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

[rguenther at suse dot de]

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

--- Comment #9 from rguenther at suse dot de <rguenther at suse dot de> ---
On Thu, 9 Nov 2017, ubizjak at gmail dot com wrote:

> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78821
> 
> --- Comment #8 from Uroš Bizjak <ubizjak at gmail dot com> ---
> (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.

I believe we should aggressively merge stores as this helps STLF
(as opposed to merging loads which can introduce STLF issues)