Re: [PATCH] Add busy loop polling for idle SMT

From: Peter Zijlstra
Date: Fri Nov 19 2021 - 04:26:10 EST


On Fri, Nov 19, 2021 at 11:19:03AM +0800, Peng Wang wrote:
>
> Yes, idle SMT busy loop polling can only provide approximately pipeline
> interference for normal instructions.
>
> When it comes to AVX works, we notice an idea modifing CPU time
> accounting[1], do you think the combination can lead to a feasible
> solution, or any other better ideas?

I'm not at all interested in solving this business model induced brain
trauma.