[Bug tree-optimization/78821] GCC7: Copying whole 32 bits structure field by field not optimised into copying whole 32 bits at once

[ubizjak at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78821

--- Comment #12 from Uroš Bizjak <ubizjak at gmail dot com> ---
(In reply to Uroš Bizjak from comment #8)
> (In reply to rguenther@suse.de from comment #6)
> 
> > > In addition to a merge opportunity, there is a redundant move [*], that results
> > > in redundant operation [**]. The whole function could be just:
> > > 
> > >         movw    %dx, -4(%rdi,%rsi)
> > >         notl    %edx
> > >         movw    %dx, -2(%rdi,%rsi)
> > 
> > or
> > 
> >           xorl    $0xffff0000, %edx
> >           movl    %edx, -4(%rdi,%rsi)
> > 
> > ?
> 
> Yes, even this. It looks that store merging opens many optimization
> opportunities.

Actually, the testcase stores the same word (one inverted) to two different
locations. But following testcase:

--cut here--
struct s { char a; char b; char c; char d; };

void foo (struct s *__restrict a, struct s *__restrict b)
{
  a->a = b->a;
  a->b = b->b;
  a->c = ~b->c;
  a->d = b->d;
}
--cut here--

This testcase can be optimized by inserting xorl mask between load and store,
as suggested above.