From: Tom Lane <tgl@sss.pgh.pa.us>
To: Nathan Bossart <nathandbossart@gmail.com>
cc: Jeff Davis <pgsql@j-davis.com>, pgsql-hackers@postgresql.org,
        Xiang.Gao@arm.com
Subject: Re: always use runtime checks for CRC-32C instructions
In-reply-to: <2613682.1698779776@sss.pgh.pa.us>
References: <20231030161706.GA3011@nathanxps13> <2427946.1698683963@sss.pgh.pa.us> <c1e9436426cb0368c6664130c3e89b8923bc449d.camel@j-davis.com> <20231031033601.GA68409@nathanxps13> <20231031155518.GA70172@nathanxps13> <2613682.1698779776@sss.pgh.pa.us>
Comments: In-reply-to Tom Lane <tgl@sss.pgh.pa.us>
	message dated "Tue, 31 Oct 2023 15:16:16 -0400"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <2617041.1698781353.1@sss.pgh.pa.us>
Content-Transfer-Encoding: quoted-printable
Date: Tue, 31 Oct 2023 15:42:33 -0400
Message-ID: <2617042.1698781353@sss.pgh.pa.us>
Archived-At: <https://www.postgresql.org/message-id/2617042.1698781353%40sss.pgh.pa.us>
Precedence: bulk

I wrote:
> I did a more thorough scrape of the buildfarm results.  Of 161 animals
> currently reporting configure output on HEAD, we have

Oh ... take "current" with a grain of salt there, because I just noticed
that I typo'd my search condition so that it collected results from all
systems that reported since 2022-Oct, rather than in the last month as
I'd intended.  There are just 137 animals currently reporting.

Of those, I broke down the architectures reporting using slicing-by-8:

# select arch,count(*) from results where crc =3D 'slicing-by-8' group by =
1 order by 1;
        arch        | count =

--------------------+-------
 aarch64            |     1
 macppc             |     1
 mips64eb; -mabi=3D64 |     1
 mips64el; -mabi=3D32 |     1
 ppc64 (power7)     |     4
 ppc64 (power8)     |     2
 ppc64le            |     7
 ppc64le (power8)   |     1
 ppc64le (power9)   |    15
 riscv64            |     2
 s390x (z15)        |    14
 sparc              |     1
(12 rows)

The one machine using slicing-by-8 where there might be a better
alternative is arowana, which is CentOS 7 with a pretty ancient gcc
version.  So I reject the idea that slicing-by-8 is an appropriate
baseline for comparisons.  There isn't anybody who will see an
improvement over current behavior: in the population of interest,
just about all platforms are using CRC instructions with or without
a runtime check.

			regards, tom lane