On Mon, Jan 18, 2016 at 2:39 PM, Kevin Grittner <kgrittn@gmail.com> wrote:
>> but I don't think that Andreas' patch is necessarily a
>> performance patch. There can be value in removing superfluous
>> code; doing so sometimes clarifies intent and understanding.
>
> Well, that's why I said I would be satisfied with a neutral
> benchmark result -- when there is a tie, the shorter, simpler code
> should generally win. I'm not really sure what there was in what I
> said to argue about; since that I've just been trying figure that
> out. If we all agree, let's let it drop.
If we don't want to apply this, then I think that a sensible
compromise would be to add a code comment that says that we don't
believe the LOCK prefix matters.
--
Peter Geoghegan