<div dir="ltr">Hi Dennis,<div><br></div><div>While Clang's code is significantly larger,  that is probably on purpose: Clang has vectorized the goto-loop.</div><div><br></div><div>To validate whether that was correct and a good idea, plug both results into a benchmark and look at the actual performance data.</div><div><br></div><div>Philip</div></div><div class="gmail_extra"><br><div class="gmail_quote">2016-12-05 12:32 GMT+01:00 Dennis Luehring via llvm-dev <span dir="ltr"><<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">FYI<br>
<br>
found this example while reading:<br>
<a href="https://github.com/jameysharp/corrode/issues/30#issuecomment-231969365" rel="noreferrer" target="_blank">https://github.com/jameysharp/<wbr>corrode/issues/30#issuecomment<wbr>-231969365</a><br>
and compared it with current gcc 6.2, clang 3.9<br>
<br>
gcc 6.2 result is quite small - clang 3.9 produces much much more code<br>
for this example<br>
<a href="https://godbolt.org/g/uWxr8F" rel="noreferrer" target="_blank">https://godbolt.org/g/uWxr8F</a><br>
<br>
is that a missing optimization opportunity or just wrong behavior of the<br>
optimizer?<br>
<br>
______________________________<wbr>_________________<br>
LLVM Developers mailing list<br>
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" rel="noreferrer" target="_blank">http://lists.llvm.org/cgi-bin/<wbr>mailman/listinfo/llvm-dev</a><br>
</blockquote></div><br></div>