NVIDIA announced its newest GPUs based on the new Turing architecture at the SIGGRAPH professional graphics conference in Vancouver.

Turing, NVIDIA's eight generation GPU architecture, is being hailed as the greatest leap since the invention of the CUDA GPU in 2006. Fusing real-time ray tracing, AI, simulation and rasterization, Turing promised to fundamentally change computer graphics. Accelerating ray tracing thanks to new RT Cores and featuring new Tensor Cores for AI inferencing which, together for the first time, will make real-time ray tracing possible.

"This fundamentally changes how computer graphics will be done, it’s a step change in realism,” Jensen Huang, NVIDIA CEO

Key Turing Innovations

RT CORES FOR REAL-TIME RAY TRACING
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. 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.

NEW STREAMING MULTIPROCESSOR
The Turing architecture dramatically improves raster performance over the previous Pascal generation with an enhanced graphics pipeline and new programmable shading technologies. These technologies include variable-rate shading, texture-space shading, and multi-view rendering, which provide for more fluid interactivity with large models and scenes and improved VR experiences.

TENSOR CORES FOR AI ACCELERATION
Turing features new Tensor Cores, processors that accelerate deep learning training and inferencing, providing up to 500 trillion Tensor operations per second. This level of performance dramatically accelerates AI-enhanced features -- such as denoising, resolution scaling and video re-timing -- creating applications with powerful new capabilities.

CUDA FOR SIMULATION
Turing-based GPUs feature a new streaming multiprocessor (SM) architecture that supports up to 16 trillion floating point operations in parallel with 16 trillion integer operations per second. Developers can take advantage of up to 4,608 CUDA cores with NVIDIA’s CUDA 10, FleX and PhysX SDKs to create complex simulations, such as particles or fluid dynamic for scientific visualization, virtual environments and special effects.

NVIDIA also announced CUDA 10, the latest software development platform for building GPU-accelerated applications with support for Turing GPUs, performance optimised libraries, a new programming model for defining program execution, and enhanced graphics API interoperability.

Turing based Quadro Products (Contact us for availability)

Designed, built and tested by NVIDIA, Quadro® desktop products are the #1 choice of millions of creative and technical users. Equipped with the world’s most powerful GPUs, large memory capacities, 8K display outputs, advanced features to drive real-time photorealistic rendering, AI-augmented workflows, VR environments and more, Quadro is built to accelerate a range of professional workflows.

QUADRO RTX 8000 Armed with NVIDIA Turing architecture, 4608 CUDA cores, 576 Tensor cores and 48 GB memory, it is built to power the next generation of visual computing workflows. ENQUIRE	QUADRO RTX 6000 Created with 24 GB of GDDR6 memory and the NVIDIA Turing architecture to dramatically boost productivity and create content faster than ever before. ENQUIRE	QUADRO RTX 5000 Built with the NVIDIA Turing architecture and 16 GB of GDDR6 memory to tackle demanding design and visualization workloads with ease. ENQUIRE

Turing resets the way content is created and enjoyed across industries, opening amazing creative possibilities that until recently were assumed to be years away. Contact BIOS IT for more information, pricing and availability.