NVIDIA Ampere Feature

Any links to online stores should be assumed to be affiliates. The company or PR agency provides all or most review samples. They have no control over my content, and I provide my honest opinion.

I am still reeling over the launch price of the original Nvidia RTX price, so it was surprising to remember that they were actually launched in Q3 2018. So there is a good chance we will see a new generation of Nvidia cards this year and a new leak claims to reveal some of the specs we will see.

The two new GPUs are codenamed GA103 and GA104 with these two designs likely to be the RTX 3080 and RTX 3070 respectively. There is also mention of a GA102 chip which could likely be the RTX 3080 Ti or Titan but no details were revealed about this.

Mydrivers.com states that both cards will use the 7nm fabrication process but they are unclear if this will be Samsung or TSMC.

The GA103 which we expect to be the RTX 3070 offering users 10 GB of VRAM over a 320-bit memory bus and up to 3480 CUDA cores. With this 320-bit memory bus, 20GB of VRAM could also be offered, but such a high allotment of VRAM would only be suitable for Nvidia’s Quadro series graphics cards. 

In comparison, the RTX 2080 Ti has 4,352 stream processors and the RTX 2080 Super has 3072 CUDA cores so this should sit nicely in the middle of the two cards,

The GA103 scales things down a little hence it is likely to be the RTX 3070. This is believed to have 3072 CUDA cores and 8/16 GB of memory over a 256-bit memory bus.

In the past Nvidia’s previous core names used even-numbered naming scheme which would make the GA103 a deviation from the norm.

The memory and CUDA cores are nice to know but they don’t directly reflect the true performance the new NVIDIA Ampere architecture offers, and it will likely be a while before we find out any information about this.

Similar Posts

Leave a Reply

Your email address will not be published.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