From: Solar Designer <solar@openwall.com>
To: musl@lists.openwall.com
Subject: Re: crypt* files in crypt directory
Date: Wed, 8 Aug 2012 10:27:06 +0400 [thread overview]
Message-ID: <20120808062706.GA23135@openwall.com> (raw)
In-Reply-To: <20120808052844.GF27715@brightrain.aerifal.cx>
On Wed, Aug 08, 2012 at 01:28:44AM -0400, Rich Felker wrote:
> On Wed, Aug 08, 2012 at 08:42:35AM +0400, Solar Designer wrote:
> > I see that you did this - and I think you took it too far. The code
> > became twice slower on Pentium 3 when compiling with gcc 3.4.5 (approx.
> > 140 c/s down to 77 c/s). Adding -finline-functions
> > -fold-unroll-all-loops regains only a fraction of the speed (112 c/s);
> > less aggressive loop unrolling results in lower speeds.
>
> Can you compare with a more modern gcc?
I could and I might do that later, but to me the slowdown with gcc 3 is
enough reason not to make those changes in that specific way.
> > The impact on x86-64 is less. With Ubuntu 12.04's gcc 4.6.3 on FX-8120
> > I get 490 c/s for the original code, 450 c/s for your code without
> > inlining/unrolling, and somehow only 430 c/s with -finline-functions
> > -funroll-loops.
>
> Actually this is a lot closer to what I expected. I think you'll find
> similar results on 32-bit with gcc 4.6.3 too. The modern expectation
> is that manually unrolling loops will give worse performance than
> letting the compiler decide what to do. Certainly there are exceptions
> to the expected result, but on average, it's the right decision.
Per the numbers above, here the compiler's unroll is slower not only
than manual unroll, but also than non-unrolled code.
> Even if it's twice as slow, that should only be the cost of
> incrementing the (logarithmic) iteration count by one).
Yes, and I think this is significant.
> The size difference between the versions is roughly 50%
It doesn't have to be. There are 6 instances of BF_ENCRYPT in
BF_crypt(). I am only asking you to revert to their larger form the two
that are inside BF_body. The remaining 4 may remain as calls to a
function. Alternatively, all 6 may be function calls, but then the
function's BF_ENCRYPT should be a fully manually unrolled one. I am not
sure which of these options will be faster overall for typical settings
(we'd need to benchmark these at $2a$08).
> (7k vs 11.5k with -Os
> and roughly 9k vs 13.5k with -O3). Yes one can argue that the
> difference doesn't matter for one particular component they especially
> care about,
Exactly.
> but everyone cares about something different, and in the
> end the whole library ends up 50% larger if you follow that to its
> logical end.
Makes sense.
> I'd much rather stick with letting the compiler do the
> bloating-up for performance purposes if the user wants it, so that
> the choice is left to them.
Maybe you could support -DFAST_CRYPT or the like. It could enable
forced inlining and manual unrolls in crypt_blowfish.c.
Alexander
next prev parent reply other threads:[~2012-08-08 6:27 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-21 15:23 Łukasz Sowa
2012-07-21 17:11 ` Solar Designer
2012-07-21 20:17 ` Rich Felker
2012-07-22 16:23 ` Łukasz Sowa
2012-07-25 7:57 ` Rich Felker
2012-08-08 2:24 ` Rich Felker
2012-08-08 4:42 ` Solar Designer
2012-08-08 5:28 ` Rich Felker
2012-08-08 6:27 ` Solar Designer [this message]
2012-08-08 7:03 ` Daniel Cegiełka
2012-08-08 7:24 ` Solar Designer
2012-08-08 7:42 ` Daniel Cegiełka
2012-08-08 21:48 ` Rich Felker
2012-08-08 23:08 ` Isaac Dunham
2012-08-08 23:24 ` John Spencer
2012-08-09 1:03 ` Isaac Dunham
2012-08-09 3:16 ` Rich Felker
2012-08-09 3:36 ` Solar Designer
2012-08-09 7:13 ` orc
2012-08-09 7:28 ` Rich Felker
2012-08-09 7:29 ` Solar Designer
2012-08-09 10:53 ` Solar Designer
2012-08-09 11:58 ` Szabolcs Nagy
2012-08-09 16:43 ` Solar Designer
2012-08-09 17:30 ` Szabolcs Nagy
2012-08-09 18:22 ` Rich Felker
2012-08-09 23:21 ` Rich Felker
2012-08-10 17:04 ` Solar Designer
2012-08-10 18:06 ` Rich Felker
2012-08-09 21:46 ` crypt_blowfish integration, optimization Rich Felker
2012-08-09 22:21 ` Solar Designer
2012-08-09 22:32 ` Rich Felker
2012-08-10 17:18 ` Solar Designer
2012-08-10 18:08 ` Rich Felker
2012-08-10 22:52 ` Solar Designer
2012-08-08 7:52 ` crypt* files in crypt directory Szabolcs Nagy
2012-08-08 13:06 ` Rich Felker
2012-08-08 14:30 ` orc
2012-08-08 14:53 ` Szabolcs Nagy
2012-08-08 15:05 ` orc
2012-08-08 18:10 ` Rich Felker
2012-08-09 1:51 ` Solar Designer
2012-08-09 3:25 ` Rich Felker
2012-08-09 4:04 ` Solar Designer
2012-08-09 5:48 ` Rich Felker
2012-08-09 15:52 ` Solar Designer
2012-08-09 17:59 ` Rich Felker
2012-08-09 21:17 ` Rich Felker
2012-08-09 21:44 ` Solar Designer
2012-08-09 22:08 ` Rich Felker
2012-08-09 23:33 ` Rich Felker
2012-08-09 6:03 ` Rich Felker
-- strict thread matches above, loose matches on Subject: below --
2012-07-17 9:40 Daniel Cegiełka
2012-07-17 17:51 ` Rich Felker
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=20120808062706.GA23135@openwall.com \
--to=solar@openwall.com \
--cc=musl@lists.openwall.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.
Code repositories for project(s) associated with this public inbox
https://git.vuxu.org/mirror/musl/
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).