From: Nigel Stephens <nigel@mips.com>
To: Thiemo Seufer <ths@networkno.de>
Cc: Franck Bui-Huu <vagabon.xyz@gmail.com>,
"Maciej W. Rozycki" <macro@linux-mips.org>,
Ralf Baechle <ralf@linux-mips.org>,
linux-mips@linux-mips.org
Subject: Re: [PATCH] mm/pg-r4k.c: Dump the generated code
Date: Wed, 17 Oct 2007 14:25:05 +0100 [thread overview]
Message-ID: <47160D31.5080201@mips.com> (raw)
In-Reply-To: <20071017123046.GY3379@networkno.de>
Thiemo Seufer wrote:
> Franck Bui-Huu wrote:
>
>> Nigel Stephens wrote:
>>
>>> Could you run that gcc command manually, adding the options "-v
>>> --save-temps", and post the resulting output messages, and the user.s file.
>>>
>>>
>> Ok, I did it except I used init/do_mounts.c file since it has at least
>> one nop load delay slot (cf label $L50 in do_mount.s)
>>
>
> I only see a nop after the final LW, this is alignment for the next label.
>
>
Aha, that probably explains it. Franck is using the "SDE for Linux
v6.05" toolchain, and in that version of GCC -march=mips32r2 implies a
default of -mtune=24k. Tuning for 24K implies -falign-loops=8
-falign-jumps=8 and -falign-functions=8. This is undoubtedly why code
compiled with "-march=mips32r2 -msmartmips" contains more nops than
"-march=4ksd".nIn theory the extra nops should also disappear if you
compile with -Os instead of -O2.
Nigel
next prev parent reply other threads:[~2007-10-17 13:28 UTC|newest]
Thread overview: 93+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-02 13:54 [PATCH] mm/pg-r4k.c: Dump the generated code Maciej W. Rozycki
2007-10-02 14:11 ` Thiemo Seufer
2007-10-02 15:49 ` Ralf Baechle
2007-10-02 16:03 ` Thiemo Seufer
2007-10-02 16:08 ` Maciej W. Rozycki
2007-10-03 1:00 ` Ralf Baechle
2007-10-03 7:05 ` Geert Uytterhoeven
2007-10-03 10:32 ` Ralf Baechle
2007-10-03 12:17 ` Franck Bui-Huu
2007-10-03 13:11 ` Thiemo Seufer
2007-10-03 13:51 ` Maciej W. Rozycki
2007-10-03 19:45 ` Franck Bui-Huu
2007-10-03 20:18 ` Thiemo Seufer
2007-10-04 7:33 ` Franck Bui-Huu
2007-10-04 10:30 ` Maciej W. Rozycki
2007-10-04 12:15 ` Ralf Baechle
2007-10-04 15:01 ` Franck Bui-Huu
2007-10-04 15:23 ` Maciej W. Rozycki
2007-10-04 15:30 ` Ralf Baechle
2007-10-04 15:35 ` Maciej W. Rozycki
2007-10-04 15:42 ` Ralf Baechle
2007-10-04 17:34 ` Maciej W. Rozycki
2007-10-08 15:46 ` Maciej W. Rozycki
2007-10-08 16:41 ` Ralf Baechle
2007-10-08 16:45 ` Maciej W. Rozycki
2007-10-08 16:53 ` Ralf Baechle
2007-10-05 8:03 ` Franck Bui-Huu
2007-10-05 9:09 ` Geert Uytterhoeven
2007-10-08 15:02 ` Franck Bui-Huu
2007-10-08 15:21 ` Geert Uytterhoeven
2007-10-08 15:26 ` Ralf Baechle
2007-10-09 20:20 ` Franck Bui-Huu
2007-10-05 12:19 ` Maciej W. Rozycki
2007-10-08 14:48 ` Franck Bui-Huu
2007-10-08 15:24 ` Ralf Baechle
2007-10-08 15:39 ` Maciej W. Rozycki
2007-10-09 20:17 ` Franck Bui-Huu
2007-10-10 11:58 ` Maciej W. Rozycki
2007-10-10 12:08 ` [SPAM?] " Nigel Stephens
2007-10-11 12:01 ` Maciej W. Rozycki
2007-10-13 10:53 ` Richard Sandiford
2007-10-15 13:17 ` Maciej W. Rozycki
2007-10-14 19:37 ` Franck Bui-Huu
2007-10-15 13:26 ` Maciej W. Rozycki
2007-10-14 19:32 ` Franck Bui-Huu
2007-10-14 19:53 ` Thiemo Seufer
2007-10-14 20:29 ` Franck Bui-Huu
2007-10-15 19:35 ` Franck Bui-Huu
2007-10-15 20:11 ` Nigel Stephens
2007-10-16 8:24 ` Franck Bui-Huu
2007-10-16 12:58 ` Nigel Stephens
2007-10-17 7:56 ` Franck Bui-Huu
2007-10-17 12:30 ` Thiemo Seufer
2007-10-17 13:25 ` Nigel Stephens [this message]
2007-10-17 13:31 ` Maciej W. Rozycki
2007-11-04 8:21 ` Franck Bui-Huu
2007-11-04 17:47 ` Thiemo Seufer
2007-11-04 20:19 ` Franck Bui-Huu
2007-11-05 11:36 ` Ralf Baechle
2007-11-05 21:34 ` Franck Bui-Huu
2007-11-05 23:30 ` Ralf Baechle
2007-11-06 7:23 ` Franck Bui-Huu
2007-11-05 15:58 ` Nigel Stephens
2007-11-05 20:43 ` Franck Bui-Huu
2007-10-10 8:53 ` Ralf Baechle
2007-10-10 12:17 ` Maciej W. Rozycki
2007-10-05 11:51 ` Ralf Baechle
2007-10-08 14:11 ` Franck Bui-Huu
2007-10-08 14:41 ` Ralf Baechle
2007-10-09 20:33 ` Franck Bui-Huu
2007-10-09 20:34 ` [PATCH 1/6] tlbex.c: Cleanup __init usages Franck Bui-Huu
2007-10-11 16:16 ` Ralf Baechle
2007-10-12 6:36 ` Franck Bui-Huu
2007-10-12 14:43 ` Ralf Baechle
2007-10-09 20:35 ` [PATCH 2/6] tlbex.c: Remove relocs[] and labels[] from the init.data section Franck Bui-Huu
2007-10-09 20:35 ` Franck Bui-Huu
2007-10-10 14:27 ` Ralf Baechle
2007-10-10 16:17 ` Maciej W. Rozycki
2007-10-10 16:42 ` Ralf Baechle
2007-10-10 16:55 ` Geert Uytterhoeven
2007-10-10 17:01 ` Maciej W. Rozycki
2007-10-10 17:09 ` Geert Uytterhoeven
2007-10-10 19:58 ` Franck Bui-Huu
2007-10-10 19:29 ` Franck Bui-Huu
2007-10-09 20:36 ` [PATCH 3/6] tlbex.c: remove tlb_handler[] from " Franck Bui-Huu
2007-10-09 20:36 ` Franck Bui-Huu
2007-10-09 20:37 ` [PATCH 4/6] tlbex.c: remove final_handler[] " Franck Bui-Huu
2007-10-09 20:37 ` Franck Bui-Huu
2007-10-09 20:38 ` [PATCH 5/6] tlbex.c: cleanup debug code Franck Bui-Huu
2007-10-09 20:38 ` Franck Bui-Huu
2007-10-09 20:39 ` [PATCH 6/6] tlbex.c: cleanup include files Franck Bui-Huu
2007-10-09 20:39 ` Franck Bui-Huu
2007-10-03 13:41 ` [PATCH] mm/pg-r4k.c: Dump the generated code Ralf Baechle
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=47160D31.5080201@mips.com \
--to=nigel@mips.com \
--cc=linux-mips@linux-mips.org \
--cc=macro@linux-mips.org \
--cc=ralf@linux-mips.org \
--cc=ths@networkno.de \
--cc=vagabon.xyz@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