MONTREAL — At the Conference on Neural Information Processing Systems, Nvidia (nvidia.com) introduced Titan RTX, what it claims is the world’s most powerful desktop GPU. Driven by the company’s Turing architecture, Titan RTX — dubbed T-Rex — delivers 130 teraflops of deep learning performance and 11 GigaRays of ray-tracing performance.
“Turing is Nvidia’s biggest advance in a decade – fusing shaders, ray tracing, and deep learning to reinvent the GPU,” explains Jensen Huang, founder and CEO of Nvidia. “The introduction of T-Rex puts Turing within reach of millions of the most demanding PC users — developers, scientists and content creators.”
Turing features new RT Cores to accelerate ray tracing, plus new multi-precision Tensor Cores for AI training and inferencing. These two engines — along with more powerful compute and enhanced rasterization — enable capabilities that will help transform the work of developers, designers and artists across multiple industries.
Designed for a variety of computationally demanding applications, Titan RTX provides an combination of AI, realtime ray-traced graphics, next-gen virtual reality and high performance computing. It delivers 576 multi-precision Turing Tensor Cores, providing up to 130 teraflops of deep learning performance; 72 Turing RT Cores, delivering up to 11 GigaRays per second of realtime ray-tracing performance; and 24GB of high-speed GDDR6 memory with 672GB/s of bandwidth — 2x the memory of previous-generation Titan GPUs.
The 100GB/s Nvidia NVLink can pair two Titan RTX GPUs to scale memory and compute. The performance and memory bandwidth is well suited for realtime 8K video editing. And the VirtualLink port provides the performance and connectivity required by next-gen VR headsets.
Titan RTX will be available later this month for $2,499.