[Bug rtl-optimization/40924] [4.4 Regression] miscompiles with -03 (seemingly related to attribute may_alias)

[jakub at gcc dot gnu dot org]

------- Comment #4 from jakub at gcc dot gnu dot org  2009-08-04 10:27 -------
On the 4.4 branch/x86_64-linux, I can reproduce even with -O1 on:
extern "C" void abort (void);

#define _MAY_ALIAS __attribute__((__may_alias__))

typedef struct { float v[2]; } _float_v;
typedef struct { int v[2]; } _int_v;

typedef unsigned int _UInt _MAY_ALIAS;
typedef signed int _Int _MAY_ALIAS;
typedef float _Float _MAY_ALIAS;

static inline unsigned short less_than (_int_v a, _int_v b)
{
  unsigned short r = 0;
  const _UInt *p1 = (const _UInt *) &a;
  const _UInt *p2 = (const _UInt *) &b;
  for (int i=0; i < 2; i++)
    if (p1[i] < p2[i]) r |= (1 << i);
  return r;
}

static inline _int_v multiply (_int_v b, _int_v c)
{
  _int_v r;
  _Int *p3 = (_Int *) &c;
  for (int i=0; i < 2; i++)
    r.v[i] = (int) (b.v[i] * p3[i] & 0xFFFFFFFF);
  return r;
}

static inline _float_v gather (_int_v indexes, const void *baseAddr)
{
  _float_v r;

  _Int *idx = (_Int *) &indexes;
  _Float *src = (_Float *) baseAddr;
  for (int i=0; i < 2; i++)
    r.v[i] = *(src + idx[i]);
  return r;
}

static inline _int_v add (const _int_v &b, const _int_v &c)
{
  _int_v result;
  _Int *r = (_Int *) &result;

  for (int i=0; i < 2; i++)
    r[i] = b.v[i] + c.v[i];
  return result;
}

struct uint_v
{
  _int_v data;
  inline uint_v () { data.v[0] = 0; data.v[1] = 1; }
  inline uint_v (unsigned int a) {
    for (int i=0; i < 2; i++)
      *(_UInt *) &data.v[i] = a;
  }
  inline uint_v (_int_v x) : data (x) {}
  inline uint_v operator* (const uint_v &x) const { return multiply (data,
x.data); }
  inline uint_v operator+ (const uint_v &x) const { return uint_v (add (data,
x.data)); }
  inline unsigned short operator< (const uint_v &x) const { return less_than
(data, x.data); }
};

struct float_v
{
  _float_v data;
  explicit inline float_v (const uint_v &x) {
    _UInt *p2 = (_UInt *) &x.data;
    for (int i=0; i < 2; i++)
      data.v[i] = p2[i];
  }
  inline float_v (const float *array, const uint_v &indexes) {
    const uint_v &offsets = indexes * uint_v (1);
    data = gather (offsets.data, array);
  }
  __attribute__((noinline)) unsigned short operator== (const float_v &x) const
{
    unsigned short r = 0;
    for (int i=0; i < 2; i++)
      if (data.v[i] == x.data.v[i]) r |= (1 << i);
    return r;
  }
};

int main ()
{
  const float array[2] = { 2, 3 };
  unsigned short mask;
  for (uint_v i; (mask = (i < 2)) == 3; i = i + 2) {
    const float_v ii (i + 2);
    asm volatile ("# Barrier 1 %0 %1 %2" : : "r" (&ii), "r" (&i), "r" (array) :
"memory");
    float_v a (array, i);
    asm volatile ("# Barrier 2 %0 %1 %2 %3" : : "r" (&ii), "r" (&i), "r"
(array), "r" (&a) : "memory");
    if ((a == ii) != 3)
      abort();
  }
  return 0;
}

Apparently there is some stack slot sharing and RTL DSE decides to remove a
store to stack related address as dead when that memory is later on read using
a non-%rsp related read.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=40924