The RX 7000 will be less powerful, AMD cuts its specifications

High demand for the 5nm wafers coming out of TSMC has caused AMD to cut back on its RX 7000 . Specifically in its specifications. The reason behind this is that they share space with NVIDIA and it is important to have enough units produced to be able to sell them later. How have the plans been affected compared to those you had a few months ago?

If a few hours ago we told you that the RX 7900 XT could reach 92 TFLOPS, now we have to contradict ourselves with this news. And it is that the latest information about the RX 7000, based on RDNA 3 architecture, points to significant cuts compared to what was initially planned by Lisa Su’s company regarding its next generation of graphics cards. Of course, it must be clarified that until now the information that had been appearing did not have a reliable authority. The reason? Easy, it does not come from AMD itself, but from the different information leakers.

The RX 7000 will be less powerful

Although the RX 7000 will receive cuts compared to what was initially planned, they will represent a significant leap compared to the current generation. Also, the two highest performance configurations will be the first two chiplet-based graphics cards. Going ahead of NVIDIA and Intel when launching a graphic disaggregated into several chips. Something inherited from their desktop Ryzen processors, but we have yet to see how it affects performance on desktop GPUs.

Changes in the configuration of future AMD RX 7000 graphics

First of all, we must bear in mind that months have passed since the specifications of the AMD RX 7000 based on its future RDNA 3 architecture were leaked. At the moment we do not have evidence of any graphics card that has been finished, so a much later release than the NVIDIA RTX 40 is expected.

Radeon RX 7000 recorte

What has been the surprise? Well, the fact that the different GPUs in the range, Navi 31, 32 and 33, have received a considerable cut. In what? Well, in the number of ALUs in FP32 within each of the shader units. Which means that:

  • The top of the range, Navi 31 , has gone from 15,360 FP32 ALUs in total to 12,288 . This figure means 48 WGP in the whole processor distributed in 12 Shader Arrays in 6 Shader Engine s.
  • As for the mid-range, Navi 32 , the cut has been from the 10,240 cores of the leaked specifications last year to 8,192 . Which translates to 32 WGPs in 8 Shader Arrays within 4 Shader Engines .
  • Already to end the low range, Navi 33 would have half the units than the previous case. Thus, 4,096 FP32 ALUs in 16 WGPs within 4 Shader Arrays which are contained within 2 Shader Engines.

This cut in the RX 7000 means that the RX 7900 XT has gone from being rated at 92 TFLOPS to 73 TFLOPS . This is if the 3 GHz speed is maintained and AMD decides not to make last-minute changes to the graphics processor, which is not yet finished. So we should expect changes in that aspect as well. Has AMD relinquished the throne to NVIDIA for the umpteenth time or may there still be any surprises?