[Bug tree-optimization/25413] wrong alignment or incorrect address computation in vectorized code on Pentium 4 SSE

[reichelt at gcc dot gnu dot org]

------- Comment #5 from reichelt at gcc dot gnu dot org  2007-04-02 21:52 
-------
Any news on this one?
The bug makes tree vectorization on pentium 4 totally useless. :-(

Btw, here's a smaller code snippet for testing. Just compile it with
  gcc -O -msse2 -ftree-vectorize
on a pentium 4 and see the resulting executable segfault:

================================
struct
{
  char c;
  double d[2];
} a;

int main()
{
  int i;
  for ( i=0; i<2; ++i )
    a.d[i]=0;
  return 0;
}
================================


-- 

reichelt at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |reichelt at gcc dot gnu dot
                   |                            |org
           Keywords|                            |monitored


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=25413