Hi!
I know this is a weird question to ask at this time, I won't be able to get a definite answer, since we know next to nothing about the RTX 3080 Ti, but I was just wondering. I usually buy a new GPU every generation of the Ti class(currently on the 2080 Ti), but I don't replace my CPU nearly as often since games are mostly bottlenecked by the GPU, especially at 4K where I play. However I did replace my ageing 4770K(it wasn't bottlenecking my 1080 Ti that bad at 4K, but I don't know if that would have been the case with the 2080 Ti) last november to an i9 9900K,. I'm not planning to replace my 9900K for at least a couple of years (maybe I will when the RTX 4080 Ti comes out), but since AMDs latest motherboards already support PCI 4.0, and my Z390 doesn't. I expect the next generation of GPUs from Nvidia to be PCI 4.0 cards, and I'm a bit nervous that PCI 3.0 will become a bottleneck at the high-end. TechPowerUp did an analysis of this with the RTX 2080 Ti:
https://www.techpowerup.com/review/nvidia-geforce-rtx-2080-ti-pci-express-scaling/7.html
What they found was that PCIe 3.0 8x was in fact a bottleneck here, tough the difference wasn't huge (2-3%). Does that mean, that in order for PCIe 3.0 16x to become a bottleneck, the GPU needs to be twice as fast as an RTX 2080 Ti or it doesn't work that way?
Thank you for the help in advance!
I know this is a weird question to ask at this time, I won't be able to get a definite answer, since we know next to nothing about the RTX 3080 Ti, but I was just wondering. I usually buy a new GPU every generation of the Ti class(currently on the 2080 Ti), but I don't replace my CPU nearly as often since games are mostly bottlenecked by the GPU, especially at 4K where I play. However I did replace my ageing 4770K(it wasn't bottlenecking my 1080 Ti that bad at 4K, but I don't know if that would have been the case with the 2080 Ti) last november to an i9 9900K,. I'm not planning to replace my 9900K for at least a couple of years (maybe I will when the RTX 4080 Ti comes out), but since AMDs latest motherboards already support PCI 4.0, and my Z390 doesn't. I expect the next generation of GPUs from Nvidia to be PCI 4.0 cards, and I'm a bit nervous that PCI 3.0 will become a bottleneck at the high-end. TechPowerUp did an analysis of this with the RTX 2080 Ti:
https://www.techpowerup.com/review/nvidia-geforce-rtx-2080-ti-pci-express-scaling/7.html
What they found was that PCIe 3.0 8x was in fact a bottleneck here, tough the difference wasn't huge (2-3%). Does that mean, that in order for PCIe 3.0 16x to become a bottleneck, the GPU needs to be twice as fast as an RTX 2080 Ti or it doesn't work that way?
Thank you for the help in advance!