Re: Improving and extending int128.h to more of numeric.c

From: Dean Rasheed <dean(dot)a(dot)rasheed(at)gmail(dot)com>
To: John Naylor <johncnaylorls(at)gmail(dot)com>
Cc: Andres Freund <andres(at)anarazel(dot)de>, PostgreSQL Hackers <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: Improving and extending int128.h to more of numeric.c
Date: 2025-08-04 14:58:15
Message-ID: CAEZATCWjPZ6w_JZDZmDJPJhYKKJZx8ywxbZYbvSbtrtKyvN-qw@mail.gmail.com
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Fri, 18 Jul 2025 at 07:42, John Naylor <johncnaylorls(at)gmail(dot)com> wrote:
>
> While testing something else on s390x, I noticed that __int128 support
> is broken on that platform at least for some versions of clang [1],
> and I see improvement there with this patch:
>
> Query 1:
> HEAD: 3015ms
> Patch: 2206ms
>
> Query 2:
> HEAD: 3394ms
> Patch: 2514ms

Thanks for testing.

On Fri, 18 Jul 2025 at 07:47, John Naylor <johncnaylorls(at)gmail(dot)com> wrote:
>
> On Thu, Jul 17, 2025 at 2:30 PM Dean Rasheed <dean(dot)a(dot)rasheed(at)gmail(dot)com> wrote:
> >
> > BTW, my other motivation for doing this was to simplify the numeric
> > code. Even if this had zero performance benefit, as long as it didn't
> > make things any slower, I would argue that it's worth doing.
>
> I gathered that was the main motivation, and I agree. I looked over
> 0005 and don't see any issues.

Thanks for reviewing. If there are no objections, I'll push this
shortly (though I'll change INT64_HEX_FORMAT to PRIx64, since it looks
like the former is about to go away).

Regards,
Dean

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Fujii Masao 2025-08-04 15:18:16 Re: Bug in pg_dump --filter? - Invalid object types can be misinterpreted as valid
Previous Message Thomas Munro 2025-08-04 14:53:18 Re: [PATCH] OAuth: fix performance bug with stuck multiplexer events