<div dir="ltr"><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Jan 27, 2014 at 1:41 PM, Chandler Carruth <span dir="ltr"><<a href="mailto:chandlerc@gmail.com" target="_blank">chandlerc@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 class="im"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="overflow:hidden">
---- Block Freqs ----<br>
entry = 1.0<br>
entry -> if.else = 0.375<br>
entry -> if.then = 0.625<br>
if.then = 0.625<br>
if.then -> if.end22 = 0.625<br>
if.else = 0.375<br>
if.else -> for.cond.preheader = 0.1406<br>
if.else -> if.end22 = 0.23437<br>
for.cond.preheader = 0.1406<br>
for.cond.preheader -> <a href="http://for.body.lr.ph" target="_blank">for.body.lr.ph</a> = 0.08789<br>
for.cond.preheader -> for.end = 0.05273<br>
<a href="http://for.body.lr.ph" target="_blank">for.body.lr.ph</a> = 0.08789 ### Preheader in question<br>
<a href="http://for.body.lr.ph" target="_blank">for.body.lr.ph</a> -> for.body = 0.08789<br>
for.body = 2.8125 ### Loop in question</div></blockquote><div><br></div></div><div>Oh goodness. These static frequencies don't really make any sense at all. But they're also not wrong at all. ARRRRG!</div>
</blockquote></div><br>Oh my, its worse than that. I've not thought about the block frequencies this way before, but it appears that with the current model, inlining a function call guarded by a branch has the perplexing property of making any blocks within the function colder relative to their function's entry block.</div>
</div>