From: Linus Torvalds <torvalds@linux-foundation.org>
To: David Sterba <dsterba@suse.cz>,
Linus Torvalds <torvalds@linux-foundation.org>,
Nikolay Borisov <nborisov@suse.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Nick Desaulniers <ndesaulniers@google.com>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Dave Chinner <david@fromorbit.com>
Subject: Re: [PATCH] lib/string: Bring optimized memcmp from glibc
Date: Wed, 21 Jul 2021 13:27:56 -0700 [thread overview]
Message-ID: <CAHk-=whCygw44p30Pmf+Bt8=LVtmij3_XOxweEA3OQNruhMg+A@mail.gmail.com> (raw)
In-Reply-To: <20210721201029.GQ19710@twin.jikos.cz>
On Wed, Jul 21, 2021 at 1:13 PM David Sterba <dsterba@suse.cz> wrote:
>
> adding a memcmp_large that compares by native words or u64 could be
> the best option.
Yeah, we could just special-case that one place.
But see the patches I sent out - I think we can get the best of both worlds.
A small and simple memcmp() that is good enough and not the
_completely_ stupid thing we have now.
The second patch I sent out even gets the mutually aligned case right.
Of course, the glibc code also ended up unrolling things a bit, but
honestly, the way it did it was too disgusting for words.
And if it really turns out that the unrolling makes a big difference -
although I doubt it's meaningful with any modern core - I can add a
couple of lines to that simple patch I sent out to do that too.
Without getting the monster that is that glibc code.
Of course, my patch depends on the fact that "get_unaligned()" is
cheap on all CPU's that really matter, and that caches aren't
direct-mapped any more. The glibc code seems to be written for a world
where registers are cheap, unaligned accesses are prohibitively
expensive, and unrolling helps because L1 caches are direct-mapped and
you really want to do chunking to not get silly way conflicts.
If old-style Sparc or MIPS was our primary target, that would be one
thing. But it really isn't.
Linus
next prev parent reply other threads:[~2021-07-21 20:28 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-21 13:59 [PATCH] lib/string: Bring optimized memcmp from glibc Nikolay Borisov
2021-07-21 14:32 ` Christoph Hellwig
2021-07-21 14:35 ` Nikolay Borisov
2021-07-21 14:42 ` Christoph Hellwig
2021-07-21 14:51 ` Matthew Wilcox
2021-07-21 15:17 ` Peter.Enderborg
2021-07-21 15:34 ` Matthew Wilcox
2021-07-21 15:39 ` Peter.Enderborg
2021-07-21 18:00 ` Linus Torvalds
2021-07-21 18:17 ` Nikolay Borisov
2021-07-21 18:45 ` Linus Torvalds
2021-07-21 18:55 ` Linus Torvalds
2021-07-21 19:26 ` Linus Torvalds
2021-07-22 11:28 ` Nikolay Borisov
2021-07-22 16:40 ` Linus Torvalds
2021-07-22 17:03 ` Nikolay Borisov
2021-08-26 9:03 ` Nikolay Borisov
2021-07-22 8:28 ` Nikolay Borisov
2021-07-23 14:02 ` David Laight
2021-07-21 20:10 ` David Sterba
2021-07-21 20:27 ` Linus Torvalds [this message]
2021-07-22 5:54 ` Nikolay Borisov
2021-07-28 20:12 ` Florian Weimer
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAHk-=whCygw44p30Pmf+Bt8=LVtmij3_XOxweEA3OQNruhMg+A@mail.gmail.com' \
--to=torvalds@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=dsterba@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nborisov@suse.com \
--cc=ndesaulniers@google.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 NNTP newsgroup(s).