[Bug target/54089] [SH] Refactor shift patterns

["klepikov.alex+bugs at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54089

--- Comment #50 from Alexander Klepikov <klepikov.alex+bugs at gmail dot com> ---
> > I've found that my patch catches integer division. In short, it appears to
> > work unpredictable. It looks like there's no easy way to catch right shift.
> 
> What do you mean it catches integer division? There could be several places
> during compilation, where the compiler will try to convert integer division
> to right shifts.  But it will not do so unless it's wrong.  The patterns you
> have added shouldn't match a division operation.

Ooh, my bad! You are absolutely right. A function is inlined and division is
converted to 4 'shar's which at combine pass are catched by 'define_insn
"ashrsi3_libcall_collapsed"' which is little unexpected to me. Of course, it is
expanded at 'split' pass to lib call. 5 and less right shifts should not
convert to a lib call, but that can be easily corrected.

But maybe there is a way to exclude particular insn from combine pass? (I guess
not).

Here are the files that confused me:

$ cat pr49880-3.c
/* Check that the option -mdiv=call-table works.  */
/* { dg-do link }  */
/* { dg-options "-mdiv=call-table" }  */

int
test00 (int a, int b)
{
  return a / b;
}

unsigned int
test01 (unsigned int a, unsigned b)
{
  return a / b;
}

int
main (int argc, char** argv)
{
  return test00 (argc, 123) + test01 (argc, 123);
}

Not-patched GCC

$ cat pr49880-3.s.clean
        .file   "pr49880-3.c"
        .text
        .text
        .align 1
        .align 2
        .global _test00
        .type   _test00, @function
_test00:
        mov.l   .L4,r0
        sts.l   pr,@-r15
        jsr     @r0
        nop
        lds.l   @r15+,pr
        rts
        nop
.L5:
        .align 2
.L4:
        .long   ___sdivsi3
        .size   _test00, .-_test00
        .align 1
        .align 2
        .global _test01
        .type   _test01, @function
_test01:
        mov.l   .L8,r0
        sts.l   pr,@-r15
        jsr     @r0
        nop
        lds.l   @r15+,pr
        rts
        nop
.L9:
        .align 2
.L8:
        .long   ___udivsi3
        .size   _test01, .-_test01
        .section        .text.startup,"ax",@progbits
        .align 1
        .align 2
        .global _main
        .type   _main, @function
_main:
        mov.l   .L11,r1
        dmuls.l r1,r4
        sts     mach,r0
        shar    r0
        shar    r0
        shar    r0
        shar    r0
        mov     r4,r1
        shll    r1
        subc    r1,r1
        sub     r1,r0
        mov.l   .L12,r1
        dmulu.l r1,r4
        sts     mach,r1
        sub     r1,r4
        shlr    r4
        add     r4,r1
        shlr2   r1
        shlr2   r1
        shlr2   r1
        rts
        add     r1,r0
.L13:
        .align 2
.L11:
        .long   558694933
.L12:
        .long   174592167
        .size   _main, .-_main
        .ident  "GCC: (GNU) 13.1.0"

Patched GCC

$ cat pr49880-3.s
        .file   "pr49880-3.c"
        .text
        .text
        .align 1
        .align 2
        .global _test00
        .type   _test00, @function
_test00:
        mov.l   .L4,r0
        sts.l   pr,@-r15
        jsr     @r0
        nop
        lds.l   @r15+,pr
        rts
        nop
.L5:
        .align 2
.L4:
        .long   ___sdivsi3
        .size   _test00, .-_test00
        .align 1
        .align 2
        .global _test01
        .type   _test01, @function
_test01:
        mov.l   .L8,r0
        sts.l   pr,@-r15
        jsr     @r0
        nop
        lds.l   @r15+,pr
        rts
        nop
.L9:
        .align 2
.L8:
        .long   ___udivsi3
        .size   _test01, .-_test01
        .section        .text.startup,"ax",@progbits
        .align 1
        .align 2
        .global _main
        .type   _main, @function
_main:
        mov.l   .L12,r2
        mov     r4,r1
        sts.l   pr,@-r15
        dmuls.l r2,r4
        mov.l   .L13,r2
        jsr     @r2
        sts     mach,r4
        mov     r1,r2
        shll    r2
        subc    r2,r2
        mov     r4,r0
        sub     r2,r0
        mov.l   .L14,r2
        dmulu.l r2,r1
        sts     mach,r2
        sub     r2,r1
        shlr    r1
        add     r1,r2
        shlr2   r2
        shlr2   r2
        shlr2   r2
        add     r2,r0
        lds.l   @r15+,pr
        rts
        nop
.L15:
        .align 2
.L12:
        .long   558694933
.L13:
        .long   ___ashiftrt_r4_4
.L14:
        .long   174592167
        .size   _main, .-_main
        .ident  "GCC: (GNU) 13.1.0"



Now concerning GCC testsuite. I ran it in such way:

make check RUNTESTFLAGS="CFLAGS='$CFLAGS -I/usr/local/sh-elf/include/'
--target_board=sh-sim\{-m2e,-m4\}\{-ml,-mb\}"

There are lots of failed tests on non-patched GCC. Even if I narrow tests list
to sh.exp, it still fails a lot of times. At last there's nothing in logs that
produce ICE in RTL. I'm not sure I could find a crash due to the patch at all,
even if it were there.

And finally, 'parallel' appears to be unnecessary, thank you for pointing.