[Bug rtl-optimization/57967] Incorrect code generated on ARM with -fexpensive-optimizations

["daniel.blaukopf at oracle dot com" <gcc-bugzilla@gcc.gnu.org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=57967

--- Comment #2 from Daniel Blaukopf <daniel.blaukopf at oracle dot com> ---
This code:

int f1(int x0, int y0, int z0, int x1, int y1, int z1) {
    int xx = ((x0 << 16) + (x1 - x0) * 0x1234 + 0x8000) >> 16;
    int yy = ((y0 << 16) + (y1 - y0) * 0x2345 + 0x8000) >> 16;
    int zz = ((z0 << 16) + (z1 - z0) * 0x3456 + 0x8000) >> 16;
    return (xx << 16) | (yy << 8) | zz;
}

Compiles (incorrectly) to:
f1:
    @ args = 8, pretend = 0, frame = 0
    @ frame_needed = 0, uses_anonymous_args = 0
    @ link register save eliminated.
    ldr    r0, [sp, #4]
    subs    r0, r0, r2
    movw    r3, #13398
    mul    r0, r3, r0
    add    r2, r0, r2, lsl #16
    ldr    r3, [sp, #0]
    subs    r3, r3, r1
    movw    r0, #9029
    mul    r3, r0, r3
    add    r1, r3, r1, lsl #16
    add    r1, r1, #32768
    asr    r1, r1, #16
    lsl    r1, r1, #8
    add    r0, r2, #32768
    orr    r0, r1, r0, asr #16
    bx    lr

This almost identical code:

int f2(int x0, int x1, int y0, int y1, int z0, int z1) {
    int xx = ((x0 << 16) + (x1 - x0) * 0x1234 + 0x8000) >> 16;
    int yy = ((y0 << 16) + (y1 - y0) * 0x2345 + 0x8000) >> 16;
    int zz = ((z0 << 16) + (z1 - z0) * 0x3456 + 0x8000) >> 16;
    return (xx << 16) | (yy << 8) | zz;
}

Compiles (correctly) to:
f2:
    @ args = 8, pretend = 0, frame = 0
    @ frame_needed = 0, uses_anonymous_args = 0
    @ link register save eliminated.
    push    {r4, r5}
    ldr    r4, [sp, #8]
    subs    r3, r3, r2
    movw    r5, #9029
    mul    r3, r5, r3
    add    r2, r3, r2, lsl #16
    add    r2, r2, #32768
    asr    r2, r2, #16
    subs    r1, r1, r0
    movw    r3, #4660
    mul    r1, r3, r1
    add    r0, r1, r0, lsl #16
    add    r0, r0, #32768
    asr    r0, r0, #16
    lsl    r0, r0, #16
    orr    r2, r0, r2, lsl #8
    ldr    r0, [sp, #12]
    subs    r0, r0, r4
    movw    r3, #13398
    mul    r0, r3, r0
    add    r4, r0, r4, lsl #16
    add    r0, r4, #32768
    orr    r0, r2, r0, asr #16
    pop    {r4, r5}
    bx    lr