The Siggraph 2018 Conference brought in the biggest announcements from Nvidia unveiling a new turing architecture and three new pro-oriented workstation graphics cards in its Quadro family. This is the greatest leap for Nvidia since the introduction of the CUDA GPU in 2006. The Turing architecture features new RT Cores to accelerate ray tracing and new Tensor Cores for AI inferencing to enable real-time ray tracing.
The two engines along with more powerful compute for simulation and enhanced rasterization will usher in a new generation of hybrid rendering to address the $250 billion visual effects industry. Hybrid rendering enables cinematic-quality interactive experience, amazing new effects powered by neural networks and fluid interactivity on highly complex models.
The company also unveiled its initial Turing-based products – the NVIDIA® Quadro® RTX™ 8000, Quadro RTX 6000 and Quadro RTX 5000 GPUs. They are expected to revolutionize the work of approximately 50 million designers and artists across multiple industries.
At the Annual Siggraph conference, Jensen Huang, founder and CEO, Nvidia mentions,
“Turing is NVIDIA’s most important innovation in computer graphics in more than a decade.
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.”
Here’s the list of Turing architecture features in detail.
Real-Time Ray Tracing Accelerated by RT Cores
- The Turing architecture is armed with dedicated ray-tracing processors called RT Cores. It will accelerate the computation similar to light and sound travel in 3D environments at up to 10 GigaRays a second.
- Turing will accelerate real-time ray tracing operations by up to 25x than that of the previous Pascal generation.
- GPU nodes can be used for final-frame rendering for film effects at more than 30x the speed of CPU nodes.
AI Accelerated by powerful Tensor Cores
- The Turing architecture also features Tensor Cores, processors that accelerate deep learning training and inferencing, providing up to 500 trillion tensor operations a second.
- It will power AI-enhanced features for creating applications with new capabilities including DLAA (deep learning anti-aliasing). DLAA is a breakthrough in high-quality motion image generation for denoising, resolution scaling and video re-timing.
- These features are part of the NVIDIA NGX™ software development kit, a new deep learning-powered technology stack. It will enable developers to easily integrate accelerated, enhanced graphics, photo imaging and video processing into applications with pre-trained networks
Faster Simulation and Rasterization with New Turing Streaming Multiprocessor
- A new streaming multiprocessor architecture is featured in the new Turing-based GPUs to add an integer execution unit, that will execute in parallel with the floating point datapath. A new unified cache architecture with double bandwidth of the previous generation is added too.
- As it is combined with new graphics technologies like variable rate shading, the Turing SM achieves unprecedented levels of performance per core. With up to 4,608 CUDA cores, Turing supports up to 16 trillion floating point operations in parallel with 16 trillion integer operations per second.
- Developers will be able to take advantage of NVIDIA’s CUDA 10, FleX and PhysX SDKs to create complex simulations, such as particles or fluid dynamics for scientific visualization, virtual environment and special effects.
The new Turing architecture has already received support from companies like Adobe, Pixar, Siemens, Black Magic, Weta Digital, Epic Games and Autodesk. The new Quadro RTX is priced at $2,300 for a 16GB version and $6,300 for 24GB version. Double the memory to 48GB and Nvidia expects you to pay about $10,000 for the high-end card.
For more information you may visit the Nvidia official blog page.