Computer

This is the performance that the new AMD and NVIDIA graphics will have

For months we have been immersed in everything that has to do with the new AMD and NVIDIA graphics cards, of which we are learning day after day about their characteristics or performance. Despite the fact that almost a year ago the possible percentage yields on the current RTX 30 and RX 6000 of the two companies were leaked, those data were deleted and now they have been updated, where there are very interesting surprises and that ghosts are brought to light again From the past. Than performance they will have the new graphics from AMD and NVIDIA?

There are two parts to this news, the first as we say already old and that places the base, and the second that gives new information about what was leaked at the time. For this reason and given that a year is a long time, we are going to update the information and above all to put it in context, because since we have no other choice we will have to enter the field of speculation that we are so good at after seeing the successes .

The performance of the new AMD and NVIDIA graphics

What we saw at the time is that NVIDIA and its AD102 for its RTX 40 would mean a performance jump of more than double, specifically 2.2X, over what was the fastest GPU at the time and is still on sale, the RTX 3090. As for AMD, its jump would be even greater (2.5X) and it would be, if not at the height of its eternal rival, ahead and by the minimum.

— kopite7kimi (@kopite7kimi) April 29, 2022

Finally we had Hopper as architecture, which was supposed to be launched with a GH202 chip, something that in the end we have seen is not such and the GH100 with Hopper micro architecture has been in charge of said performance (3X).

How much truth is there in these statements? Well, since we have not seen anything about the performance, we cannot verify if the chips are so far above their predecessors as such, since we only know the specifications of one of them and it effectively points to a similar figure thanks to its 18,432 shaders in 144 SM. But there is more…

NVIDIA changes in Ada Lovelace

And it is that the leaker himself, despite launching the tweet again where he respecifies the same data alleging a war that we do not know who it would affect, now also determines that the AD102 he named is not the current AD102 that NVIDIA has already finished and what It’s not just an Ampere soda as reported at the time.

This means that, as expected, NVIDIA is going to introduce significant changes (especially in the performance of the RT Cores and Tensor Cores) that will improve the data offered at that time.

The conclusions that we can draw from this are simple: NVIDIA’s leap forward will be greater than that 2.2X and possibly end up being at the height of AMD’s leap (2.5X), so if this were the expected GAP the tables would turn They would continue with distances similar to those between the current RTX 30 and RX 6000.

If these speculations come true, the battle will be tough again, except that on this occasion and apparently there will be no price war because they will be high and the margin of movement will therefore be greater, especially considering that NVIDIA starts from a node that is exclusive: 4N, like the one used by the GH100. What we are sure of is that the performance of the new AMD and NVIDIA graphics will be not one, but two steps forward in a single generation.

Related Articles

Leave a Reply

Your email address will not be published.