| From: | John Naylor <johncnaylorls(at)gmail(dot)com> |
|---|---|
| To: | Nathan Bossart <nathandbossart(at)gmail(dot)com> |
| Cc: | Ants Aasma <ants(at)cybertec(dot)at>, pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: autovectorize page checksum code included elsewhere |
| Date: | 2023-11-25 07:24:11 |
| Message-ID: | CANWCAZYb3zydUR2iaZZHipH2mhH7yMFjwGWsQxt6GG2wbkTLfg@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Thu, Nov 23, 2023 at 1:49 AM Nathan Bossart <nathandbossart(at)gmail(dot)com> wrote:
>
> On Wed, Nov 22, 2023 at 02:54:13PM +0200, Ants Aasma wrote:
> > For reference, executing the page checksum 10M times on a AMD 3900X CPU:
> >
> > clang-14 -O2 4.292s (17.8 GiB/s)
> > clang-14 -O2 -msse4.1 2.859s (26.7 GiB/s)
> > clang-14 -O2 -msse4.1 -mavx2 1.378s (55.4 GiB/s)
>
> Nice. I've noticed similar improvements with AVX2 intrinsics in simd.h.
If you're thinking to support AVX2 anywhere, I'd start with checksum
first. Much less code to review, and less risk.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | jian he | 2023-11-25 08:28:32 | Re: pg_stats and range statistics |
| Previous Message | John Naylor | 2023-11-25 07:09:14 | Re: autovectorize page checksum code included elsewhere |