Thugnificient
Banned
Source
Multiple outlets are reporting on it. If true, this one at least gives credence to the fact AMD has something great in the pipeline.
Of course, this wouldn’t affect performance dramatically but this might allow for a 3080 Ti with higher clocks and a slightly lower core count than a 3090. It would likely outperform it, draw significantly less power and with the cut down VRAM, still be cheaper.
Otherwise, this could simply mean Hopper will be with TSMC (which is more likely than a shift mid-generation since you can't exactly copy-paste an architecture onto a different node on the fly.)
Multiple outlets are reporting on it. If true, this one at least gives credence to the fact AMD has something great in the pipeline.
Of course, this wouldn’t affect performance dramatically but this might allow for a 3080 Ti with higher clocks and a slightly lower core count than a 3090. It would likely outperform it, draw significantly less power and with the cut down VRAM, still be cheaper.
It has also been reported that NVIDIA’s previous annual masterpiece RTX 30 series uses Samsung Electronics’ 8nm process at a considerable OEM discount, but will switch to TSMC’s 7nm process in 2021. The order volume is not less. The reason for NVIDIA's transfer of orders is that TSMC's 7nm offer is relatively close to the people, and the other is that it has previously planned to diversify risks to deal with Samsung's 8nm yield problem. The NVIDIA 7nm large order is also one of TSMC's important customers to maintain high-end 7nm capacity utilization in 2021.
Otherwise, this could simply mean Hopper will be with TSMC (which is more likely than a shift mid-generation since you can't exactly copy-paste an architecture onto a different node on the fly.)
Last edited: