NVIDIA introduced NVIDIA® GPUDirect™ for Video, a technology that enables application developers to deliver higher quality, more realistic on-air graphics – or take faster advantage of the parallel processing power of the GPU for image processing – by permitting industry-standard video I/O devices to communicate directly with NVIDIA professional Quadro® and Tesla™ graphics processing units (GPUs) at ultra-low latency.
NVIDIA GPUDirect™ for Video technology is the fastest, most deterministic way to get video to the GPU for processing, enabling leading video I/O board manufacturers to take advantage of the programmability of the GPU. With GPU Direct for Video, the video I/O card is fully synchronized with the GPUs, eliminating CPU overhead and, most importantly, dramatically reducing latency.
“NVIDIA and our partners are redefining what’s possible in real-time video production,” said Greg Estes, industry executive, Media & Entertainment, NVIDIA. “Enabling lower latency solutions for processing real-time video streams will benefit not just those working in broadcast and production facilities, but also applications in manufacturing, healthcare and government agencies.”
“AJA is supporting NVIDIA's new capability with our latest generation of video I/O products,” said Nick Rashby, President, AJA Video Systems. “This
will allow developers whose apps support AJA video I/O products to take
better advantage of the power of NVIDIA Quadro and Tesla GPUs,
resulting in low-latency access for both graphics compositing and
general purpose processing using CUDA or OpenCL, with all the I/O and
performance they depend on from AJA.”
broadcasters and video production professionals had to contend with
delays of as many as ten frames – an amount easily visible to the eye -
when transferring video from a video I/O device to a GPU, because the
two devices could not communicate directly with one another to ensure
synchronization. This required application developers to manage complex
buffering schemes, leading to unnecessary CPU overhead and increased
latency. Most importantly, these delays in aggregate significantly
raised the cost and complexity of larger broadcast productions.
“DVS is known for developing the highest quality video boards in the market,” says Juergen Heger, senior product manager at DVS Digital Video Systems GmbH. “In real-time production environments, the latency between GPU and SDI is a critical point for our customers. Our famous, longstanding SDK now includes NVIDIA GPUDirect for Video. Our hardware solutions directly communicate with NVIDIA professional Quadro and Tesla GPUs without noticeable delay, which is ideal for applications like compositing, live graphics or real-time video-processing.”
NVIDIA GPUDirect for Video technology will further advance the growing adoption of GPUs in film, live broadcast, and video production. Companies such as 3Ality Digital, Adobe, AJA, Autodesk, Avid, Binocle, Blackmagic Design, Brainstorm, Chyron, DVS, GenArts, MainConcept, RT Software, Quantel, Sony, The Foundry, Vizrt plus a growing number of application developers are already using GPU computing to accelerate their applications.
With the new NVIDIA GPUDirect™ for Video solution being unveiled at IBC 2011, video I/O manufacturers, companies who make their own proprietary hardware, and even companies making video switchers will be able to take advantage of these sub-frame, low latency transfers in their own SDKs and commercial solutions for no additional cost.
NVIDIA GPUDirect™ for Video technology is available immediately, free of charge, directly from NVIDIA for video I/O manufacturers, proprietary hardware providers, and video switcher manufacturers. Video I/O hardware developers can request information and access to the SDK via e-mail: GPUDirectForVideoemail@example.com, or they can visit the NVIDIA GPUDirect™ for Video registration page at http://developer.nvidia.com/gpudirectforvideo. NVIDIA expects commercially available solutions from its partners will be on the market by late 2011. NVIDIA GPUDirect™ for Video is supported on Windows 7 and Linux, and is designed to work with NVIDIA Quadro® 4000, Quadro® 5000, and Quadro® 6000 GPUs, and NVIDIA Tesla® C-Series GPUs.