I realize that Netkas & I have not been as present as we were in the past and that there was a vacuum for a knowledgeable poster, but posting nonsense isn't going to help anyone.
Specifically:https://egpu.io/performance-internal-vs-external-display/I’m sure you’re asking why the numbers from the Mac Pro internal 16x PCIe 2.0 slot are lower than External Display eGPU. Well, Apple crippled non-Mac GPUs to only be able to run at 2.5 Gbps lane speed. This gimpy connection effectively makes the graphics card run at 16x PCIe 1.1, which is close to 4x PCIe 3.0.
The above statement is complete and utter garbage. For quite some time the Nvidia Web Driver has enabled PCIE 2.0 in Mac Pro. This can be verified in about 4-5 seconds by firing up CUDA-Z. (Maybe the spread of "alternative facts"?)
Here are real
PCIE 2.0 facts on cMP with Nvidia cards:
Mac Pro 1,1 and 2,1 ALWAYS PCIE 1.0 in OS X and Windows.
Mac Pro 3,1 last I checked Nvidia Web Drivers didn't enable PCIE 2.0, so only our flashed cards enabled in OS X and Windows.
Mac Pro 4,1 and 5,1 for last couple years Web Drivers enabled PCIE 2.0 in OS X. Our flashed cards enabled in OS X and Windows.
For AMD cards there is a resistor that has to move, or be removed or be added for any given card. PCIE 2.0 only works once this is done.
Point here is, anyone is free to becomes new "source of knowledge" but paying attention to details is kind of important, best to be right, not just loud.