NVIDIA’s latest workstation is a beast equipped with four A100 GPUs of 80GB each

NVIDIA has revealed its latest workstation for professionals. An impressive golden obelisk that contains enough power inside to be used in serious machine learning and artificial intelligence work in general. The DGX Station A100Among other things, it brings a total of 320 GB of GPU memory.

Waste of power encapsulated in a gold box

The new DGX is a workstation that part of A100 GPUs what NVIDIA introduced in May of this year. As we saw at the time, they were not designed for the average consumer, but for a professional environment. The new DGX A100s are just that, a professional rig that comes equipped with up to four A100 GPUs.

Inside the box are a number of other components that are worth highlighting alongside the GPUs. For example, we find a 64-core AMD CPU with 512GB memory. As for storage, it comes equipped with 7.68 TB NVME SSDs. We also find PCIe Gen-4 support and a DGX display adapter with four DisplayPort outputs and support for 4K resolutions.

Nvidia A100 Sxm4 80gbNvidia A100 Sxm4 80gb

The most interesting of all is that it does not require a special power or cooling equipment. According to NVIDIa, just plug it into the home socket like a normal computer.

Going back a bit to the GPU of this DGX A100, it uses third-generation tensioning cores, along with third-generation NVLink and NVSwith technology. That doubles the bandwidth from GPU to GPU, for transfers of up to 600GB per second. NVIDIA indicates that it is the only workgroup that supports NVIDIA Multi-Instance GPU (MIG) technology. With it the DGX A100 can offer up to 28 separate GPU instances to work in parallel with different users or different tasks.


NVIDIA declined to say how much one of these workstations cost. However, we can be clear that the figure is certainly high. Just to put things in context each of the A100 GPUs are priced at $ 200,000.

Via | Engadget
More information | NVIDIA

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.