From: Andrew Pinski <pinskia@gmail.com>
To: Sebastian Pop <sebpop@gmail.com>
Cc: Richard Biener <rguenther@suse.de>,
GCC Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH][0/n] Merge from match-and-simplify
Date: Thu, 16 Oct 2014 20:50:00 -0000 [thread overview]
Message-ID: <CA+=Sn1mFvukeSpkXNN7+rkTFok5hNHA-410noLj1+o2ChRKsMA@mail.gmail.com> (raw)
In-Reply-To: <20141016203852.GB29134@f1.c.bardezibar.internal>
On Thu, Oct 16, 2014 at 1:38 PM, Sebastian Pop <sebpop@gmail.com> wrote:
> Richard Biener wrote:
>>
>> I have posted 5 patches as part of a larger series to merge
>> (parts) from the match-and-simplify branch. While I think
>> there was overall consensus that the idea behind the project
>> is sound there are technical questions left for how the
>> thing should look in the end. I've raised them in 3/n
>> which is the only patch of the series that contains any
>> patterns sofar.
>>
>> To re-iterate here (as I expect most people will only look
>> at [0/n] patches ;)), the question is whether we are fine
>> with making fold-const (thus fold_{unary,binary,ternary})
>> not handle some cases it handles currently.
>
> I have tested on aarch64 all the code in the match-and-simplify against trunk as
> of the last merge at r216315:
>
> 2014-10-16 Richard Biener <rguenther@suse.de>
>
> Merge from trunk r216235 through r216315.
>
> Overall, I see a lot of perf regressions (about 2/3 of the tests) than
> improvements (1/3 of the tests). I will try to reduce tests.
>
> For instance, saxpy regresses at -O3 on aarch64:
>
> void saxpy(double* x, double* y, double* z) {
> int i=0;
> for (i = 0 ; i < ARRAY_SIZE; i++) {
> z[i] = x[i] + scalar*y[i];
> }
> }
This looks like a scheduling issue rather than anything else. The
scheduler for a57 is not complete and does not model some things like
the fusion of the compares and branch which is most likely what you
are seeing.
Thanks,
Andrew Pinski
>
> $ diff -u base.s mas.s
> --- base.s 2014-10-16 15:30:15.351430000 -0500
> +++ mas.s 2014-10-16 15:30:16.183035000 -0500
> @@ -2,12 +2,14 @@
> add x1, x2, 800
> ldr q0, [x0, x2]
> add x3, x2, 1600
> + cmp x0, 784
> ldr q1, [x0, x1]
> + add x1, x0, 16
> fmla v0.2d, v1.2d, v2.2d
> str q0, [x0, x3]
> - add x0, x0, 16
> - cmp x0, 800
> + mov x0, x1
> bne .L140
> .LBE179:
> - subs w4, w4, #1
> + cmp w4, 1
> + sub w4, w4, #1
> bne .L139
>
>
>
> Thanks,
> Sebastian
next prev parent reply other threads:[~2014-10-16 20:43 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-15 13:20 Richard Biener
2014-10-15 16:30 ` Kyrill Tkachov
2014-10-17 7:39 ` Ramana Radhakrishnan
2014-10-17 8:24 ` Richard Biener
2014-10-17 11:58 ` Richard Biener
2014-10-15 17:13 ` Jakub Jelinek
2014-10-16 20:43 ` Sebastian Pop
2014-10-16 20:50 ` Andrew Pinski [this message]
2014-10-17 7:29 ` Ramana Radhakrishnan
2014-10-17 8:00 ` Richard Biener
2014-10-17 16:44 ` Sebastian Pop
2014-10-17 17:37 ` Richard Biener
2014-10-17 18:32 ` Sebastian Pop
2014-10-20 11:47 ` Richard Biener
2014-10-22 21:06 ` Jeff Law
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='CA+=Sn1mFvukeSpkXNN7+rkTFok5hNHA-410noLj1+o2ChRKsMA@mail.gmail.com' \
--to=pinskia@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=rguenther@suse.de \
--cc=sebpop@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).