From: Bernd Roesch <nospamname@gmx.de>
To: ami_stuff <ami_stuff@o2.pl>
Cc: gcc@gcc.gnu.org
Subject: Re: m68k - GCC 4.4.0 generates not so good code from asm inline
Date: Wed, 29 Jul 2009 17:12:00 -0000 [thread overview]
Message-ID: <yam11532.481.281956144@mail.gmx.net> (raw)
In-Reply-To: <50a927e3.506a88ff.4a707f6a.ca5d5@o2.pl>
Hello
On 29.07.09, you wrote:
if you have a account you can report that as a Bug.
gcc4 have the advantage its possible to switch in source optimizer on or
off, but how it work, i dont know.
> When I use -O1 with GCC 4.4.0 (-m68060 -fomit-frame-pointer), I get better
> code.
>
> #include <stdio.h>
> #include <stdint.h>
>
> inline int64_t MUL64(int a, int b)
> {
>
> uint32_t resh, resl;
> uint32_t au = a;
> uint32_t bu = b;
>
> __asm__ ("move.l %0, d5\n\t"
> "move.l %1, d4\n\t"
> "moveq #16, d3\n\t"
> "move.l %0, d2\n\t"
> "mulu %1, %0\n\t"
> "lsr.l d3, d4\n\t"
> "lsr.l d3, d5\n\t"
> "mulu d4, d2\n\t"
> "mulu d5, %1\n\t"
> "mulu d5, d4\n\t"
> "move.l d2, d5\n\t"
> "lsr.l d3, d2\n\t"
> "add.w %1, d5\n\t"
> "addx.l d2, d4\n\t"
> "lsl.l d3, d5\n\t"
> "lsr.l d3, %1\n\t"
> "add.l d5, %0\n\t"
> "addx.l d4, %1\n\t"
> : "=d"(resl), "=d"(resh)
> : "0"(au), "1"(bu)
> : "d2", "d3", "d4", "d5");
>
> if (a < 0)
> resh -= bu;
> if (b < 0)
> resh -= au;
>
> return ((uint64_t)resh << 32) | resl;
> }
>
> GCC 4.4.0 -O3:
>
> #NO_APP
> .text
> .even
> .globl _MUL64
> _MUL64:
> movem.l #16128,-(sp)
> move.l 28(sp),d0
> move.l 32(sp),a0
> move.l d0,d6
> move.l a0,d1
> #APP
> ;# 11 "mul645.c" 1
> move.l d6, d5
> move.l d1, d4
> moveq #16, d3
> move.l d6, d2
> mulu d1, d6
> lsr.l d3, d4
> lsr.l d3, d5
> mulu d4, d2
> mulu d5, d1
> mulu d5, d4
> move.l d2, d5
> lsr.l d3, d2
> add.w d1, d5
> addx.l d2, d4
> lsl.l d3, d5
> lsr.l d3, d1
> add.l d5, d6
> addx.l d4, d1
>
> #NO_APP
> tst.l d0
> jlt L6
> tst.l a0
> jlt L7
> L3:
> move.l d1,d2
> clr.l d3
> move.l d2,d0
> move.l d3,d1
> or.l d6,d1
> move.l d0,d6
> move.l d1,d7
> move.l d7,d1
> movem.l (sp)+,#252
> rts
> L7:
> sub.l d0,d1
> move.l d1,d2
> clr.l d3
> move.l d2,d0
> move.l d3,d1
> or.l d6,d1
> move.l d0,d6
> move.l d1,d7
> move.l d7,d1
> movem.l (sp)+,#252
> rts
> L6:
> sub.l a0,d1
> tst.l a0
> jge L3
> jra L7
>
> GCC 4.4.0 -O2:
>
> #NO_APP
> .text
> .even
> .globl _MUL64
> _MUL64:
> movem.l #16128,-(sp)
> move.l 28(sp),d0
> move.l 32(sp),a0
> move.l d0,d6
> move.l a0,d1
> #APP
> ;# 11 "mul645.c" 1
> move.l d6, d5
> move.l d1, d4
> moveq #16, d3
> move.l d6, d2
> mulu d1, d6
> lsr.l d3, d4
> lsr.l d3, d5
> mulu d4, d2
> mulu d5, d1
> mulu d5, d4
> move.l d2, d5
> lsr.l d3, d2
> add.w d1, d5
> addx.l d2, d4
> lsl.l d3, d5
> lsr.l d3, d1
> add.l d5, d6
> addx.l d4, d1
>
> #NO_APP
> tst.l d0
> jlt L6
> tst.l a0
> jlt L7
> L3:
> move.l d1,d2
> clr.l d3
> move.l d2,d0
> move.l d3,d1
> or.l d6,d1
> move.l d0,d6
> move.l d1,d7
> move.l d7,d1
> movem.l (sp)+,#252
> rts
> L7:
> sub.l d0,d1
> move.l d1,d2
> clr.l d3
> move.l d2,d0
> move.l d3,d1
> or.l d6,d1
> move.l d0,d6
> move.l d1,d7
> move.l d7,d1
> movem.l (sp)+,#252
> rts
> L6:
> sub.l a0,d1
> tst.l a0
> jge L3
> jra L7
>
> GCC 4.4.0 -O1:
>
> #NO_APP
> .text
> .even
> .globl _MUL64
> _MUL64:
> movem.l #16176,-(sp)
> move.l 40(sp),d0
> move.l 36(sp),a2
> move.l a2,d7
> move.l d0,d6
> #APP
> ;# 11 "mul645.c" 1
> move.l d7, d5
> move.l d6, d4
> moveq #16, d3
> move.l d7, d2
> mulu d6, d7
> lsr.l d3, d4
> lsr.l d3, d5
> mulu d4, d2
> mulu d5, d6
> mulu d5, d4
> move.l d2, d5
> lsr.l d3, d2
> add.w d6, d5
> addx.l d2, d4
> lsl.l d3, d5
> lsr.l d3, d6
> add.l d5, d7
> addx.l d4, d6
>
> #NO_APP
> tst.l a2
> jge L2
> sub.l d0,d6
> L2:
> tst.l d0
> jge L3
> sub.l a2,d6
> L3:
> move.l d6,d1
> clr.l d2
> or.l d7,d2
> move.l d1,d0
> move.l d2,d1
> movem.l (sp)+,#3324
> rts
>
> GCC 4.4.0 -O0:
>
> #NO_APP
> .text
> .even
> .globl _MUL64
> _MUL64:
> lea (-16,sp),sp
> movem.l #16128,-(sp)
> move.l 44(sp),32(sp)
> move.l 48(sp),36(sp)
> move.l 32(sp),d1
> move.l 36(sp),d0
> #APP
> ;# 11 "mul645.c" 1
> move.l d1, d5
> move.l d0, d4
> moveq #16, d3
> move.l d1, d2
> mulu d0, d1
> lsr.l d3, d4
> lsr.l d3, d5
> mulu d4, d2
> mulu d5, d0
> mulu d5, d4
> move.l d2, d5
> lsr.l d3, d2
> add.w d0, d5
> addx.l d2, d4
> lsl.l d3, d5
> lsr.l d3, d0
> add.l d5, d1
> addx.l d4, d0
>
> #NO_APP
> move.l d1,28(sp)
> move.l d0,24(sp)
> tst.l 44(sp)
> jge L2
> move.l 36(sp),d0
> sub.l d0,24(sp)
> L2:
> tst.l 48(sp)
> jge L3
> move.l 32(sp),d2
> sub.l d2,24(sp)
> L3:
> move.l 24(sp),d7
> clr.l d6
> move.l d7,d0
> clr.l d1
> move.l 28(sp),a1
> lea 0.w,a0
> move.l a0,d2
> move.l a1,d3
> or.l d2,d0
> or.l d3,d1
> movem.l (sp)+,#252
> lea (16,sp),sp
> rts
>
> Regards
>
Regards
prev parent reply other threads:[~2009-07-29 17:12 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-29 11:41 ami_stuff
2009-07-29 16:57 ` ami_stuff
2009-07-29 17:12 ` Bernd Roesch [this message]
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=yam11532.481.281956144@mail.gmx.net \
--to=nospamname@gmx.de \
--cc=ami_stuff@o2.pl \
--cc=gcc@gcc.gnu.org \
/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).