From: David Laight <David.Laight@ACULAB.COM>
To: 'Stephen Rothwell' <sfr@canb.auug.org.au>,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jiri Slaby <jirislaby@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
"Matthew Wilcox (Oracle)" <willy@infradead.org>,
Christoph Hellwig <hch@infradead.org>,
"Jason A. Donenfeld" <Jason@zx2c4.com>
Subject: RE: [PATCH next v4 0/5] minmax: Relax type checks in min() and max().
Date: Wed, 10 Jan 2024 09:03:30 +0000 [thread overview]
Message-ID: <ddd07dbe318d451db6897b277e37410f@AcuMS.aculab.com> (raw)
In-Reply-To: <20240110171739.2e2d9de0@canb.auug.org.au>
From: Stephen Rothwell
> Sent: 10 January 2024 06:18
>
> Hi Linus,
>
> On Mon, 8 Jan 2024 13:11:12 -0800 Linus Torvalds <torvalds@linux-foundationorg> wrote:
> >
> > Whee.
>
> Yeah.
>
> > On my machine, that patch makes an "allmodconfig" build go from
> >
> > 10:41 elapsed
> >
> > to
> >
> > 8:46 elapsed
> >
> > so that min/max type checking is almost 20% of the build time.
> >
> > Yeah, I think we need to get rid of it.
> >
> > Can somebody else confirm similar time differences? Or is it just me?
>
> I was hopeful, but:
>
> no patch:
>
> $ /usr/bin/time make ARCH=x86_64 CROSS_COMPILE=x86_64-linux-gnu- -j140 -O -s
> 102460.07user 3710.56system 13:29.05elapsed 13122%CPU (0avgtext+0avgdata 4023168maxresident)k
> 304inputs+7917056outputs (1998673major+120730959minor)pagefaults 0swaps
>
> with patch:
>
> $ /usr/bin/time make ARCH=x86_64 CROSS_COMPILE=x86_64-linux-gnu- -j140 -O -s
> 99775.75user 3684.45system 13:12.89elapsed 13048%CPU (0avgtext+0avgdata 2217536maxresident)k
> 64inputs+7890304outputs (2104371major+119837267minor)pagefaults 0swaps
That looks like 2500 in 100000 (user) or about 2.5%
I did some rebuilds just changing minmax.h and got just over 1%
for changing __types_ok() to be 1.
I did try a few other things, got some marginal improvements.
But I'm not trying to compile the code with 4 nested calls.
One of the things that does explode it somewhat is the
'return constant for constant' path needed to avoid VLA.
That generates two copies of the expansion.
A separate define for that would help a bit.
Doesn't matter much until you get nested min/max they will hurt.
The other slight annoyance is an extra __builtin_choose_expr()
needed for pointer types - because (void *)1 isn't constant.
min3() was mentioned, but that seems to be a nested expansion.
It would need to be more like clamp() to get any benefit.
(And maybe removing the const-for-const option.)
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
next prev parent reply other threads:[~2024-01-10 9:03 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-18 8:14 David Laight
2023-09-18 8:16 ` [PATCH next v4 1/5] minmax: Add umin(a, b) and umax(a, b) David Laight
2024-01-12 12:49 ` Dan Carpenter
2024-01-12 13:40 ` David Laight
2024-01-12 14:03 ` Dan Carpenter
2024-01-12 14:26 ` David Laight
2024-01-18 10:30 ` Dan Carpenter
2023-09-18 8:17 ` [PATCH next v4 2/5] minmax: Allow min()/max()/clamp() if the arguments have the same signedness David Laight
2023-09-18 8:17 ` [PATCH next v4 3/5] minmax: Fix indentation of __cmp_once() and __clamp_once() David Laight
2023-09-18 8:18 ` [PATCH next v4 4/5] minmax: Allow comparisons of 'int' against 'unsigned char/short' David Laight
2023-09-18 8:19 ` [PATCH next v4 5/5] minmax: Relax check to allow comparison between unsigned arguments and signed constants David Laight
2023-09-27 17:30 ` [PATCH next v4 0/5] minmax: Relax type checks in min() and max() Andrew Morton
2023-09-28 8:10 ` David Laight
2024-01-08 11:46 ` Jiri Slaby
2024-01-08 13:34 ` David Laight
2024-01-08 18:19 ` Linus Torvalds
2024-01-08 20:04 ` Linus Torvalds
2024-01-08 21:11 ` Linus Torvalds
2024-01-09 0:39 ` [PATCH next v4 0/5] minmax: Relax type checks in min() and max().^[[C John Stoffel
2024-01-09 6:54 ` [PATCH next v4 0/5] minmax: Relax type checks in min() and max() Jiri Slaby
2024-01-10 6:17 ` Stephen Rothwell
2024-01-10 9:03 ` David Laight [this message]
2024-01-10 19:35 ` Linus Torvalds
2024-01-10 22:58 ` David Laight
2024-01-20 21:33 ` Linus Torvalds
2024-01-21 22:18 ` David Laight
2024-01-09 9:35 ` David Laight
2024-01-09 9:41 ` David Laight
2024-01-09 12:09 ` Kalle Valo
2024-01-19 7:14 ` Jiri Slaby
2024-01-19 8:23 ` Hans Verkuil
2024-01-19 9:14 ` David Laight
2024-01-12 9:13 ` Dan Carpenter
2024-01-12 12:16 ` David Laight
2024-01-12 12:40 ` Dan Carpenter
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=ddd07dbe318d451db6897b277e37410f@AcuMS.aculab.com \
--to=david.laight@aculab.com \
--cc=Jason@zx2c4.com \
--cc=akpm@linux-foundation.org \
--cc=andriy.shevchenko@linux.intel.com \
--cc=hch@infradead.org \
--cc=jirislaby@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=sfr@canb.auug.org.au \
--cc=torvalds@linux-foundation.org \
--cc=willy@infradead.org \
/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
Powered by JetHome