[Bug tree-optimization/63599] New: "wrong" branch optimization with Ofast in a loop

[vincenzo.innocente at cern dot ch]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63599

            Bug ID: 63599
           Summary: "wrong" branch optimization with Ofast in a loop
           Product: gcc
           Version: 5.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: vincenzo.innocente at cern dot ch

given this code

#include <x86intrin.h>

typedef float __attribute__( ( vector_size( 16 ) ) ) float32x4_t;

inline
float32x4_t atan(float32x4_t t) {
  constexpr float PIO4F = 0.7853981633974483096f;
  float32x4_t high = t > 0.4142135623730950f;
  auto z = t;
  float32x4_t ret={0.f,0.f,0.f,0.f};
    // if all low no need to blend
  if ( _mm_movemask_ps(high) != 0) {
    z   = ( t > 0.4142135623730950f ) ? (t-1.0f)/(t+1.0f) : t;
    ret = ( t > 0.4142135623730950f ) ? ret+PIO4F : ret;
  }
  /* polynomial removed */
  return  ret += z;
}


float32x4_t doAtan(float32x4_t z) { return atan(z);}

float32x4_t va[1024];
float32x4_t vb[1024];

void computeV() {
  for (int i=0;i!=1024;++i)
    vb[i]=atan(va[i]);
}


compiled with -Ofast
c++ -S -std=c++1y -Ofast bugmvmk.cc -march=nehalem; cat bugmvmk.s
produces the following code where the "movmskps    %xmm8, %edx"
does not protect the code in the if block...

__Z8computeVv:
LFB2512:
    movaps    LC0(%rip), %xmm4
    xorl    %eax, %eax
    movaps    LC1(%rip), %xmm7
    leaq    _va(%rip), %rcx
    movaps    LC2(%rip), %xmm6
    movaps    LC3(%rip), %xmm5
    .align 4,0x90
L10:
    movaps    (%rcx,%rax), %xmm2
    movaps    %xmm4, %xmm8
    movaps    %xmm2, %xmm3
    cmpltps    %xmm2, %xmm8
    movaps    %xmm2, %xmm1
    addps    %xmm6, %xmm3
    addps    %xmm7, %xmm1
    movmskps    %xmm8, %edx
    andps    %xmm5, %xmm8
    rcpps    %xmm3, %xmm0
    mulps    %xmm0, %xmm3
    mulps    %xmm0, %xmm3
    addps    %xmm0, %xmm0
    subps    %xmm3, %xmm0
    mulps    %xmm0, %xmm1
    movaps    %xmm2, %xmm0
    cmpleps    %xmm4, %xmm0
    blendvps    %xmm0, %xmm2, %xmm1
    pxor    %xmm0, %xmm0
    testl    %edx, %edx
    je    L7
    movaps    %xmm8, %xmm0
L7:
    testl    %edx, %edx
    je    L9
    movaps    %xmm1, %xmm2
L9:
    addps    %xmm0, %xmm2
    leaq    _vb(%rip), %rdx
    movaps    %xmm2, (%rdx,%rax)
    addq    $16, %rax
    cmpq    $16384, %rax
    jne    L10
    ret

while with O2 is ok
__Z8computeVv:
LFB2512:
    movaps    LC0(%rip), %xmm4
    xorl    %eax, %eax
    movaps    LC1(%rip), %xmm7
    leaq    _va(%rip), %rsi
    movaps    LC2(%rip), %xmm6
    leaq    _vb(%rip), %rcx
    movaps    LC3(%rip), %xmm5
    .align 4,0x90
L7:
    movaps    (%rsi,%rax), %xmm1
    movaps    %xmm4, %xmm0
    pxor    %xmm2, %xmm2
    cmpltps    %xmm1, %xmm0
    movmskps    %xmm0, %edx
    testl    %edx, %edx
    je    L6
    movaps    %xmm1, %xmm3
    movaps    %xmm1, %xmm2
    addps    %xmm6, %xmm2
    addps    %xmm7, %xmm3
    divps    %xmm2, %xmm3
    movaps    %xmm0, %xmm2
    andps    %xmm5, %xmm2
    blendvps    %xmm0, %xmm3, %xmm1
L6:
    addps    %xmm2, %xmm1
    movaps    %xmm1, (%rcx,%rax)
    addq    $16, %rax
    cmpq    $16384, %rax
    jne    L7
    ret

note that the function not in the loop (doAtan) is ok with both O2 and Ofast