Nvidia launches RTX A400/A1000, bringing Tensor Core and RT Core to desktop low-end professional cards for the first time

According to news from this site on April 17, Nvidia recently added two entry-level products of the Ampere architecture to its professional visualization GPUs for workstations: RTX A400 and RTX A1000. For the first time, Tensor Core and RT Core are introduced into low-end professional desktops. Graphics card product line.

These two graphics cards have a rated TDP power consumption of 50W, adopt active cooling, half-height and half-length HHHL specifications, are based on the GA107 core of Samsung's 8nm process, and are equipped with 4 Mini DP 1.4a interfaces.

The RTX A400 and RTX A1000 are designed to replace the T1000 and T400 launched in 2021. The latter two and the T600 are NVIDIA's last three professional visualization GPU products that are not included in the NVIDIA RTX naming system.

Nvidia said that the RTX A1000 can provide more than 3 times the generative AI processing speed compared to the previous generation product. At the same time, its RT Core also significantly accelerates the process of CAD, video editing and other applications.

This site organizes the GPU parameters of these two graphics cards as follows:

## A1000A400CUDA Quantity23047683rd Number of Generation Tensor Cores7224 Number of Generation 2 RT Cores186 Acceleration frequency (MHz)14601755Video memory type12Gbps GDDR612Gbps GDDR6Video memory specifications128bit 8GB64bit 4GBNumber of NVDEC decoders21##Number of NVENC encodersThe RTX A1000 GPU is currently available through NVIDIA's global distribution partners; the RTX A400 will be available later and is expected to be available from channel partners starting in May and from manufacturers starting in the summer.

1	1

The above is the detailed content of Nvidia launches RTX A400/A1000, bringing Tensor Core and RT Core to desktop low-end professional cards for the first time. For more information, please follow other related articles on the PHP Chinese website!