| From: | John Naylor <johncnaylorls(at)gmail(dot)com> |
|---|---|
| To: | Dean Rasheed <dean(dot)a(dot)rasheed(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: | 2025-07-16 09:02:46 |
| Message-ID: | CANWCAZZVkLP0jF3bWGOt-boikafgBkh0n4iWdXNP4OuVLP3gLw@mail.gmail.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Tue, Jul 15, 2025 at 4:07 AM Dean Rasheed <dean(dot)a(dot)rasheed(at)gmail(dot)com> wrote:
>
> I have reduced the number of iterations and changed it to use the
> current time for the PRNG seed. I don't see much value in logging the
> seed though, since we already log the inputs that cause any failure.
Ah, right.
On Mon, Jun 23, 2025 at 3:01 PM Dean Rasheed <dean(dot)a(dot)rasheed(at)gmail(dot)com> wrote:
> 0005 is the main patch. It adds a few more functions to int128.h and
> uses them in numeric.c to allow various functions (mainly aggregate
> functions) to use 128-bit integers unconditionally on all platforms.
> This applies to the following aggregates:
>
> - sum(int8)
> - avg(int8)
> - stddev_pop(int4)
> - stddev_samp(int4)
> - var_pop(int4)
> - var_samp(int4)
> Testing on a 32-bit system without native int128 support, I see
> something like a 1.3-1.5x speedup in a couple of simple queries using
> those aggregates.
With v5, I don't see any difference from master when building on x86
with -m32 for these queries:
select sum(i) from generate_series(1e10, 1e10+1e6, 1) i;
select var_pop(i) from generate_series(1e9, 1e9+1e6, 1) i;
Which queries were you testing?
(Also, unrelated to the patch set, but I was surprised to find
replacing the numeric expressions above with bigint ones
(10_000_000_000 etc) makes the queries at least 5 times slower, and
that's true with a normal 64-bit build as well.)
--
John Naylor
Amazon Web Services
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Peter Eisentraut | 2025-07-16 09:07:41 | Re: patch: Use pg_assume in jsonb_util.c to fix GCC 15 warnings |
| Previous Message | Tomas Vondra | 2025-07-16 08:40:29 | Re: index prefetching |