From: Richard Sandiford <richard.sandiford@linaro.org>
To: "H.J. Lu" <hjl.tools@gmail.com>
Cc: gcc-patches@gcc.gnu.org, bonzini@gnu.org
Subject: Re: RFC: allowing fwprop to propagate subregs
Date: Wed, 14 Sep 2011 16:09:00 -0000 [thread overview]
Message-ID: <g439fzqgbj.fsf@richards-thinkpad.stglab.manchester.uk.ibm.com> (raw)
In-Reply-To: <CAMe9rOq=zEi2=-Q9CTu77q90+WW4PBpZ7Eo8ZrZJdK3w1YAO-Q@mail.gmail.com> (H. J. Lu's message of "Wed, 14 Sep 2011 08:30:57 -0700")
"H.J. Lu" <hjl.tools@gmail.com> writes:
> On Wed, Sep 14, 2011 at 8:24 AM, Richard Sandiford
> <rdsandiford@googlemail.com> wrote:
>> At the moment, fwprop will propagate constants and registers
>> even if no further rtl simplifications are possible:
>>
>> if (REG_P (new_rtx) || CONSTANT_P (new_rtx))
>> flags |= PR_CAN_APPEAR;
>>
>> What do you think about extending this to subregs? The reason for
>> asking is that on NEON, vector loads like vld4 are represented as a load
>> of a single monolithic register followed by subreg extractions of each
>> vector:
>>
>> (set (reg:OI FULL) (...))
>> (set (reg:V2SI V0) (subreg:V2SI (reg:OI FULL) 0))
>> (set (reg:V2SI V1) (subreg:V2SI (reg:OI FULL) 16))
>> (set (reg:V2SI V2) (subreg:V2SI (reg:OI FULL) 32))
>> (set (reg:V2SI V3) (subreg:V2SI (reg:OI FULL) 48))
>>
>> Nothing ever propagates these subregs, so the separate moves
>> survive until IRA. This has three problems:
>>
>> - We generally want the registers allocated to V0...V3 to be the same
>> as FULL, so that the four subreg moves become nops. And this often
>> happens in simple examples. But if register pressure is relatively
>> high, these moves can sometimes cause IRA to spill in cases where
>> it doesn't if the subregs are used instead of each Vi.
>>
>> - Perhaps related, register pressure becomes harder to estimate.
>>
>> - These moves can interfere with pre-reload scheduling.
>>
>> In combination with the MODES_TIEABLE_P patch that I posted here:
>>
>> http://gcc.gnu.org/ml/gcc-patches/2011-09/msg00626.html
>>
>> this patch significantly improves the code generated for several libav
>> loops. Unfortunately, I don't have a setup that can do meaningful
>> x86_64 performance measurements, but a diff of the before and after
>> output for libav showed many cases where the patch removed moves.
>>
>> What do you think? Alternatives include propagating in lower-subreg,
>> or maybe only in the second fwprop pass.
>>
>> Richard
>>
>>
>> gcc/
>> * fwprop.c (propagate_rtx): Also set PR_CAN_APPEAR for subregs.
>>
>> Index: gcc/fwprop.c
>> ===================================================================
>> --- gcc/fwprop.c 2011-08-26 09:58:28.829540497 +0100
>> +++ gcc/fwprop.c 2011-08-26 10:14:03.767707504 +0100
>> @@ -664,7 +664,7 @@ propagate_rtx (rtx x, enum machine_mode
>> return NULL_RTX;
>>
>> flags = 0;
>> - if (REG_P (new_rtx) || CONSTANT_P (new_rtx))
>> + if (REG_P (new_rtx) || CONSTANT_P (new_rtx) || GET_CODE (new_rtx) == SUBREG)
>> flags |= PR_CAN_APPEAR;
>> if (!for_each_rtx (&new_rtx, varying_mem_p, NULL))
>> flags |= PR_HANDLE_MEM;
>>
>
> A SUBREG may not be REG nor CONSTANT. Don't you need
> to check REG_P/CONSTANT_P on SUBREG?
Yeah, good point. There should be a "&& REG_P (SUBREG_REG (new_rtx))"
in there. Probably also worth checking for non-paradoxical subregs.
Richard
next prev parent reply other threads:[~2011-09-14 15:45 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-14 15:40 Richard Sandiford
2011-09-14 15:45 ` H.J. Lu
2011-09-14 16:09 ` Richard Sandiford [this message]
2011-09-14 18:28 ` Paolo Bonzini
2012-01-11 16:55 ` Ulrich Weigand
2012-01-11 19:12 ` Paolo Bonzini
2012-01-12 9:57 ` Richard Sandiford
2012-01-12 11:56 ` Richard Kenner
2012-01-16 14:21 ` Ulrich Weigand
2012-01-16 14:32 ` Richard Kenner
2012-01-17 19:25 ` Ulrich Weigand
2012-01-17 19:56 ` Richard Kenner
2012-03-07 17:40 ` [PATCH] Do not handle SUBREG in apply_distributive_law (Re: RFC: allowing fwprop to propagate subregs) Ulrich Weigand
2012-03-12 10:23 ` Richard Guenther
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=g439fzqgbj.fsf@richards-thinkpad.stglab.manchester.uk.ibm.com \
--to=richard.sandiford@linaro.org \
--cc=bonzini@gnu.org \
--cc=gcc-patches@gcc.gnu.org \
--cc=hjl.tools@gmail.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).