Nvidia Expands RTX Studio GPUs With New Ampere Playing cards

At its virtual GPU technology conference in 2021, Nvidia introduced its next generation GPUs to developers. The new graphics cards are part of the RTX Studio product range and are aimed at developers on laptops, workstations and desktops. A total of eight new GPUs based on the Ampere graphics architecture of the gaming GeForce RTX 3000 series have been announced.

On the desktop, Nvidia expanded its creative portfolio with the introduction of the Nvidia RTX A5000 and RTX A4000 cards. The company stated that the cards include new RT Cores, Tensor Cores, and CUDA Cores that are optimized for A.I., graphics, and real-time rendering. Thanks to the new architecture, these new cards are up to twice as fast as offers from the previous generation.

This includes second generation RT cores delivering up to twice the throughput of the previous generation to perform simultaneous ray tracing, shading and labeling tasks together with third generation tensor cores and CUDA cores. The CUDA cores offer up to 2.5 times the FP32 performance compared to previous generations.

The desktop GPUs come with up to 24GB of video memory, and all cards come with GDDR6 RAM. The RTX A4000 ships with 16 GB of memory, twice as much as the previous generation, while the RTX A5000 ships with 24 GB of GDDR6 memory. However, with Nvidia NVLink you can double this to connect two GPUs. All desktop cards support PCIe Gen 4, which offers twice the bandwidth of the previous generation. This is important for data-intensive tasks that are important for working in A.I., 3D modeling, and data analysis.

"Speed ​​is everything when we have to evaluate new concepts for the most adventurous vehicles, and the NVIDIA RTX A5000 really delivers what we need," said CGI boss Erick Green of Polaris, a manufacturer of motorcycles and off-road vehicles. "The basic rendering of viewports in Octane Render is incredibly fast – 5x faster – and unlocks things we couldn't have tried before."

The RTX 5000 desktop card has 28.3 billion transistors on a Samsung 8N node. It has 64 RT cores, 256 tensor cores and 8,192 CUDA cores. The RT performance of this card is measured at 54.2 TFLOPs, according to Nvidia. The maximum power consumption is 230W. The RTX 4000 supports 17.4 billion transistors and has 48 RT cores, 192 tensor cores and 6,144 CUDA cores on the same 8N node. The maximum power consumption is 140W.

RTX Studio laptops

Nvidia presented its mobile graphics cards from the RTX A2000, RTX A3000, RTX A4000 and RTX A5000 series on laptops. RTX Studio Lap (According to Nvidia, the tops will also feature the latest Max-Q designs combined with the latest RTX graphics technologies. The laptops support the third Max-Q technology, so the systems are thin and light, Dynamic Boost 2.0 -, WhisperMode 2.0 and Resizable Bar technologies. The laptops support up to 16 GB of video memory.

The RTX A5000 laptop graphic comes with 6,144 CUDA cores, 192 tensor cores and 48 RT cores. The power consumption specified by Nvidia for this card is between 80 and 165 W. The card has 16 GB of GDDR6 memory and an RT core performance of 75.6 TFLOPs.

The mobile RTX A4000 GPU has 5,120 CUDA cores, 160 tensor cores and 40 RT cores. The mobile RTX A3000 GPU supports 4,096 CUDA cores, 128 tensor cores and 32 RT cores (ray tracing). The mobile RTX A2000 GPU supports 2,560 CUDA cores, 80 tensor cores and 20 RT cores. The entry card has a maximum power consumption between 35 and 95 W.

In addition, Nvidia announced updates to the Turing architecture that preceded the current generation of Amps. New Nvidia T1200 and T600 laptops based on Turing were also presented.

In data centers, Nvidia announced its new GPUs Nvidia A10 and A16. “The A10 offers designers and engineers up to 2.5 times the performance of previous generation virtual workstations, while the A16 GPU offers up to 2 times the user density at a lower total cost of ownership and an improved virtual desktop infrastructure over the previous generation. “Company claims.

The latest RTX desktop and data center GPUs from Nvidia will be available from partners later this month, while the RTX Studio laptops will be available worldwide in the second quarter of the year.

Editor's recommendations




Leave a Reply

Your email address will not be published. Required fields are marked *