Nvidia unveils RTX A6000 and RTX A40 – Ampere retires Quadro

Nvidia’s rollout of the Ampere graphics architecture continues unabated, with the premiere of the DGX A100 data center product followed by consumer cards in the Geforce RTX 3000 series. Now the next step in the rollout is unveiled in the form of RTX A6000 and RTX A40, which according to Nvidia cover the product spectrum between workstations and data centers.

Both graphics cards are equipped with the Ampere architecture and the full capacity of the GA102 graphics circuit. This means 84 calculation units (SM) and 10,752 CUDA cores. The same amount of graphics memory takes up space in both 48 GB GDDR6 cards with ECC support, but the cards differ in the current memory speed. The RTX A6000 offers a memory speed of 16,000 MHz, which gives a total bandwidth of 768 GB / s. The RTX A40 will instead have a memory speed of 14,500 MHz for a total bandwidth of 696 GB / s.

NV_A6000-3.jpg

Calculations related to ray tracing is also supported as the Ampere architecture’s second generation RT cores are also in place. The graphics cards can be linked via the third generation NVLink interface. Support for the virtual GPU (vGPU) technology makes it possible to convert the hardware into a virtual computing resource that can be used by remote users for acceleration of, for example, design, simulation and scientific calculations remotely.

Read This Now:   Price information for Intel Arc is spreading on the web - on a par with the Geforce RTX 3070

The RTX A40 is included in Nvidia’s data center graphics card and its three Displayport 1.4 ports are therefore disabled. As the RTX A6000 is designed for workstations and is to be used by creators, among others, it is equipped with as many as four Displayport 1.4, all of which are active. Both RTX A40 and RTX A6000 have a TDP level of 300 watts and occupy two card slots in the system.

With the DGX A100 for data centers and the RTX A40 / A6000 for workstations, it seems that Nvidia is retiring the Quadro product family, which means that the company has previously put the Tesla product family in the mothballs. Now the letter A is used instead to indicate that it is a graphics card with the architecture Ampere as the base plate. Price information for RTX A6000 and RTX A40 is missing at the time of writing.

Read more about Nvidia’s graphics card for data centers and companies:


Notice: ob_end_flush(): failed to send buffer of zlib output compression (1) in /home/gamefeve/bitcoinminershashrate.com/wp-includes/functions.php on line 5420

Notice: ob_end_flush(): failed to send buffer of zlib output compression (1) in /home/gamefeve/bitcoinminershashrate.com/wp-includes/functions.php on line 5420