Re: better atomics - v0.6 - Mailing list pgsql-hackers

From Tom Lane
Subject Re: better atomics - v0.6
Date
Msg-id 18919.1411577049@sss.pgh.pa.us
Whole thread Raw
In response to Re: better atomics - v0.6  (Andres Freund <andres@2ndquadrant.com>)
Responses Re: better atomics - v0.6  (andres@anarazel.de (Andres Freund))
List pgsql-hackers
Andres Freund <andres@2ndquadrant.com> writes:
> On 2014-09-24 18:55:51 +0300, Heikki Linnakangas wrote:
>> There doesn't seem to be any hardware implementations of that in the patch.
>> Is there any architecture that has an instruction or compiler intrinsic for
>> that?

> You can implement it rather efficiently on ll/sc architectures. But I
> don't really think it matters. I prefer add_until (I've seen it named
> saturated add before as well) to live in the atomics code, rather than
> reimplement it in atomics employing code. I guess you see that
> differently?

I think the question is more like "what in the world happened to confining
ourselves to a small set of atomics".  I doubt either that this exists
natively anywhere, or that it's so useful that we should expect platforms
to have efficient implementations.
        regards, tom lane



pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: identify_locking_dependencies is broken for schema-only dumps
Next
From: Andrew Gierth
Date:
Subject: Re: Final Patch for GROUPING SETS