Re: always use runtime checks for CRC-32C instructions

From: Nathan Bossart <nathandbossart(at)gmail(dot)com>
To: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>
Cc: Jeff Davis <pgsql(at)j-davis(dot)com>, pgsql-hackers(at)postgresql(dot)org, Xiang(dot)Gao(at)arm(dot)com
Subject: Re: always use runtime checks for CRC-32C instructions
Date: 2023-10-31 19:57:43
Message-ID: 20231031195743.GB77436@nathanxps13
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Tue, Oct 31, 2023 at 03:42:33PM -0400, Tom Lane wrote:
> 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.

I only included the slicing-by-8 benchmark to demonstrate that 1) the CRC
computations are a big portion of that pg_waldump -z command and that 2)
the CRC instructions provide significant performance gains.

--
Nathan Bossart
Amazon Web Services: https://aws.amazon.com

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message Tristan Partin 2023-10-31 20:02:36 Use thread-safe locale APIs
Previous Message Nathan Bossart 2023-10-31 19:53:31 Re: always use runtime checks for CRC-32C instructions