So they’re basically making a 4080 Ti using the AD102 die for China by fusing off an additional 28 SMs.

Arc is no threat whatsoever to Nvidia, not unless Intel manage to scale up the architecture to enterprise-grade levels and develop something akin to the CUDA API.

GN needs to start testing CPU performance on each cooler due to how Zen 4 and the 13/14th gen utilise thermal boost algorithms to run near their tJmax.

My 7950X3D runs at ~88c on both my 360mm AIO and the D15S that I currently have on it, but it does not maintain the same clock speeds on both coolers. It runs at 100-200Mhz higher on the AIO. Both can easily handle the wattage of the 7950X3D, but the better cooler still allows it to run slightly faster.

Slap a low end air cooler on a 7950X3D and it will still run at ~88c, but the clock speeds will probably be more like 4Ghz than 5Ghz+ like they will be on a high end cooler.

The Xeon Max CPUs contain 64GB of HBM2e, which can be configured to act as a cache. You could run a lot of games entirely on the HBM!

AMD really did have a golden era from 2008-2013. Somehow they managed to blow it.

I went from a 6700k to a 12900k. I’ll probably get Zen 5 3D or the i9 15th gen next year.

It isn’t a major architecture update. Nvidia’s slides from Ampere’s release stated that the next two architectures after Ampere would be part of the same family.

Performance gains will be had by improving the RT & tensor cores, using an improved node, probably N4X, to facilitate clock speed increases at the same voltages, and by increasing the number of SMs across the product stack. The maturity of the 5nm process will allow Nvidia to use larger die than they could in Ada.