From: Ulrich Drepper <drepper.fsp@gmail.com>
To: Xionghu Luo <luoxhu@linux.ibm.com>
Cc: Richard Biener <richard.guenther@gmail.com>,
Segher Boessenkool <segher@kernel.crashing.org>,
Bill Schmidt <wschmidt@linux.ibm.com>,
linkw@gcc.gnu.org, GCC Patches <gcc-patches@gcc.gnu.org>,
Jan Hubicka <hubicka@ucw.cz>, David Edelsohn <dje.gcc@gmail.com>
Subject: Re: [RFC] Don't move cold code out of loop by checking bb count
Date: Tue, 10 Aug 2021 06:25:54 +0200 [thread overview]
Message-ID: <CAOPLpQdiuETKvQYHP+G0toncwiZ1GY8wo-SvGtgRyKnvtE45tA@mail.gmail.com> (raw)
In-Reply-To: <e9cc0874-b066-5eaf-6334-e7c8492a22a5@linux.ibm.com>
On Tue, Aug 10, 2021 at 4:03 AM Xionghu Luo via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
> For this case, theorotically I think the master GCC will optimize it to:
>
> invariant;
> for (;;)
> if (unlikely_cond)
> for (;;)
> ;
>
> 'invariant' is moved out of outer loop, but with the patch, it will get:
>
> for (;;)
> if (unlikely_cond)
> {
> invariant;
> for (;;)
> ;
> }
>
> 'invariant' is *cold* for outer loop, but it is still *hot* for inner loop,
> so hoist it out of inner loop, this is exactly what we want, right?
Is relying on absolute numbers really what you want? If the
'unlikely_cond' condition depends on the iteration count of the outer
loop the probability of it being true in each individual iteration can
be low (at least that's how I use unlikely) but the overall
probability of needing the code is higher 1 - (1 - p)^n if 'p' is the
probability of 'unlikely_cond' and 'n' is the number of iterations.
Assuming complete independence of the loop iterations, otherwise it's
rather an upper limit.
At the very least I'd generate code like this:
first = true;
for (;;)
if (unlikely_cond)
{
if (first)
{
invariant;
first = false;
}
for (;;)
;
}
If it's worth hoisting the code the the extra test and flag should be
small in cost in comparison.
If 'unlikely_cond' does not in any way depend on the loop iteration
then I think your code generation is fine.
next prev parent reply other threads:[~2021-08-10 4:26 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-02 5:05 Xiong Hu Luo
2021-08-06 12:15 ` Richard Biener
2021-08-10 2:03 ` Xionghu Luo
2021-08-10 4:25 ` Ulrich Drepper [this message]
2021-08-19 5:51 ` [PATCH v2] " Xionghu Luo
2021-08-26 11:33 ` [RFC] " Richard Biener
2021-09-09 1:55 ` Xionghu Luo
2021-09-22 9:14 ` Richard Biener
2021-09-23 2:13 ` Xionghu Luo
2021-09-23 2:16 ` Xionghu Luo
2021-09-24 6:29 ` Xionghu Luo
2021-09-28 12:09 ` Richard Biener
2021-10-09 3:44 ` Xionghu Luo
2021-10-15 8:11 ` Richard Biener
2021-10-18 4:29 ` Xionghu Luo
2021-10-19 1:47 ` [PATCH v5 2/2] " Xionghu Luo
2021-10-26 13:20 ` [RFC] " Richard Biener
2021-10-27 2:40 ` Xionghu Luo
2021-10-29 11:48 ` Richard Biener
2021-11-03 6:49 ` Xionghu Luo
2021-11-03 13:29 ` Xionghu Luo
2021-11-04 13:00 ` Richard Biener
2021-11-10 3:08 ` [PATCH v7 2/2] " Xionghu Luo
2021-11-24 5:15 ` Ping: " Xionghu Luo
2021-11-24 7:35 ` Richard Biener
2021-12-01 10:09 ` Richard Biener
2021-12-06 5:09 ` [PATCH v8 " Xionghu Luo
2021-12-06 5:26 ` Xionghu Luo
2021-12-07 12:17 ` Richard Biener
2021-12-08 6:32 ` Xionghu Luo
2021-12-20 7:29 ` Richard Biener
2021-12-21 3:59 ` Xionghu Luo
2021-10-27 12:54 ` [RFC] " Jan Hubicka
2021-10-28 1:49 ` Xionghu Luo
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=CAOPLpQdiuETKvQYHP+G0toncwiZ1GY8wo-SvGtgRyKnvtE45tA@mail.gmail.com \
--to=drepper.fsp@gmail.com \
--cc=dje.gcc@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hubicka@ucw.cz \
--cc=linkw@gcc.gnu.org \
--cc=luoxhu@linux.ibm.com \
--cc=richard.guenther@gmail.com \
--cc=segher@kernel.crashing.org \
--cc=wschmidt@linux.ibm.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).