From: Janne Blomqvist <blomqvist.janne@gmail.com>
To: "Thomas König" <tk@tkoenig.net>
Cc: Thomas Koenig <tkoenig@netcologne.de>,
Tobias Burnus <tobias@codesourcery.com>,
"fortran@gcc.gnu.org" <fortran@gcc.gnu.org>,
gcc-patches <gcc-patches@gcc.gnu.org>
Subject: Re: [patch, fortran] Load scalar intent-in variables at the beginning of procedures
Date: Wed, 20 Nov 2019 22:19:00 -0000 [thread overview]
Message-ID: <CAO9iq9F6-F0nkuFRC+edsA7rN3OTKX20L2k87cwQARy1QHipjA@mail.gmail.com> (raw)
In-Reply-To: <4e68f250-1e41-ac7c-dc64-88f91cdf183e@tkoenig.net>
On Wed, Nov 20, 2019 at 11:35 PM Thomas König <tk@tkoenig.net> wrote:
>
> Am 20.11.19 um 21:45 schrieb Janne Blomqvist:
> > BTW, since this is done for the purpose of optimization, have you done
> > testing on some suitable benchmark suite such as polyhedron, whether
> > it a) generates any different code b) does it make it go faster?
>
> I haven't run any actual benchmarks.
>
> However, there is a simple example which shows its advantages.
> Consider
>
> subroutine foo(n,m)
> m = 0
> do 100 i=1,100
> call bar
> m = m + n
> 100 continue
> end
>
> (I used old-style DO loops just because :-)
>
> Without the optimization, the inner loop is translated to
>
> .L2:
> xorl %eax, %eax
> call bar_
> movl (%r12), %eax
> addl %eax, 0(%rbp)
> subl $1, %ebx
> jne .L2
>
> and with the optimization to
>
> .L2:
> xorl %eax, %eax
> call bar_
> addl %r12d, 0(%rbp)
> subl $1, %ebx
> jne .L2
>
> so the load of the address is missing. (Why do we zero %eax
> before each call? It should not be a variadic call right?)
Not sure. Maybe some belt and suspenders thing? I guess someone better
versed in ABI minutiae knows better. It's not Fortran-specific though,
the C frontend does the same when calling a void function.
AFAIK on reasonably current OoO CPU's xor'ing a register with itself
is handled by the renamer and doesn't consume an execute slot, so it's
in effect a zero-cycle instruction. Still bloats the code slightly,
though.
> Of course, Fortran language rules specify that the call to bar
> cannot do anything to n
Hmm, does it? What about the following modification to your testcase:
module nmod
integer :: n
end module nmod
subroutine foo(n,m)
m = 0
do 100 i=1,100
call bar
m = m + n
100 continue
end subroutine foo
subroutine bar()
use nmod
n = 0
end subroutine bar
program main
use nmod
implicit none
integer :: m
n = 1
m = 0
call foo(n, m)
print *, m
end program main
> So, a copy in / copy out for variables where we can not be sure that
> no value is assigned? Does anybody see a downside for that?)
In principle sounds good, unless my concerns above are real and affect
this case too.
> > Is there a risk of performance regressions due to higher register pressure?
>
> I don't think so. Either the compiler realizes that it can
> keep the variable in a register (then it makes no difference),
> or it has to load it fresh from its address (then there is
> one additional register needed).
Yes, true. Good point.
--
Janne Blomqvist
next prev parent reply other threads:[~2019-11-20 22:18 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-11 21:57 Thomas König
2019-11-11 22:08 ` Thomas Koenig
2019-11-11 22:53 ` Janne Blomqvist
2019-11-11 23:02 ` Thomas König
2019-11-12 7:48 ` Janne Blomqvist
2019-11-12 12:50 ` Thomas König
2019-11-12 14:33 ` Tobias Burnus
2019-11-12 17:22 ` Thomas König
2019-11-15 7:41 ` Tobias Burnus
2019-11-15 18:07 ` Thomas König
2019-11-16 20:42 ` Thomas Koenig
2019-11-19 10:46 ` Bernhard Reutner-Fischer
2019-11-19 23:04 ` Thomas Koenig
2019-11-20 18:00 ` Bernhard Reutner-Fischer
2019-11-20 20:45 ` Janne Blomqvist
2019-11-20 21:07 ` Steve Kargl
2019-11-20 21:35 ` Bernhard Reutner-Fischer
2019-11-20 20:46 ` Janne Blomqvist
2019-11-20 21:39 ` Thomas König
2019-11-20 22:19 ` Janne Blomqvist [this message]
2019-11-20 22:32 ` Janne Blomqvist
2019-11-21 9:35 ` Janne Blomqvist
2019-11-20 22:37 ` Tobias Burnus
2019-11-20 22:41 ` Thomas König
2019-11-20 22:30 ` Tobias Burnus
2019-11-21 9:41 ` Tobias Burnus
2019-11-21 12:30 ` Richard Biener
2019-11-21 13:17 ` Tobias Burnus
2019-11-21 13:37 ` Tobias Burnus
2019-11-21 14:10 ` Richard Biener
2019-11-21 14:39 ` Tobias Burnus
2019-11-22 10:44 ` Tobias Burnus
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=CAO9iq9F6-F0nkuFRC+edsA7rN3OTKX20L2k87cwQARy1QHipjA@mail.gmail.com \
--to=blomqvist.janne@gmail.com \
--cc=fortran@gcc.gnu.org \
--cc=gcc-patches@gcc.gnu.org \
--cc=tk@tkoenig.net \
--cc=tkoenig@netcologne.de \
--cc=tobias@codesourcery.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).