What would be interesting to me would be how quickly developers start targeting ARM64 directly.
https://docs.nvidia.com/dgx/dgx-spark-porting-guide/porting/...
One reason it works surprisingly well on modern systems is how much is offloaded to the GPU. You aren't going to get great power optimization or anything without it being truly native though.
There are games which are CPU limited though, and it will be interesting how those do. Curiously those also tend to be in engines with Arm support already.
When you lay out the software stack it is essentially OS > Game code > APIs. Both the OS and APIs are native code, it is only that middle point that needs the real work.
This is why x86 to ARM doesn't have such a heavy performance cost. So games can be CPU heavy but if it is heavy at the API end, that isnt a huge issue.
Very cool.