<p dir="ltr">Isn't this going to emit a full fence on x86/64? Is storestore insufficient?</p>
<p dir="ltr">Also, is the load side ordered properly already?</p>
<p dir="ltr">sent from my phone</p>
<div class="gmail_quote">On May 13, 2015 3:17 PM, "Thomas Schatzl" <<a href="mailto:thomas.schatzl@oracle.com">thomas.schatzl@oracle.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Bengt,<br>
<br>
On Wed, 2015-05-13 at 20:41 +0200, Bengt Rutisson wrote:<br>
> Hi Jon and Thomas,<br>
><br>
> On 13/05/15 19:48, Thomas Schatzl wrote:<br>
> > Hi,<br>
> ><br>
> > On Wed, 2015-05-13 at 09:42 -0700, Jon Masamitsu wrote:<br>
> >> Bengt,<br>
> >><br>
> >> Change looks good.<br>
><br>
> Thanks for the review, Jon!<br>
><br>
> >><br>
> >> Thomas,<br>
> >><br>
> >> Is the comment added as part of this change understandable to<br>
> >> you? I don't know this code so definitely lack the greater<br>
> >> understanding of what's going on. But if you think the<br>
> >> comment is clear (and since you know the context), it's<br>
> >> fine.<br>
> > it's fine, except maybe for the comment about non-TSO architectures.<br>
> > It just means that the last write publishes the data structure to the<br>
> > public, so everything written before that should be guaranteed to be<br>
> > written first.<br>
> ><br>
> > As for the comment about non-TSO architectures, TSO architectures also<br>
> > need that barrier because the compiler might otherwise reorder the<br>
> > writes which then definitely gets visible in the wrong order.<br>
> ><br>
> > Maybe Bengt can fix that (just remove the "On non-TSO systems," part)<br>
> > before pushing?<br>
><br>
> Sounds good. I'll remove that sentence before I push.<br>
><br>
<br>
It is sufficient to remove just the three words imo :)<br>
<br>
Thanks,<br>
Thomas<br>
<br>
<br>
</blockquote></div>