Messages in this thread | | | Date | Thu, 26 Feb 2015 07:50:49 -0500 | From | Steven Rostedt <> | Subject | Re: [PATCH 1/4] x86: entry.S: tidy up several suboptimal insns |
| |
On Thu, 26 Feb 2015 12:47:03 +0100 Ingo Molnar <mingo@kernel.org> wrote:
> The bona fide removal of a real instruction from a true hot > path is generally always worth doing, you don't even have > to 'prove' that it improves things: unless the claim is > that for some really robust reason the instruction was zero > cost to begin with.
I agree that removing instructions from hot paths are for the most part worth doing without any proof, as long as it doesn't change behavior or increase the memory footprint. But that's not the case here. If the change does affect behavior or increases memory footprint, then it should prove itself as worth doing.
-- Steve
| |