[Bug inline-asm/40819] New: 32x32->64 - asm code from "longlong.h" is not inlined for 68060's builds

["ami_stuff at o2 dot pl" <gcc-bugzilla at gcc dot gnu dot org>]

Hi,

There is an asm code for 32x32->64 function in the "longlong.h" file which can
be used for 68060 CPU:

#define umul_ppmm(xh, xl, a, b) \
  __asm__ ("| Inlined umul_ppmm\n"                                      \
           "    move%.l %2,%/d0\n"                                      \
           "    move%.l %3,%/d1\n"                                      \
           "    move%.l %/d0,%/d2\n"                                    \
           "    swap    %/d0\n"                                         \
           "    move%.l %/d1,%/d3\n"                                    \
           "    swap    %/d1\n"                                         \
           "    move%.w %/d2,%/d4\n"                                    \
           "    mulu    %/d3,%/d4\n"                                    \
           "    mulu    %/d1,%/d2\n"                                    \
           "    mulu    %/d0,%/d3\n"                                    \
           "    mulu    %/d0,%/d1\n"                                    \
           "    move%.l %/d4,%/d0\n"                                    \
           "    eor%.w  %/d0,%/d0\n"                                    \
           "    swap    %/d0\n"                                         \
           "    add%.l  %/d0,%/d2\n"                                    \
           "    add%.l  %/d3,%/d2\n"                                    \
           "    jcc     1f\n"                                           \
           "    add%.l  %#65536,%/d1\n"                                 \
           "1:  swap    %/d2\n"                                         \
           "    moveq   %#0,%/d0\n"                                     \
           "    move%.w %/d2,%/d0\n"                                    \
           "    move%.w %/d4,%/d2\n"                                    \
           "    move%.l %/d2,%1\n"                                      \
           "    add%.l  %/d1,%/d0\n"                                    \
           "    move%.l %/d0,%0"                                        \
           : "=g" ((USItype) (xh)),                                     \
             "=g" ((USItype) (xl))                                      \
           : "g" ((USItype) (a)),                                       \
             "g" ((USItype) (b))                                        \
           : "d0", "d1", "d2", "d3", "d4")

but it looks like in some cases(?) this asm inline is not used, so as a result
binaries generated for 68060 CPU (which heavy use 32x32->64 functions) are
about 40% slower (FFmpeg's MP3 decoder).

Here is generic C code:

#include <stdint.h>

inline int MULH(int a, int b){
    return ((int64_t)(a) * (int64_t)(b))>>32;
}


Here is asm output from GCC 4.4.0 (-m68060 -O3 -fomit-frame-pointer):

#NO_APP
        .text
        .even
        .globl  _MULH
_MULH:
        move.l d3,-(sp)
        move.l d2,-(sp)
        move.l 12(sp),d1
        smi d0
        extb.l d0
        move.l 16(sp),d3
        smi d2
        extb.l d2
        move.l d2,a0
        move.l d3,a1
        move.l a1,-(sp)
        move.l a0,-(sp)
        move.l d1,-(sp)
        move.l d0,-(sp)
        jsr ___muldi3
        lea (16,sp),sp
        move.l d0,d1
        smi d0
        extb.l d0
        move.l d1,d0
        move.l (sp)+,d2
        move.l (sp)+,d3
        rts


The same problem happens for functions defined like this:

#define MULL(a,b,s) (((int64_t)(a) * (int64_t)(b)) >> (s))
#define MUL64(a,b) ((int64_t)(a) * (int64_t)(b))
#define MAC64(d, a, b) ((d) += MUL64(a, b))
#define MLS64(d, a, b) ((d) -= MUL64(a, b))

Regards


-- 
           Summary: 32x32->64 -  asm code from "longlong.h" is not inlined
                    for 68060's builds
           Product: gcc
           Version: 4.4.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: inline-asm
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: ami_stuff at o2 dot pl
  GCC host triplet: i686-cygwin
GCC target triplet: m68k-amigaos


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40819