News

Nvidia Announces Turing Hybrid GPUs for Deep Learning, Real-Time Ray Tracing

• By Becky Nagel
• 08/15/2018

Calling it the "greatest leap since the invention of the CUDA GPU," Nvidia this week announced its new Nvidia Turing architecture: hybrid GPUs combining Tensor Cores (aimed at AI processing) and RT Cores (aimed at real-time ray tracing) that significantly boost what creative professionals and enterprises can achieve with these GPUs.

"Turing features new Tensor Cores, processors that accelerate deep learning training and inferencing, providing up to 500 trillion Tensor operations per second," the company said of the new product line.

"The Turing architecture is armed with dedicated ray-tracing processors called RT Cores that accelerate the computation of how light and sound travel in 3D environments at up to 10 Giga Rays per second," the company continued. "Turing accelerates real-time ray tracing by 25x over previous Pascal generation, and can be used for final frame rendering for film effects at more than 30x the speed of CPUs."

Ray tracing is a technique in computer graphic animation whereby interaction between objects is simulated by tracing the path of light streams. It is highly computation intensive and, until now, almost always rendered in advance.

The Turning architecture will initially present itself in Nvidia's line in the form of three new desktop chips -- Quadro RTX 5000, Quadro RTX 6000 and Quadro RTX 8000 GPUs. They are not yet live.

"Turing is Nvidia's most important innovation in computer graphics in more than a decade," commented Jensen Huang, founder and CEO of Nvidia. "Hybrid rendering will change the industry, opening up amazing possibilities that enhance our lives with more beautiful designs, richer entertainment and more interactive experiences. The arrival of real-time ray tracing is the Holy Grail of our industry."