SLI Zone
NVIDIA.com Developer Home

Last Updated: 10 / 12 / 2007

Developer Newsletter: Issue #27


In This Issue:

 

DEVELOPER RESOURCES


NP2_Mipmapping.jpgSDK 9.1 Released

The latest version of the NVIDIA SDK will be available this week on our developer web site.  This release includes several new code samples, bug fixes and improved documentation.  Note: SDK 9.1 requires the DirectX 9 April 2005 SDK Update.  New code samples include:

  • GPU Video and Effects
  • Discreet Cosine Transforms on the GPU
  • Computing Image Histograms using Occlusion Queries

Back to top


NP2_Mipmapping.jpgNVPerfHUD Video for Registered Developers

We've created a video that shows off all the new features in the next version of NVPerfHUD.  A beta build and the video are currently available to all registered developers.  We expect that NVPerfHUD 3.0 will be available to all developers on our Developer Web Site in the next few weeks.

Back to top


NP2_Mipmapping.jpgNon-Power-of-Two Mipmap Creation Whitepaper

This whitepaper explains the intricacies of creating mipmaps for non-power-of-two (NP2) textures.

Back to top


Translated Developer Newsletters Now Online

The last two developer newsletters are now available in Japanese, Chinese, and Korean, in addition to English.  To see previous newsletters, please visit our developer newsletter archive.  If you aren't yet receiving the newsletter, make sure to sign up -- each month, it mentions the latest developer resources, upcoming events, recently released hardware, GPGPU news, valuable tips, job postings, and more.

Back to top


Become a Registered Developer Today

Joining our Registered Developer program is free and gives you access to a number of benefits:

  • Developer Forums
  • Prerelease Tools
  • Prerelease Drivers
  • Bug Reporting

Joining is easy!  Simply fill out one of applications below:

Please note that it may take a few weeks to receive a decision on your application, due to the large number of applicants.

Back to top


GPGPU Feature: GPUs as Mathematical Coprocessors in Finite-Element Simulations

The talk slides from this workshop, which took place in April, are now available.  The first talk was an entry-level GPGPU introduction by Robert Strzodka, followed by a discussion of hardware-efficient PDE solvers with applications in Image Processing. After a brief review of the current state-of-the-art of FEM codes on the CPU side, algorithmic design patterns for efficient GPU implementations were discussed.

Back to top

EVENTS


NVIDIA at E3 2005

E3 2005 promises to be another exciting show for the interactive entertainment industry. There's no better place for you to play the hottest new titles, see the latest industry developments and trends, or make a sales pitch for your products.

This year, NVIDIA offered a SLI system seeding program to developers who wanted to show their games running on SLI in their booths. The following partners provided the components necessary to build these SLI systems: Corsair Memory, Creative Labs, Hitachi (Hard drives), MSI (Motherboards), XFX (Graphics Cards). Game Developers and Publishers including Epic, EIDOS, Majesco, Namco and WebZen are all taking advantage of the SLI seeding program and will have systems in their booths. This program coincides with NVIDIA's overall effort to get SLI into the hands of development community.

For inquiries regarding SLI systems for PC development purposes, please contact your account manager.

Back to top


Tip of the Month: The Benefits of Hardware Shadow Mapping


Comparing Filtering for 64-Sample Soft Shadows

Hardware
Shadow Mapping

Regular
Percentage-Closer Filtering
Since the GeForce3 processor was released in 2001, NVIDIA GPUs have supported hardware-accelerated shadow map filtering.  Hardware shadow mapping, as it is commonly known, allows shadow map queries to produce smoothly-varying gray-scale results that are superior to ordinary percentage-closer filtering (PCF) or nearest filtering.  And because there are dedicated transistors on-chip, the smoother result comes at extremely low cost (often for free).

So how does "hardware shadow mapping" produce such a smooth result?  Regular PCF is able to produce only as many shades of gray as the number of samples that are used.  This results in marked blockiness as one zooms closer to shadowed regions unless the number of samples increases dramatically (which causes a corresponding load increase in the pixel shader). 

In contrast, hardware shadow mapping uses a bilinear filter on top of the usual PCF step, resulting in smooth grey values even if the viewer zooms in on the shadowed regions.  As you zoom in, hardware shadow mapping is therefore able to deliver arbitrarily higher quality without taking additional samples and while maintaining the same frame rate.

Learn more about hardware shadow mapping in Section 6.2 of our GPU Programming Guide.

Back to top


Featured Pages and Downloads

Some of the most popular pages and downloads over the past few weeks have been:

  • NVIDIA GPU Programming Guide. Useful advice on how to identify bottlenecks and eliminate them by taking advantage of the latest GPU features.

  • FX Composer 1.6. Includes several new features such as Shader Model 3.0 support, material panel improvements, DXSAS support, and more.

Back to top


Job Openings

NVIDIA's Developer Technology group is always looking for talented engineers and artists in the US, Japan, and Europe. See http://talent.nvidia.com for more general information, or our specific openings for: Mobile Device Developer Technology Engineer (USA, Europe, and Korea), and 3D Professional Applications Developer Technology Engineer.

Back to top


Newsletter Distribution

Please feel free to forward this newsletter to friends, coworkers, or any other potentially interested parties. In addition, if you know of anyone who might be interested in signing up for the newsletter, please point them to http://developer.nvidia.com/object/Newsletter_Signup.html.

Back to top


Past Newsletter Issues

In case you missed any of our previous newsletter issues, you can find them online at our Developer Newsletter Archive in a variety of languages, including Japanese, Chinese, Korean, and English.

Back to top

 
If you prefer not to receive the NVIDIA Developer Newsletter in the future, please send an e-mail to devrelfeedback@nvidia.com with the word REMOVE in the subject line. Make sure to reply from the e-mail address that you would like us to remove from our list.

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.

developer.nvidia.com
The Source for GPU Programming

 



nvidiadeveloper Twitterfeed
Popular References
Free Books Online