<div dir="ltr">Yes, I think you're right, this looks like a bug.</div><div class="gmail_extra"><br><div class="gmail_quote">On Thu, Jul 7, 2016 at 1:43 AM, Jordy Potman <span dir="ltr"><<a href="mailto:jordy.potman.lists@gmail.com" target="_blank">jordy.potman.lists@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hi,<div><br></div><div>I know this functionality wasn't changed in this commit but I noticed that the arguments to the getScalarizationOverhead call appear to be inconsistent with the comment in the following piece of code:<br><div class="gmail_extra"><br><div class="gmail_quote"><span class=""><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex">@@ -480,8 +497,7 @@ public:<br>
           Opcode, ValTy->getScalarType(), CondTy);<br>
<br>
       // Return the cost of multiple scalar invocation plus the cost of<br>
-      // inserting<br>
-      // and extracting the values.<br>
+      // inserting and extracting the values.<br>
       return getScalarizationOverhead(ValTy, true, false) + Num * Cost;<br>
     }<br></blockquote><div> </div></span><div>Shouldn't the getScalarizationOverhead call be:</div><div><br></div><div>getScalarizationOverhead(ValTy, true, true)<br></div><div><br></div><div>?</div><span class="HOEnZb"><font color="#888888"><div><br></div><div>Jordy</div></font></span></div></div></div></div>
</blockquote></div><br></div>