[Bug c/113779] New: Very inefficient m68k code generated for simple copy loop

[miro.kropacek at gmail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113779

            Bug ID: 113779
           Summary: Very inefficient m68k code generated for simple copy
                    loop
           Product: gcc
           Version: 13.2.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
          Assignee: unassigned at gcc dot gnu.org
          Reporter: miro.kropacek at gmail dot com
  Target Milestone: ---

Even as simple loop as this:

void f(const long* src, long* dst, int count) {
        for (int i = 0; i < count; i++) {
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
                *dst++ = *src++;
        }
}

is compiled to:

#NO_APP
        .file   "test.c"
        .text
        .align  2
        .globl  f
        .type   f, @function
f:
        move.l 4(%sp),%a0
        move.l 8(%sp),%a1
        move.l 12(%sp),%d1
        jle .L1
        clr.l %d0
.L3:
        move.l (%a0),(%a1)
        move.l 4(%a0),4(%a1)
        move.l 8(%a0),8(%a1)
        move.l 12(%a0),12(%a1)
        move.l 16(%a0),16(%a1)
        move.l 20(%a0),20(%a1)
        move.l 24(%a0),24(%a1)
        move.l 28(%a0),28(%a1)
        move.l 32(%a0),32(%a1)
        move.l 36(%a0),36(%a1)
        move.l 40(%a0),40(%a1)
        move.l 44(%a0),44(%a1)
        move.l 48(%a0),48(%a1)
        move.l 52(%a0),52(%a1)
        move.l 56(%a0),56(%a1)
        add.w #64,%a0
        add.w #64,%a1
        move.l -4(%a0),-4(%a1)
        addq.l #1,%d0
        cmp.l %d1,%d0
        jne .L3
.L1:
        rts
        .size   f, .-f
        .ident  "GCC: (GNU) 13.2.0"

This has been like this for ages: gcc 4.6.4, gcc 7.2.0 and lately gcc 13.2.0
... the last gcc where it was reported to transform into move.l (a0)+,(a1)+ was
gcc 2.95 and gcc 3.x. 

So what's the catch here? Why gcc hates move.l (ax)+,(ay)+ so much? Tested on
m68k-elf-gcc -O2 -fomit-frame-pointer -m68020-60.