VDPAU (Video Decode and Presentation API for Unix) allows Linux systems to offload portions of video decode to the GPU. The resulting video can be post-processed with OpenGL, CUDA, or both. Watch Stephen Warren from NVIDIA explain VDPAU and demonstrate OpenGL texturing of hardware-decoded video frames. Slides (PDF) are also available.
Enj appears to be enjoying the GTC 2010 Conference this week. He brings us an inside view of the conference, and a feel of the different talks on OpenCL and CUDA. If you have 5 minutes, pop over to enja.org, it'll be worth your time.
OpenCL framework to accelerate an EMRI modeling application using the hardware accelerators – Cell BE and Tesla CUDA GPU. The main goal of this work is to evaluate an emerging computational platform, OpenCL, for scientific computation. Results show OpenCL binary on a par with CUDA SDK. Baseline is an AMD Phenom 2.5Ghz CPU.
The new version of GPU Caps Viewer is available with the support of OpenGL 4.1 context and a better support of OpenCL. Now you can select the GPU that will be used to execute the kernels of the OpenCL demos. GPU Caps Viewer is an information utility focused on the OpenGL, OpenCL and CUDA API level support.
Developers that have a CUDA codebase and wish to be using OpenCL, here is a small tool to help you make that move. Swan is an open source GPL'd command line tool that aids the reversible conversion of existing CUDA codebases to OpenCL. A complete list of what Swan can and cannot do is available on their website.
GPU Caps Viewer 1.8.0 is available for download. This new version adds OpenGL 3 as well as OpenCL support with a new panel and several OpenCL demos. GPU Caps Viewer is a graphics card utility for Windows. It quickly describes the essential capabilities of your graphics card including GPU type, amount of VRAM, GPU temperature, OpenGL, OpenCL and CUDA API support. I also offers OpenGL and OpenCL demos to test the latest features of your video card.
NVIDIA launched the GeForce GT 240. The chipset uses the newer 40 nanometer manufacturing process, is low energy occupying only one slot without the need of a separate power connector. The NVIDIA GTX 240 card has 96 processing cores, 32 texture units, a 550MHz primary clock speed and can handle up to 1GB of GDDR5 memory running at 1.7GHz. The card supports OpenGL and DirectX 10-level graphics, CUDA, PhysX and OpenCL for general-purpose computing.
NVIDIA is hosting two more seminars over the next few days which cover 'Best Practices for OpenCL Programming', and 'An Introduction to GPU Computing and OpenCL'. The series will cover many topics including C for CUDA, programming to the OpenCL™ API , using DirectCompute and performance optimization techniques. The Webinars are presented by NVIDIA Developer Technology Engineering team and have NVIDIA staff online to answer Questions.
ExtremeTech discusses GPGPU computing on Windows 7. "Both Nvidia and ATI are committed to supporting DirectX 11 on their newest boards; and both now have early OpenCL drivers out as well. In particular, I expect both of their Windows 7 drivers will support OpenCL." says Michael Miller.
NVIDIA has released the first public OpenCL conformant GPU drivers as well as a powerful performance profiling tool and an OpenCL Best Practices Guide. The OpenCL Visual Profiler uses the extensive performance instrumentation in NVIDIA’s OpenCL drivers and hardware performance signals designed into NVIDIA GPUs to provide developers with insight into performance bottlenecks and opportunities for optimization. The OpenCL Best Practices Guide designed to help OpenCL developers programming for the CUDA architecture implement high performance parallel algorithms and understand best practices for GPU Computing. The OpenCL drivers, Visual Profiler, and Best Practices Guide are all available on the NVIDIA developers website.
While OpenCL is very similar in many respects to NVIDIA's CUDA, it adds features to take advantage of other targets; and though it's quite complex, it has the potential to deliver very high performance, and is much easier than trying to map your computation into OpenGL or graphics primitives. So says Michael Wolfe, with over 30 years in both academia and industry on developing compilers, and is now a senior compiler engineer at The Portland Group, Inc., a wholly-owned subsidiary of STMicroelectronics, Inc.
NVIDIA released a new OpenCL Visual Profiler for Windows and Linux for developers. Leveraging the extensive performance instrumentation in NVIDIA's OpenCL drivers and hardware performance signals designed into NVIDIA GPUs, the OpenCL Visual Profiler provides developers with insight into performance bottlenecks and opportunities for optimization. NVIDIA also released a Best Practices guide for OpenCL.
All NVIDIA CUDA-Enabled GPUs Shipped by Apple Supported under New Operating System. OpenCL on the NVIDIA® CUDA™ architecture enables applications to use the CPU and the GPU together as co-processors. NVIDIA’s integration of the CUDA architecture across its brands and segments enables it to offer Apple users a broad selection of 10 GPU models officially supported by Snow Leopard.
Jon Peddie has issued a press release stating that 2010 will show the graphics industry making a spectacular comeback, after the dismal 2009 year. "Architectural changes like Intel's Nehalem and new product introductions from AMD, ATI, Intel, and Nvidia are going to be disruptive to the status quo" says Jon Peddie. Snow Leopard and Windows 7 will also act as a catalyst to spur on the continuing expansion of GPGPU, otherwise known as GPU compute. OpenCL along with DirectX and NVIDIA's CUDA will go even further in making the GPU a "serious, economical, and powerful coprocessor in all level of PCs."