unofficial mirror of libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: Florian Weimer <fweimer@redhat.com>
To: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>
Cc: Szabolcs Nagy <szabolcs.nagy@arm.com>,
	 Wilco Dijkstra <Wilco.Dijkstra@arm.com>,
	 'GNU C Library' <libc-alpha@sourceware.org>
Subject: Re: [PATCH] AArch64: Check kernel version for SVE ifuncs
Date: Thu, 14 Mar 2024 10:02:09 +0100	[thread overview]
Message-ID: <87cyrxnq3y.fsf@oldenburg.str.redhat.com> (raw)
In-Reply-To: <44aeef4b-1044-4be8-9f35-e592a1c26080@linaro.org> (Adhemerval Zanella Netto's message of "Wed, 13 Mar 2024 16:55:16 -0300")

* Adhemerval Zanella Netto:

> Yes, I understand this. My point it won't be possible to backport this 
> kernel fix to get the performance improvement of SVE routines without 
> hacking the glibc as well.  It is not really a blocker, but I would
> expect kernel to do proper advertise for such performance change that
> might interfere with ifunc selection. Maybe we can add a tunable to
> force SVE selection, but I don't have a strong opinion.

I think the kernel change went into the other direction: it eliminated
the SVE trap after system calls.

Thanks,
Florian


  parent reply	other threads:[~2024-03-14  9:02 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-03-13 14:31 [PATCH] AArch64: Check kernel version for SVE ifuncs Wilco Dijkstra
2024-03-13 18:12 ` Adhemerval Zanella Netto
2024-03-13 19:25   ` Szabolcs Nagy
2024-03-13 19:55     ` Adhemerval Zanella Netto
2024-03-14  8:35       ` Szabolcs Nagy
2024-03-14 13:47         ` Adhemerval Zanella Netto
2024-03-14 14:26           ` Szabolcs Nagy
2024-03-14 14:28             ` Adhemerval Zanella Netto
2024-03-14  9:02       ` Florian Weimer [this message]
2024-03-13 18:39 ` Szabolcs Nagy
2024-03-13 19:31 ` Andrew Pinski
2024-03-13 20:44   ` Wilco Dijkstra
2024-03-14  9:06 ` Florian Weimer
2024-03-14 14:42   ` Wilco Dijkstra
2024-03-14 14:55     ` Florian Weimer
2024-03-14 15:38       ` Wilco Dijkstra
2024-03-14 16:52         ` Florian Weimer
2024-03-18 11:46           ` Florian Weimer
2024-03-18 14:22             ` Wilco Dijkstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://www.gnu.org/software/libc/involved.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87cyrxnq3y.fsf@oldenburg.str.redhat.com \
    --to=fweimer@redhat.com \
    --cc=Wilco.Dijkstra@arm.com \
    --cc=adhemerval.zanella@linaro.org \
    --cc=libc-alpha@sourceware.org \
    --cc=szabolcs.nagy@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).