Nvidia has released a new generation of chips aimed at helping expand its business among movie makers and other graphics professionals.
Nvidia has rolled out Turing after the legendary British computer scientist Alan Turing.
The biggest selling point of the chips is an improvement in “ray tracing,” or the ability for the chip to simulate how light rays will bounce around in a visual scene.
That task takes so much computing power that designers have to wait while a chip churns through the data to see the results of their work. Nvidia says the new generation of chips will let designers make those changes in real time, which could speed up the creative process – and which Nvidia hopes customers will pay a premium for.
“Turing is Nvidia’s most important innovation in computer graphics in more than a decade,” Jensen Huang, founder and CEO of Nvidia, said in a statement.
The Santa Clara, California-based company’s shares have risen more than 50 percent over the past year, backed by data center chip sales that more than doubled to $1.9 billion its last fiscal year. Nvidia’s data center chips power AI tasks training computers to recognize images and are increasingly eating away Intel’s growth opportunities.
Nvidia’s biggest business, its consumer chips that let video gamers play with improved graphics, grew 35 percent to $5.5 billion in its most recent fiscal year. That growth came from hot gaming titles such Epic Games’ Fortnite and the fact that the chips were adopted by homespun cryptocurrency enthusiasts, Reuters reported.
But Nvidia’s middle line of chips, aimed at graphics and design professionals who make films and other digital content, has not fared nearly as well, growing only 11.8 percent last year to $934 million.
AMD is likely to target the same group of professional users with its new graphics chips next year. Nvidia’s existing strength in the data center market and the high-end gaming market have left it most open to attack in the middle of the market.
NVIDIA CEO Jensen Huang at the annual SIGGRAPH conference also launched NVIDIA Quadro RTX 8000, Quadro RTX 6000 and Quadro RTX 5000 GPUs bring hardware-accelerated ray tracing, AI, advanced shading and simulation to creative professionals.
According to NVIDIA, the new Quadro RTX GPUs will be available worldwide starting in October 2018.
Bob Pette, vice president, Professional Visualization, NVIDIA, said: “With up to 48GB capacity, our GPUs accommodate the largest models and scenes, and increase application performance, enabling professionals to design, develop and deliver much better results with faster turnaround.”
Samsung is leading the graphics market by offering the first available 16Gb GDDR6, which doubles the device capacity of the company’s 20-nanometer 8Gb GDDR5 memory. The new solution performs at a 14 Gbps pin speed with data transfers of 56 gigabytes per second (GB/s), which represents a 75 percent increase over 8Gb GDDR5 with its 8Gbps pin speed.
Samsung’s GDDR6 consumes 35 percent less power than that required by GDDR5 graphics solutions. Samsung 16Gb GDDR6 operates at 1.35V compared to the 1.55V consumed by GDDR5 commonly found in the market today.