Re: autovectorize page checksum code included elsewhere - Mailing list pgsql-hackers

From Andres Freund
Subject Re: autovectorize page checksum code included elsewhere
Date
Msg-id 20231128005125.hvq4jxz7gu6u5anc@awork3.anarazel.de
Whole thread Raw
In response to Re: autovectorize page checksum code included elsewhere  (John Naylor <johncnaylorls@gmail.com>)
Responses Re: autovectorize page checksum code included elsewhere
List pgsql-hackers
Hi,

On 2023-11-25 14:09:14 +0700, John Naylor wrote:
> * Note: I have seen the threads with the idea of compiling multiple
> entire binaries, and switching at postmaster start. I think it's a
> good idea, but I also suspect detecting flags from the packager is an
> easier intermediate step.

It's certainly an easier incremental step - but will it get us all that far?
Other architectures have similar issues, e.g. ARM with ARMv8.1-A having much
more scalable atomic instructions than plain ARMv8.0. And even on x86-64,
relying on distros to roll out new minimum x86_64-v2 doesn't get us that far -
we'd be up to a uarch from ~2010. And I doubt that they'll raise the bar to v4
in the next few years, so we'll leave years of improvements on the table. And
even PG specific repos can't just roll out a hard requirement for a new, more
modern, uarch that will crash some time after startup on some hardware.

Greetings,

Andres Freund



pgsql-hackers by date:

Previous
From: "Tristan Partin"
Date:
Subject: Re: SSL tests fail on OpenSSL v3.2.0
Next
From: Peter Smith
Date:
Subject: Re: GUC names in messages