[Bug c/64479] New: wrong optimization delayed-branch for SH

["oshima-ya at yagoto-urayama dot jp" <gcc-bugzilla at gcc dot gnu dot org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=64479

            Bug ID: 64479
           Summary: wrong optimization delayed-branch  for SH
           Product: gcc
           Version: 4.8.4
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
          Assignee: unassigned at gcc dot gnu.org
          Reporter: oshima-ya@yagoto-urayama.jp

On NetBSD/landisk(sh3) 7.0_BETA, gcc4.8.4 generates some strange code.

Test case:

int foo(int);
void bar(int *);
void func(int args)
{
        int key;
        int flag = (args==0);
        bar(&key);
        if (!args) foo(1);
        if (foo(args)) {
                if (flag && key == 0) foo(2);
                else
                    if (flag) foo(3);
        }
}

it generated by compile with -Os -S:

func:
.LFB0:
        .cfi_startproc
        mov.l   r8,@-r15
        .cfi_def_cfa_offset 4
        .cfi_offset 8, -4
        mov.l   r9,@-r15
        .cfi_def_cfa_offset 8
        .cfi_offset 9, -8
        mov.l   r10,@-r15
        .cfi_def_cfa_offset 12
        .cfi_offset 10, -12
        mov.l   r11,@-r15
        .cfi_def_cfa_offset 16
        .cfi_offset 11, -16
        sts.l   pr,@-r15
        .cfi_def_cfa_offset 20
        .cfi_offset 17, -20
        add     #-4,r15
        .cfi_def_cfa_offset 24
        mov.l   .L16,r1
        tst     r4,r4
        movt    r8         # T bit -> R8
        mov     r4,r9
        jsr     @r1        # subroutine call (bar)
        mov     r15,r4
        mov.l   .L18,r11
        bf      .L2ããã ã# what condition? (T bit == 0?)
        jsr     @r11
        mov     #1,r4
.L2

When compiled with -Os -fno-delayed-branch -S:

func:
.LFB0:
        .cfi_startproc
        mov.l   r8,@-r15
        .cfi_def_cfa_offset 4
        .cfi_offset 8, -4
        mov.l   r9,@-r15
        .cfi_def_cfa_offset 8
        .cfi_offset 9, -8
        mov.l   r10,@-r15
        .cfi_def_cfa_offset 12
        .cfi_offset 10, -12
        mov.l   r11,@-r15
        .cfi_def_cfa_offset 16
        .cfi_offset 11, -16
        sts.l   pr,@-r15
        .cfi_def_cfa_offset 20
        .cfi_offset 17, -20
        add     #-4,r15
        .cfi_def_cfa_offset 24
        mov.l   .L16,r1
        tst     r4,r4
        movt    r8        # T bit -> R8
        mov     r4,r9
        mov     r15,r4
        jsr     @r1       # subroutine call (bar)
        nop
        tst     r8,r8     # if (R8 == 0) then T bit = 1
        mov.l   .L18,r11  
        bt      .L2       # if (T bit == 1) branch .L2
        mov     #1,r4
        jsr     @r11
        nop
.L2:

With -Os (include -fdelayed-branch), tst r8,r8 instruction is omitted, and
branch condition is inverted.

The same problem in this case occurs in flow_loops_find() function of
gcc/cfgloop.c when building gcc 4.8.4 for NetBSD/sh3-binary. So gcc
native-binary for sh3 will be wrong.