Last Updated:
06
/
11
/
2009
NVIDIA Developer Newsletter 48: June 2009
Welcome to June's NVIDIA Developer Newsletter!
We have a lot of new things to announce this time around, but the big news is SIGGRAPH 2009. We have a ton of presentations, plus a couple of new announcements, for this year's SIGGRAPH, so you don't want to miss it!
SIGGRAPH isn't the only big conference coming up. The 3-day NVIDIA GPU Technology Conference, to be held between Spetember 30th and October 2nd in San Jose, CA, is also approaching quickly. We also currently have an open call for submissions for this conference. You can read more details below.
Starting with this issue, the developer newsletter is bringing you more information about GPU Compute news, so we're organizing the content a little differently. Our index will first feature NVIDIA announcements of interest to the entire developer community, followed by items specifically related to graphics, then by items specifically related to GPU Computing. We would love to hear specific feedback on this format, and invite you to send email to the NVIDIA Developer Relations team.
Ok, let's get on with it!
P. S. -- Don't forget you can get instant news updates from NVIDIA by subscribing to the "nvidiadeveloper" feed on Twitter!
General
Graphics
GPU Compute
General
SIGGRAPH 2009 Sessions Announced
This year, NVIDIA will have 13 presentations at SIGGRAPH 2009, including 6 special sessions designed to give you up-to-date information on the latest technical innovations from NVIDIA. This year's SIGGRAPH promises to be a great event, and we look forward to seeing you in New Orleans between August 3rd and 7th!
This newsletter represents a snapshot-in-time of the SIGGRAPH plans. For up-to-date information on NVIDIA-related events at SIGGRAPH, please visit NVIDIA's SIGGRAPH 2009 page on the NVIDIA Developer Zone.
Accepted Papers, Panels, and Tutorials
Note: Please check the formal SIGGRAPH 2009 Schedule for updates on sessions and times. You can also find updates on NVIDIA's SIGGRAPH 2009 page on the NVIDIA Developer Zone.
- Evan Hart, Panel on 3D Graphics
- Dilip Sequeira, “A Discussion of Issues Concerning Simulated Physics in Games”
- Jonathan Cohen, Simon Green, and Sarah Tariq, "Real-time Car Turbulence", Computer Animation Festival (Real Time Rendering Section)
- Louis Bavoil and Sarah Tariq, "Real-time Hair Simulation", Computer Animation Festival (Real Time Rendering Section)
- Dave Luebke, "Beyond Programmable Shading" tutorial (Long course)
- Tianyun Ni and Ignacio Castano, “Efficient substitutes for subdivision surfaces" (1/2 day course)
- Louis Bavoil, Miguel Sainz, "Multi-Layer Dual-Resolution Screen-Space Ambient Occlusion" (Rendering section)
NVIDIA-Sponsored Sessions (All day, Wednesday, August 5th)
Advances in GPU-based Image Processing and Computer Vision, James Fung (NVIDIA Corporation), 8:30-9:30am
As a massively parallel processor, the GPU is well-suited for performing 'per-pixel' operations in image processing and computer vision. However, new changes in hardware, software, and algorithm mappings allow entire vision algorithms to be performed solely on GPU. In this session, we'll discuss how GPU programming now goes beyond per-pixel mappings, and is providing speedups in image feature processing and handling, frequency domain processing, graph cuts segmentation, and more.
"3D Vision Technology - Develop, Design, Play in 3D Stereo", Samuel Gateau (NVIDIA Corporation), 9:45-10:45am
This session will present a detailed technical overview of implementing a 3D stereo experience in your application. Specifically, we will address the use cases you must address to create compelling 3D stereo applications, with an emphasis on some key technology challenges and how many are easily addressed by some basic implementation patterns. If you’re a 3D graphics developer, you will come away with a complete set of knowledge on how to implement outstanding 3D stereo applications.
Creating Immersive Environments with NVIDIA APEX, Jean Bordes, Randy Fernando, and Monier Maher (NVIDIA Corporation), 11:00am-12:15pm
In this talk, you will learn about APEX, which greatly speeds up content development by providing artist-friendly tools as well as a framework that enables turn-key solutions without a lot of engineering effort. Find out about our newly expanded suite of APEX packages (Matrix-like destruction, cinematic smoke, free-flowing clothing, fully destructible forests, interactive leaves and other ground debris, and weapon impact effects) and see real-world game examples where artists were quickly able to convert static environments into dynamic ones. Come and discover how you can enhance your games and provide a truly immersive game experience.
Alternative Rendering Pipelines on NVIDIA CUDA, Andrei Tatarinov & Alexander Kharlamov (NVIDIA Corporation), 1:30-2:30pm
This session will show how NVIDIA CUDA can be used for solving complex graphics problems. Ray-tracing and REYES are known for being hungry to computational powers, and CUDA is a perfect tool to increase performance of these approaches. The speakers present their approaches to implementing ray-tracing and REYES on CUDA, and show how to use CUDA features to achieve interactive performance on these applications.
Efficient Ray Tracing on NVIDIA GPUs, Steve Parker and Phillip Miller (NVIDIA Corporation), 2:45-3:45pm
Learn about a new, general programming interface for conducting incredibly fast ray tracing on NVIDIA GPUs using C for CUDA. This new technology will be valuable to anyone wanting to build a high performance ray trace renderer (be it interactive or off-line), accelerate an existing ray trace renderer, add ray trace capabilities to raster renderers, or even perform generic ray tracing functions.
Accelerating Realism with the NVIDIA Scene Graph, Holger Kunz and Phillip Miller (NVIDIA Corporation), 4:00-5:00pm
The NVIDIA Scene Graph quietly powers many of the world’s most demanding real-time design environments. Learn how applications can adopt this technology to greatly increase their real-time performance, interactive scene size, and rendering realism through a highly tuned scene graph, distributed GPU rendering, CgFX and now even ray tracing.
NVIDIA will be sponsoring the GPU Technology Conference, to be held at the Fairmont Hotel in San Jose, California, September 30th through October 2nd, 2009. The conference will be divided into three separate summits: Emerging Companies Summit, NVIDIA Research Summit, and GPU Developers Summit. The GPU Developers Summit is designed to help developers of consumer, professional, and HPC applications to harness the massively parallel processing power of the GPU. Experts from a broad range of industries will share insights and updates on state of the art techniques in GPU Computing, media processing, advanced visualization and related areas. Presentations will cover a wide range of topics using industry standard languages such as C/C++ with CUDA extensions and Fortran, GPU Computing APIs such as DirectX Compute and OpenCL™ on the CUDA Architecture, graphics API's such as Direct3D and OpenGL and powerful libraries and middleware. For detailed information on the entire event, please visit http://www.nvidia.com/gtc.
Submit a proposal to the call for submissions for a chance to present among your peers.
The GPU Developers Summit and NVIDIA Research Summit are seeking submissions for proposals to be presented at the GPU Technology Conference. If you are interested in submitting a proposal, click on the green button below. Please note that the deadline for tutorials, sessions, panels, and BOFs is approaching quickly.
GPU Developers Summit
Call for Tutorials, Sessions, Panels and Birds of a Feather
Deadline: June 23, 2009
NVIDIA is looking for submissions from industry and academia for the GPU Developers Summit. Submissions include tutorials, sessions, panels and birds of a feather
Criteria: The submission should be about your work using the GPU for computing or graphics, and can be completed or currently in progress.
NVIDIA Research Summit
Call for Research Roundtables
Deadline: July 7, 2009
Criteria: Roundtable sessions will be 45 minutes in length and consist of a discussion between the moderator and audience that highlight the application of the GPU in scientific and engineering research. Note that audience engagement is central to Research Roundtables. Unlike traditional talks, tutorials, or panels where an individual or small group of experts present, in Roundtables, the attendees provide the discussion and the Moderator’s job is to organize a coherent event: engage the audience, pose questions, ensure balanced discussion, and perhaps gather possible follow-up actions.
Call for Research Posters
Deadline: August 24, 2009
The NVIDIA Research Summit invites submissions of research posters describing ongoing research, exciting new research projects, and encouraging preliminary results. This poster session provides an excellent opportunity to share and discuss your ideas and latest research results with colleagues from many different fields and with NVIDIA researchers and engineers.
For a complete list of deadlines and submission guidelines please click here.
New NVIDIA Drivers: 185.85 and beta 186.08
Driver version 185.85 is now available for consumers and includes
- Stereoscopic 3D support for Windows 7, 32- and 64-bit
- Support for Mitsubishi Home Theater TVs
- Many new 3D Vision Profiles added (see here for the complete list)
The 186.08 beta drivers have numerous bug fixes, as well as support for new GPU-accelerated DirectX APIs in Windows 7: DirectX Compute, Direct2D, DirectWrite, and DXVA-HD.
Both drivers include support for the CUDA Toolkit 2.3.
Graphics
Bindless Graphics for OpenGL Tutorial
Bindless Graphics refers to changes to OpenGL that can enable close to an order of magnitude improvement in the CPU-limitedness of graphics applications. Recent improvements in programmability have focused on additional flexibility in shaders (expanding formats to include more float and integer types, better branching support, etc.) and enabling new features (geometry programs, transform feedback, etc), and while some of these allow offloading parts of certain workloads to the GPU, they don't directly attack the issues that dominate CPU time.
Read the full article here.
The formal release of NVSG 5 and Cg 2.2 is now available.
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
GPU Compute
GPU Computing Online Seminars
NVIDIA is pleased to host a series of free online seminars about GPU Computing starting from the basics of Data parallel computing, covering details about NVIDIA CUDA parallel computing architecture and tutorials on OpenCL and DirectX Compute. For details about each course, please visit http://developer.nvidia.com/object/gpu_computing_online.html. Below are the "quick links" to sign up for the courses:
GPU Computing Introduction to CUDA, 1.5 Hours
Performance considerations for CUDA programming, 1 hour
Advanced CUDA Optimization Techniques, 1 hour
CUDA-Related Online Seminars:
CUDA and MATLAB
Find out how the Jacket CUDA-plugin for NVIDIA’s GPUs accelerates MATLAB by 10x-50x for a range of applications like imaging, signal processing, life sciences, and bio-informatics.
June 17, 2009, 9am Pacific.
Follow this link to register for this free seminar https://www.livemeeting.com/lrs/1100002761/Registration.aspx?pageName=vn5l3hnncfrs1shq
OpenCL drivers now available to GPU Computing Registered Developers
OpenCL™ (Open Computing Language) is a new heterogeneous computing environment that runs on the CUDA architecture. It will allow developers to harness the massive parallel computing power of NVIDIA GPUs to create compelling computing applications.
In partnership with NVIDIA, OpenCL was submitted to Khronos by Apple in the summer of 2008 with the goal of forging a cross platform environment for GPU computing. NVIDIA chairs the OpenCL working group with direct support from NVIDIA’s SW engineering team. The SIGGRAPH ASIA Khronos OpenCL presentation by Neil Trevett of NVIDIA can be found here
As part of the OpenCL presentation NVIDIA featured the world's first OpenCL GPU demonstration, running on a laptop NVIDIA GPU.
Pre-release OpenCL conformance candidate drivers are now available to thousands of GPU Computing Registered Developers.
Click on the link if you are a professional developer interested in joining the NVIDIA GPU Computing Registered Developer Program
NVIDIA CUDA Presentations, Demos, and Code Samples
’s engineers are pushing technology boundaries with CUDA, creating new libraries, papers, applications, and demos.
Thrust (code)
Author: Nathan Bell, NVIDIA
A CUDA library of parallel algorithms with an interface resembling the C++ Standard Template Library (STL).
http://www.nvidia.com/object/cuda_home.html#state=detailsOpen;aid=dc080580-35cb-11de-8a39-0800200c9a66
3D Finite Difference Computation on GPUs using CUDA (paper)
Author: Paulius Micikevicius, NVIDIA
Describes GPU parallelization of 3D finite difference computation.
http://www.nvidia.com/object/cuda_home.html#state=detailsOpen;aid=3c7462e0-0f59-11de-8c30-0800200c9a66
Real-Time 3D Fluid and Particle Simulation and Rendering (demo)
Authors: Jonathan Cohen, Sarah Tariq, NVIDIA
Uses a GPU-based 3D fluid solver with a moving domain to seamlessly advect hundreds of thousands of particles.
http://www.nvidia.com/object/cuda_home.html#state=detailsOpen;aid=4808dd20-0f59-11de-8c30-0800200c9a66
CUDA Developer Community Contributions from Industry and Academia
Every week we learn about innovative ways people are computing with the GPU. Here are some examples recently posted on NVIDIA's CUDA Zone site:
MEDICAL
Accelerating Leukocyte Tracking Using CUDA: A Case Study in Leveraging Manycore Coprocessors (paper)
Authors: Michael Boyer, David Tarjan, Scott T. Acton, Kevin Skadron / Departments of Computer Science and Electrical and Computer Engineering, University of Virginia
Demonstrates “how a systems biology application -- detection and tracking of white blood cells in video microscopy -- can be accelerated by 200x using a CUDA-capable GPU.”
Multidimensional Decomposition for Nuclear Magnetic Resonance (code)
Author: Ilgis Ibragimov / Elegant Mathematics Ltd.
This algorithm speeds up the recording of high-resolution NMR spectra running on an NVIDIA Tesla Personal supercomputer.
GENETICS
Many-Core Algorithms for Statistical Phylogenetics (code, paper)
Authors: M. A. Suchard and A. Rambaut / Department of Biomathematics/ Biostatistics / Human Genetics, UCLA and Institute of Evolutionary Biology, University of Edinburgh
“Results: A near 90-fold speed increase over an optimized CPU-based computation and a >140-fold increase over the currently available implementation, making this the first practical use of codon models for phylogenetic inference over whole mitochondrial or microorganism genomes.”
GPU Computing on YouTube
Check out these YouTube videos posted by GPU4Vision, a project at the Institute for Computer Graphics and Vision, Graz University of Technology. The project focuses on cutting-edge research in the field of vision algorithms using CUDA-based GPUs.
- Curious about previous NVIDIA Developer Newsletters? Try these:
- Issue 47: April "Post-GDC" Report 2009
- Issue 46: February "31st" 2009
- Issue 45: January 2009
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.
© 2009 NVIDIA Corporation
