From: Jakub Jelinek <jakub@redhat.com>
To: Jason Merrill <jason@redhat.com>
Cc: Aldy Hernandez <aldyh@redhat.com>,
GCC Mailing List <gcc@gcc.gnu.org>,
"MacLeod, Andrew" <amacleod@redhat.com>
Subject: Re: 1.76% performance loss in VRP due to inlining
Date: Tue, 30 Apr 2024 21:22:09 +0200 [thread overview]
Message-ID: <ZjFE4cptpam2djqc@tucnak> (raw)
In-Reply-To: <CADzB+2=ptBaKFMj3zJgh-UM9Zuh0B8_RRmfVZhBESRFhkGQspA@mail.gmail.com>
On Tue, Apr 30, 2024 at 03:09:51PM -0400, Jason Merrill via Gcc wrote:
> On Fri, Apr 26, 2024 at 5:44 AM Aldy Hernandez via Gcc <gcc@gcc.gnu.org> wrote:
> >
> > In implementing prange (pointer ranges), I have found a 1.74% slowdown
> > in VRP, even without any code path actually using the code. I have
> > tracked this down to irange::get_bitmask() being compiled differently
> > with and without the bare bones patch. With the patch,
> > irange::get_bitmask() has a lot of code inlined into it, particularly
> > get_bitmask_from_range() and consequently the wide_int_storage code.
> ...
> > +static irange_bitmask
> > +get_bitmask_from_range (tree type,
> > + const wide_int &min, const wide_int &max)
> ...
> > -irange_bitmask
> > -irange::get_bitmask_from_range () const
>
> My guess is that this is the relevant change: the old function has
> external linkage, and is therefore interposable, which inhibits
> inlining. The new function has internal linkage, which allows
> inlining.
Even when a function is exported, when not compiled with -fpic/-fPIC
if we know the function is defined in current TU, it can't be interposed,
Try
int
foo (int x)
{
return x + 1;
}
int
bar (int x, int y)
{
return foo (x) + foo (y);
}
with -O2 -fpic -fno-semantic-interposition vs. -O2 -fpic vs. -O2 -fpie vs.
-O2.
> Relatedly, I wonder if we want to build GCC with -fno-semantic-interposition?
It could be useful just for libgccjit. And not sure if libgccjit users
don't want to interpose something.
Jakub
next prev parent reply other threads:[~2024-04-30 19:22 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-26 9:42 Aldy Hernandez
2024-04-30 7:57 ` Richard Biener
2024-04-30 8:21 ` Aldy Hernandez
2024-04-30 8:53 ` Martin Jambor
2024-04-30 19:09 ` Jason Merrill
2024-04-30 19:15 ` Richard Biener
2024-04-30 21:48 ` Building libgccjit with -fno-semantic-interposition? ( was Re: 1.76% performance loss in VRP due to inlining) David Malcolm
2024-05-02 7:40 ` Andrea Corallo
2024-04-30 19:22 ` Jakub Jelinek [this message]
2024-04-30 21:37 ` 1.76% performance loss in VRP due to inlining Jason Merrill
2024-05-03 8:55 ` Aldy Hernandez
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=ZjFE4cptpam2djqc@tucnak \
--to=jakub@redhat.com \
--cc=aldyh@redhat.com \
--cc=amacleod@redhat.com \
--cc=gcc@gcc.gnu.org \
--cc=jason@redhat.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).