<p dir="ltr">I strongly suspect pointer union and pointer int pair style classes are the source of these... But perhaps I'm wrong<br>
</p>
<div class="gmail_quote">On Nov 26, 2014 9:29 AM, "Michael Zolotukhin" <<a href="mailto:mzolotukhin@apple.com">mzolotukhin@apple.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word"><div>John,</div><div><br></div><div>That’s a great post and really interesting data, thank you!</div><br><div><blockquote type="cite"><div>On Nov 25, 2014, at 9:58 AM, Reid Kleckner <<a href="mailto:rnk@google.com" target="_blank">rnk@google.com</a>> wrote:</div><br><div><div dir="ltr">Cool! Looks like we do lots of provably unnecessary alignment checks. :)</div></div></blockquote>Indeed, but where do these checks come from? As far as I know, right now vectorizer doesn’t generate them, and who else could do that?</div><div><br></div><div>Michael</div><div><br><blockquote type="cite"><div><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Nov 25, 2014 at 9:03 AM, John Regehr <span dir="ltr"><<a href="mailto:regehr@cs.utah.edu" target="_blank">regehr@cs.utah.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Actually, let me save you some time by pointing out the thing that is perhaps immediately useful about our recent work, which is the fact that Souper now supports "optimization profiling".<br>
<br>
If you build an LLVM using Souper and then use that LLVM to build SPEC CPU 2006, here are optimizations ranked by dynamic profile count:<br>
<br>
<a href="http://blog.regehr.org/extra_files/souper-nov-14/bydprofile.html" target="_blank">http://blog.regehr.org/extra_<u></u>files/souper-nov-14/<u></u>bydprofile.html</a><br>
<br>
In other words, if you implement optimizations near the top of this list, you would be likely to make LLVM compile SPEC CPU 2006 in less time.<br>
<br>
Here are the optimizations sorted by static profile count:<br>
<br>
<a href="http://blog.regehr.org/extra_files/souper-nov-14/bysprofile.html" target="_blank">http://blog.regehr.org/extra_<u></u>files/souper-nov-14/<u></u>bysprofile.html</a><br>
<br>
Implementing the highly ranked ones would be likely to make the clang binary smaller.<br>
<br>
Finally here are the optimizations sorted by size; this is handy because the higher-ranked ones are generally easier to understand:<br>
<br>
<a href="http://blog.regehr.org/extra_files/souper-nov-14/bysize.html" target="_blank">http://blog.regehr.org/extra_<u></u>files/souper-nov-14/bysize.<u></u>html</a><div><div><br>
<br>
John<br>
______________________________<u></u>_________________<br>
LLVM Developers mailing list<br>
<a href="mailto:LLVMdev@cs.uiuc.edu" target="_blank">LLVMdev@cs.uiuc.edu</a> <a href="http://llvm.cs.uiuc.edu/" target="_blank">http://llvm.cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev" target="_blank">http://lists.cs.uiuc.edu/<u></u>mailman/listinfo/llvmdev</a><br>
</div></div></blockquote></div><br></div>
_______________________________________________<br>LLVM Developers mailing list<br><a href="mailto:LLVMdev@cs.uiuc.edu" target="_blank">LLVMdev@cs.uiuc.edu</a> <a href="http://llvm.cs.uiuc.edu" target="_blank">http://llvm.cs.uiuc.edu</a><br><a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev</a><br></div></blockquote></div><br></div><br>_______________________________________________<br>
LLVM Developers mailing list<br>
<a href="mailto:LLVMdev@cs.uiuc.edu">LLVMdev@cs.uiuc.edu</a> <a href="http://llvm.cs.uiuc.edu" target="_blank">http://llvm.cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev</a><br>
<br></blockquote></div>