On 2017-09-06 16:36, Tom Lane wrote:
> Sokolov Yura <funny.falcon@postgrespro.ru> writes:
>> On 2017-09-06 15:56, Tom Lane wrote:
>>> The point I'm trying to make is that if tweaking generic.h improves
>>> performance then it's an indicator of missed cases in the
>>> less-generic
>>> atomics code, and the latter is where our attention should be
>>> focused.
>>> I think basically all of the improvement Sokolov got was from
>>> upgrading
>>> the coverage of generic-gcc.h.
>
>> Not exactly. I've checked, that new version of generic
>> pg_atomic_fetch_or_u32
>> loop also gives improvement.
>
> But once you put in the generic-gcc version, that's not reached
> anymore.
>
Yes, you're right.
But I think, generic version still should be "fixed".
If generic version is not reached on any platform, then why it is kept?
If it is reached somewhere, then it should be improved.
--
Sokolov Yura aka funny_falcon
Postgres Professional: https://postgrespro.ru
The Russian Postgres Company