Missed optimizations at -Os

[Senthil Kumar Selvaraj <senthilkumar dot selvaraj at microchip dot com>]

Hi,

  For this (reduced) test case

  
extern int x, y, z;
void foo(void);
void bar(void);
void blah(void);

void test (void)
{
  int flag = 0;
  flag = ((x && y) || z);

  if (flag && x && y) {
     bar();
  }
}

  I expected gcc -Os (x86_64, if it matters) to generate code equivalent to

if (x && y)
  bar();


  Instead, I get

test():
        mov     eax, DWORD PTR x[rip]
        test    eax, eax
        je      .L2
        cmp     DWORD PTR y[rip], 0
        jne     .L3
.L2:
        cmp     DWORD PTR z[rip], 0
        je      .L1
        test    eax, eax
        je      .L1
.L3:
        cmp     DWORD PTR y[rip], 0
        je      .L1
        jmp     bar()
.L1:
        ret

At -O1 and above though, I get what I expected. At -O3
test():
        mov     edx, DWORD PTR x[rip]
        test    edx, edx
        je      .L1
        mov     eax, DWORD PTR y[rip]
        test    eax, eax
        je      .L1
        jmp     bar()
.L1:
        rep ret


Tracing through the dumps, I see that dom2 is where the gimple starts
diverging. At -O3, dom2 clones the bb that tests z into two copies, and
I guess that enables jump threading and subsequent dse to optimize away the
second (redundant) check for x and y, as also the check for z. At -Os,
dom2 doesn't attemp the bb clone as it thinks it would increase code
size. 

I have two questions.

1. Is the analysis right? Is there anything that can be done to fix this?

2. If nothing can be done to fix this, is there some pass that can
rewire goto <bb 5> in <bb 3> to goto <bb 6>?

Regards
Senthil


.dom2 at Os


test ()
{
  int x.1_1;
  int y.2_2;
  int z.3_3;
  int y.5_4;
  _Bool _8;
  _Bool _9;
  _Bool _10;

  <bb 2> [100.00%]:
  x.1_1 = x;
  if (x.1_1 != 0)
    goto <bb 3>; [50.00%]
  else
    goto <bb 4>; [50.00%]

  <bb 3> [50.00%]:
  y.2_2 = y;
  if (y.2_2 != 0)
    goto <bb 5>; [50.00%]
  else
    goto <bb 4>; [50.00%]

  <bb 4> [75.00%]:
  z.3_3 = z;
  _8 = x.1_1 != 0;
  _9 = z.3_3 != 0;
  _10 = _8 & _9;
  if (_10 != 0)
    goto <bb 5>; [25.60%]
  else
    goto <bb 7>; [74.40%]

  <bb 5> [35.37%]:
  y.5_4 = y;
  if (y.5_4 != 0)
    goto <bb 6>; [48.99%]
  else
    goto <bb 7>; [51.01%]

  <bb 6> [17.33%]:
  bar ();

  <bb 7> [100.00%]:
  return;

}

.dom2 at O3


test ()
{
  int x.1_1;
  int y.2_2;
  int z.3_11;
  _Bool _12;
  _Bool _13;
  _Bool _14;
  int y.5_15;
  int z.3_16;
  _Bool _17;
  _Bool _18;
  _Bool _19;
  int y.5_20;

  <bb 2> [100.00%]:
  x.1_1 = x;
  if (x.1_1 != 0)
    goto <bb 3>; [50.00%]
  else
    goto <bb 5>; [50.00%]

  <bb 3> [50.00%]:
  y.2_2 = y;
  if (y.2_2 != 0)
    goto <bb 8>; [50.00%]
  else
    goto <bb 7>; [50.00%]

  <bb 4> [100.00%]:
  return;

  <bb 5> [50.00%]:
  z.3_11 = z;
  _12 = x.1_1 != 0;
  _13 = z.3_11 != 0;
  _14 = _12 & _13;
  goto <bb 4>; [100.00%]

  <bb 6> [18.04%]:
  y.5_15 = y;
  goto <bb 4>; [100.00%]

  <bb 7> [25.00%]:
  z.3_16 = z;
  _17 = x.1_1 != 0;
  _18 = z.3_16 != 0;
  _19 = _17 & _18;
  if (_19 != 0)
    goto <bb 6>; [72.17%]
  else
    goto <bb 4>; [27.83%]

  <bb 8> [25.00%]:
  y.5_20 = y;
  bar ();
  goto <bb 4>; [100.00%]

}