My personal experience with GPU accelerated GUIs is that latency is always worse.

Drawing text is something that the cpu is pretty good at and the GPU just means more back and forth over the buss, more driver coupling, more weird libraries.

I think you're right about GPU tending to have worse latency, but I think it's because that's the way the swap chain is set up and the use of blocking present calls. I've been studying this and am pretty sure I know how to make low latency on Windows work, mostly it's following the advice in [1]. If you do it right, then on modern hardware, DirectFlip kicks in and that saves you an additional frame that would ordinarily be eaten by the compositor. I plan to measure this at some point in the not too distant future, or would be happy to mentor somebody interested in taking it on.

[1]: https://devblogs.microsoft.com/directx/dxgi-flip-model/

Matches user reports like https://stackoverflow.com/questions/42888024/git-bash-mintty...

That would be my concern. But there are so many factors, I'd like to see some scientific measurement.

AFAIK, GPUs are throughput devices, not latency-reducing devices.

Happy to be proven wrong!

iTerm is a GPU based terminal emulator now too, as long as the metal backend is active