[Bug tree-optimization/66012] New: Sub-optimal 64bit load is generated instead of zero-extension

[ubizjak at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66012

            Bug ID: 66012
           Summary: Sub-optimal 64bit load is generated instead of
                    zero-extension
           Product: gcc
           Version: 6.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: ubizjak at gmail dot com
  Target Milestone: ---

This testcase:

--cut here--
long l[4];

long long test (void)
{
  return (l[0] & (long long) 0xffffffff)
         | ((l[1] & (long long) 0xffffffff) << 32);
}
--cut here--

generates non-optimal 64bit load:

        movl    l(%rip), %edx
>>      movq    l+8(%rip), %rax
        salq    $32, %rax
        orq     %rdx, %rax
        ret

The .optimized dump is already missing masking that would generate
zero-extension on x86_64:

test ()
{
  long int _2;
  long long int _3;
  long int _4;
  long long int _5;
  long long int _6;

  <bb 2>:
  _2 = l[0];
  _3 = _2 & 4294967295;
  _4 = l[1];
  _5 = _4 << 32;
  _6 = _3 | _5;
  return _6;

}