Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizen OC_Formula for the clue delivery! CTOnews.com Sept. 21 news, in addition to the game graphics card, Nvidia also launched a professional card based on Ada Lovelace architecture-RTX 6000 on GTC 2022.

Nvidia claims that the new RTX6000 can provide 2-4 times the performance improvement in the enterprise environment, and the major OEM will start shipping in December, with a full-card power of 300W, using the PCIe 4 × 16 interface, thus ushering in a new era of neurographics that combines AI and simulation.

The RTX6000 professional card can provide up to 2 times the light recovery performance of the previous generation products, up to 2 times the AI training performance of the previous generation products, and up to 2 times the single precision floating point performance of the previous generation products. Nvidia is equipped with 48GB ECC-enabled GDDR6 memory to support maximum volume 3D model rendering or AI computing.

"Neurographics is driving the next wave of innovation in computer graphics and will change the way content is created and experienced," said Bob Pette, vice president of professional visualization at NVIDIA. NVIDIA RTX 6000 is ready to power this new era of engineers, designers, and scientists to meet the demanding needs of content creation, rendering, artificial intelligence and simulated workloads needed to build a world in a virtual world. "

CTOnews.com learned that NVIDIA RTX 6000 uses the world's most advanced GPU architecture, NVIDIA Ada architecture, and the most advanced NVIDIA RTX technology. Features include:

The third-generation RT kernel: twice the throughput of the previous generation, and the ability to run ray tracing with shading or denoising capabilities at the same time.

The fourth generation Tensor core: AI training performance is 2 times faster than the previous generation, extending the support for FP8 data format.

CUDA kernel: compared with the previous generation, the single-precision floating-point throughput is up to 2x.

GPU memory: GDDR6 memory with 48GB for processing the largest 3D models, rendered images, simulations, and AI datasets.

Virtualization: NVIDIA Virtual GPU (vGPU) software for multiple high-performance virtual workstation instances will be supported, enabling remote users to share resources and drive high-end design, artificial intelligence, and computing workloads.

XR: with 3 times the previous generation video coding performance, multiple synchronous XR sessions can be streamed using NVIDIA CloudXR.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.