Re: Improve CRC32C performance on SSE4.2

From: Andy Fan <zhihuifan1213(at)163(dot)com>
To: "Devulapalli, Raghuveer" <raghuveer(dot)devulapalli(at)intel(dot)com>
Cc: Nathan Bossart <nathandbossart(at)gmail(dot)com>, John Naylor <johncnaylorls(at)gmail(dot)com>, Jesper Pedersen <jesperpedersen(dot)db(at)gmail(dot)com>, Tomas Vondra <tomas(at)vondra(dot)me>, "pgsql-hackers(at)lists(dot)postgresql(dot)org" <pgsql-hackers(at)lists(dot)postgresql(dot)org>, "Shankaran, Akash" <akash(dot)shankaran(at)intel(dot)com>
Subject: Re: Improve CRC32C performance on SSE4.2
Date: 2025-06-16 23:40:19
Message-ID: 87bjqncl24.fsf@163.com
Views: Whole Thread | Raw Message | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

"Devulapalli, Raghuveer" <raghuveer(dot)devulapalli(at)intel(dot)com> writes:

> Great catch! From the intrinsic manual:
>
> Cast vector of type __m128i to type __m512i; the upper 384 bits of the
> result are undefined.

Just be curious, what kind of optimization (like what -O2 does) could
mask this issue?

> Replacing that with _mm512_zextsi128_si512 fixes the problem.

congratulations!

--
Best Regards
Andy Fan

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Masahiko Sawada 2025-06-16 23:46:53 Re: Fix slot synchronization with two_phase decoding enabled
Previous Message Tom Lane 2025-06-16 23:09:17 Re: pg_dump --with-* options