Nvidia unveils Turing architecture and GPUs with dedicated ray-tracing hardwareAugust 14, 2018
Nvidia has unveiled its new Turing architecture along with details of the first GPUs to use it. Turing includes dedicated “RT Core” hardware designed to drive ray tracing, a complex technique that can deliver extremely realistic lighting effects but has been prohibitively resource-intensive to render in real time. Nvidia calls the new Turing-based Quadro RTX the “world’s first ray-tracing GPU” and claims it’s the biggest leap since the company introduced CUDA in 2006.
The Quadro RTX products are intended for high-end professional use, not gaming — the flagship Quadro RTX 8000 will cost $10,000 when it ships toward the end of the year. For that, you get a GPU with 48GB of new GDDR6 memory, 4,608 CUDA cores, and 576 Tensor cores. Nvidia clocks its ray tracing capabilities at 10 gigarays a second, with more general performance at 16 teraflops. The GPUs will use Nvidia’s NVLink interface for hooking up multiple cards, and they also support the new VirtualLink standard that can power VR headsets over a single USB-C cable.
Nvidia made today’s announcements at SIGGRAPH, a conference targeting computer graphics professionals. Next week, however, is Gamescom, and Nvidia is widely expected to be making announcements on the next generation of its consumer-focused GeForce gaming GPUs. With Turing now unveiled at a technical level, the “spectacular surprises” Nvidia has teased could relate to how its new ray-tracing acceleration hardware will be used in mainstream games.