From: Richard Sandiford <richard.sandiford@arm.com>
To: Qing Zhao <QING.ZHAO@ORACLE.COM>
Cc: Richard Biener <rguenther@suse.de>,
Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org>
Subject: Re: The performance data for two different implementation of new security feature -ftrivial-auto-var-init
Date: Mon, 18 Jan 2021 13:09:02 +0000 [thread overview]
Message-ID: <mpt7doa5r4h.fsf@arm.com> (raw)
In-Reply-To: <4BD13E0F-A561-4429-AEB8-5BDEA6987D21@ORACLE.COM> (Qing Zhao's message of "Fri, 15 Jan 2021 11:57:51 -0600")
Qing Zhao <QING.ZHAO@ORACLE.COM> writes:
>>>> D will keep all initialized aggregates as aggregates and live which
>>>> means stack will be allocated for it. With A the usual optimizations
>>>> to reduce stack usage can be applied.
>>>
>>> I checked the routine “poverties::bump_map” in 511.povray_r since it
>>> has a lot stack increase
>>> due to implementation D, by examine the IR immediate before RTL
>>> expansion phase.
>>> (image.cpp.244t.optimized), I found that we have the following
>>> additional statements for the array elements:
>>>
>>> void pov::bump_map (double * EPoint, struct TNORMAL * Tnormal, double
>>> * normal)
>>> {
>>> …
>>> double p3[3];
>>> double p2[3];
>>> double p1[3];
>>> float colour3[5];
>>> float colour2[5];
>>> float colour1[5];
>>> …
>>> # DEBUG BEGIN_STMT
>>> colour1 = .DEFERRED_INIT (colour1, 2);
>>> colour2 = .DEFERRED_INIT (colour2, 2);
>>> colour3 = .DEFERRED_INIT (colour3, 2);
>>> # DEBUG BEGIN_STMT
>>> MEM <double> [(double[3] *)&p1] = p1$0_144(D);
>>> MEM <double> [(double[3] *)&p1 + 8B] = p1$1_135(D);
>>> MEM <double> [(double[3] *)&p1 + 16B] = p1$2_138(D);
>>> p1 = .DEFERRED_INIT (p1, 2);
>>> # DEBUG D#12 => MEM <double> [(double[3] *)&p1]
>>> # DEBUG p1$0 => D#12
>>> # DEBUG D#11 => MEM <double> [(double[3] *)&p1 + 8B]
>>> # DEBUG p1$1 => D#11
>>> # DEBUG D#10 => MEM <double> [(double[3] *)&p1 + 16B]
>>> # DEBUG p1$2 => D#10
>>> MEM <double> [(double[3] *)&p2] = p2$0_109(D);
>>> MEM <double> [(double[3] *)&p2 + 8B] = p2$1_111(D);
>>> MEM <double> [(double[3] *)&p2 + 16B] = p2$2_254(D);
>>> p2 = .DEFERRED_INIT (p2, 2);
>>> # DEBUG D#9 => MEM <double> [(double[3] *)&p2]
>>> # DEBUG p2$0 => D#9
>>> # DEBUG D#8 => MEM <double> [(double[3] *)&p2 + 8B]
>>> # DEBUG p2$1 => D#8
>>> # DEBUG D#7 => MEM <double> [(double[3] *)&p2 + 16B]
>>> # DEBUG p2$2 => D#7
>>> MEM <double> [(double[3] *)&p3] = p3$0_256(D);
>>> MEM <double> [(double[3] *)&p3 + 8B] = p3$1_258(D);
>>> MEM <double> [(double[3] *)&p3 + 16B] = p3$2_260(D);
>>> p3 = .DEFERRED_INIT (p3, 2);
>>> ….
>>> }
>>>
>>> I guess that the above “MEM <double>….. = …” are the ones that make the
>>> differences. Which phase introduced them?
>>
>> Looks like SRA. But you can just dump all and grep for the first occurrence.
>
> Yes, looks like that SRA is the one:
>
> image.cpp.035t.esra: MEM <double> [(double[3] *)&p1] = p1$0_195(D);
> image.cpp.035t.esra: MEM <double> [(double[3] *)&p1 + 8B] = p1$1_182(D);
> image.cpp.035t.esra: MEM <double> [(double[3] *)&p1 + 16B] = p1$2_185(D);
I realise no-one was suggesting otherwise, but FWIW: SRA could easily
be extended to handle .DEFERRED_INIT if that's the main source of
excess stack usage. A single .DEFERRED_INIT of an aggregate can
be split into .DEFERRED_INITs of individual components.
In other words, the investigation you're doing looks like the right way
of deciding which passes are worth extending to handle .DEFERRED_INIT.
Thanks,
Richard
next prev parent reply other threads:[~2021-01-18 13:09 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-23 23:05 How to traverse all the local variables that declared in the current routine? Qing Zhao
2020-11-24 7:32 ` Richard Biener
2020-11-24 15:47 ` Qing Zhao
2020-11-24 15:55 ` Richard Biener
2020-11-24 16:54 ` Qing Zhao
2020-11-25 9:11 ` Richard Biener
2020-11-25 17:41 ` Qing Zhao
2020-12-01 19:47 ` Qing Zhao
2020-12-02 8:45 ` Richard Biener
2020-12-02 15:36 ` Qing Zhao
2020-12-03 8:45 ` Richard Biener
2020-12-03 16:07 ` Qing Zhao
2020-12-03 16:36 ` Richard Biener
2020-12-03 16:40 ` Qing Zhao
2020-12-03 16:56 ` Richard Sandiford
2020-11-26 0:08 ` Martin Sebor
2020-11-30 16:23 ` Qing Zhao
2020-11-30 17:18 ` Martin Sebor
2020-11-30 23:05 ` Qing Zhao
2020-12-03 17:32 ` Richard Sandiford
2020-12-03 23:04 ` Qing Zhao
2020-12-04 8:50 ` Richard Biener
2020-12-04 16:19 ` Qing Zhao
2020-12-07 7:12 ` Richard Biener
2020-12-07 16:20 ` Qing Zhao
2020-12-07 17:10 ` Richard Sandiford
2020-12-07 17:36 ` Qing Zhao
2020-12-07 18:05 ` Richard Sandiford
2020-12-07 18:34 ` Qing Zhao
2020-12-08 7:35 ` Richard Biener
2020-12-08 7:40 ` Richard Biener
2020-12-08 19:54 ` Qing Zhao
2020-12-09 8:23 ` Richard Biener
2020-12-09 15:04 ` Qing Zhao
2020-12-09 15:12 ` Richard Biener
2020-12-09 16:18 ` Qing Zhao
2021-01-05 19:05 ` The performance data for two different implementation of new security feature -ftrivial-auto-var-init Qing Zhao
2021-01-05 19:10 ` Qing Zhao
2021-01-12 20:34 ` Qing Zhao
2021-01-13 7:39 ` Richard Biener
2021-01-13 15:06 ` Qing Zhao
2021-01-13 15:10 ` Richard Biener
2021-01-13 15:35 ` Qing Zhao
2021-01-13 15:40 ` Richard Biener
2021-01-14 21:16 ` Qing Zhao
2021-01-15 8:11 ` Richard Biener
2021-01-15 16:16 ` Qing Zhao
2021-01-15 17:22 ` Richard Biener
2021-01-15 17:57 ` Qing Zhao
2021-01-18 13:09 ` Richard Sandiford [this message]
2021-01-18 16:12 ` Qing Zhao
2021-02-01 19:12 ` Qing Zhao
2021-02-02 7:43 ` Richard Biener
2021-02-02 15:17 ` Qing Zhao
2021-02-02 23:32 ` Qing Zhao
2020-12-07 17:21 ` How to traverse all the local variables that declared in the current routine? Richard Sandiford
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=mpt7doa5r4h.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=QING.ZHAO@ORACLE.COM \
--cc=gcc-patches@gcc.gnu.org \
--cc=rguenther@suse.de \
/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).