The death of thread per core

Context switches (when you change the thread running on a specific core) is one of the most computational expensive things computers do. If somehow you can't use a threadpool and some sort of task abstraction, you probably shouldn't be doing anything with multiple threads or asynchronous code.

I have absolutely no idea why anyone would think breaking the thread per core model is better and I seriously question the knowledge of anyone proposing another model without some VERY good explanation. The GP isn't even close to this in any way.

Changing task is some fraction as bad as changing thread because less state is changed, but some state is still changed. For example, if you run unrelated tasks, they all start with cold caches. It might not clear the IBPB, TLB etc for security because it doesn't go through the kernel, but if the task was completely unrelated, none of those caches were helping with the transition anyway. Usually, the task is related to some small degree.