systems, a revamped user interface, and much more.
CUDA: The Democratization of Parallel Computing
3:45 – 4:45 pm, Wednesday, August 13, Room 405
Paulius Micikevicius, NVIDIA Corporation
Massively parallel computing, once the domain of supercomputers, is now widely accessible in the form of millions of CUDA-enabled GPUs. These GPUs are fully programmable, support tens of thousands of concurrent threads, and have accelerated computations in a variety of disciplines by up to 2 orders of magnitude.
We will provide an overview of the newest GPU architecture, the CUDA programming model, and latest development tools. CUDA enables efficient implementation of parallel algorithms by providing a small set of readily understood extensions to the C/C++ languages, eliminating the need to learn a new language. Development is facilitated by insightful profiling and debugging tools. Since the GPU is the only widely available commodity "manycore" chip, we will explore it as a research platform for parallel programming and architecture.
Interactive Ray Tracing with CUDA New Addition!
5:00 – 6:00 pm, Wednesday, August 13, Room 405
David Luebke and Steven Parker, NVIDIA Corporation
Ray tracing has long been associated with high-quality graphics, but it has not been suitable for interactive use. With CUDA and an NVIDIA GPU, it is now possible to ray trace reflections from curved surfaces, refractions, and accurate shadows. By combining these effects with rasterization to efficiently compute viewing ray intersections, accurate inter-reflections and other effects can be achieved at high resolutions and frame rates.

In addition to these standard-program talks:

Image-Space Horizon-Based Ambient Occlusion
Louis Bavoil, Miguel Sainz, and Rouslan Dimitrov, NVIDIA Corporation
Ambient occlusion is a lighting model that approximates the amount of light reaching a point on a diffuse surface based on its directly visible occluders. It provides a soft shadow appearance which enhances depth perception and spatial relationship between objects. In this talk, we will present a new algorithm for rendering ambient occlusion as a post-processing pass by sampling a depth buffer and its associated normal buffer. We will discuss how to integrate this approach in real-time engines as well as provide performance analysis.
Real Time Hair Simulation and Rendering on the GPU
Sarah Tariq and Louis Bavoil, NVIDIA Corporation
Simulating and rendering realistic hair with tens of thousands of strands is something that until recently was not possible in real time. In this talk we present a method for simulating and rendering realistic hair in real time using the power and programmability of modern GPUs (Graphics Processing Units). Our method utilizes new features of graphics hardware (including Stream Output, Geometry Shader and Texture Buffers) that make it possible for all simulation and rendering to be processed on the GPU in an intuitive manner, with no need for CPU intervention or read back. In addition, we propose fast new algorithms for inter-hair collision, and collision detection and resolution of interpolated hair.

URLs:
http://developer.nvidia.com/object/siggraph-2008.html
http://www.siggraph.org/s2008/
http://www.siggraph.org/s2008/attendees/techtalks/sessions.php

July Pre-NVISION Survey & GPU Giveaway

In each NVIDIA Developer Newsletter, we ask your opinion. Answer soon and you could be the winner of a new high-end NVIDIA Graphics Card.

This month we congratulate researcher and developer John Ashley of SGI. John was the winner of last month's survey giveaway. We've sent him a powerful new NVIDIA Quadro FX 3700 professional graphics card as his prize -- perfect for use with CUDA.

For July, we'd appreciate your help in planning details for NVISION 2008's Events for Developers

This offer is open only to newsletter readers. Be sure to have your answers in no later than the deadline: Wednesday, 23 July 2008.

URL: http://surveys.nvidia.com/index.jsp?pi=180fe4ebe2436360eb517b5e72f74ee5


Curious about Previous NVIDIA Developer Newsletters? Try these:
Issue 40: June 2008
Issue 39: May 2008
Issue 38: GDC 2008

If you prefer not to receive the NVIDIA Developer Newsletter in the future, please unsubscribe at http://lyris01.nvidia.com/devRelRegister/frmOptOut.asp.

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.

© 2008 NVIDIA Corporation

NVISION2008.COM




nvidiadeveloper Twitterfeed
Popular References
Free Books Online