NVIDIA Unveils Ray-Tracing Powerhouse TITAN RTX

NVIDIA officially unveils its flagship Titan RTX GPU

It was rumored the Titan RTX might "only" ship with 12GB of GDDR6 memory, but is instead outfitted with twice that amount-T-Rex wields 24GB of GDDR6 memory underneath the hood, pushing 672GB/s of memory bandwidth.

Raw specs are much as expected.

As with all RTX card, the Titan RTX-or T-Rex, as NVIDIA has nicknamed it-is built around the company's Turing GPU. Clockspeeds check in at 1,350MHz (base) and 1,770MHz (boost). Researchers will also be able to leverage NVLink to combine two Titan RTXs when working with large data sets.

The Titan RTX delivers high-end performance for demanding applications with 576 multi-precision Turing Tensor Cores for deep learning performance, 72 Turing RT cores for ray-tracing performance and 24 gigabytes of high-speed GDDR6 memory, double the memory of last-generation Titan GPUs.

Nvidia, having already launched the RTX 2070, 2080, and 2080 Ti, is moving forward to push the RTX Titan into view.

Titan RTX also marks a return of SLI (NVLink) support to the Titan line, after it was missing in the Titan V. Like the 2080 Ti, it uses the full 100GB/s NVLink connection if you pair up a couple of Titan RTX cards. That's the biggest advantage a Titan card has ever held over a Ti.

All this should translate to minimal graphics improvements, but this isn't really a card aimed at gamers. In theory that's up to a 21 percent performance advantage.

By comparison, the original Titan was up to 16 percent faster than the GTX 780, while the Titan Black was only 4 percent faster than the 780 Ti.

Nvidia's Turing graphics cards may cost a pretty penny, but few people are going to argue with the performance of their massive arrays of tensor, RT, and CUDA cores.

Nvidia has announced today the most powerful GPU the company has manufactured so far, and possible the most powerful GPU yet produced.

The RTX Titan certainly won't come cheap.

Related:

Comments


Other news