<div dir="ltr">To close the loop here for those not CC-ed in the PR, I fixed this in r201104. It was "just" a missing preservation of AA in LCSSA that caused globalmodref-aa to be invalidated in the LTO pipeline. =[[[ 4 days to debug, but wow the fix was easy.<div>
<br></div><div>-Chandler</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Sun, Feb 9, 2014 at 10:28 AM, 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 dir="ltr">Evan, see the PR. Essentially, making LICM *better* causes a very strange degradation in DSE. The thing that is found to be loop invariant *is* loop invariant, and ostensibly should be moved into the exit block. I have not yet uncovered the root cause of why this change would cause us to fail to delete dead stores in some other function...</div>
<div class="HOEnZb"><div class="h5">
<div class="gmail_extra"><br><br><div class="gmail_quote">On Sun, Feb 9, 2014 at 10:19 AM, Evan Cheng <span dir="ltr"><<a href="mailto:evan.cheng@apple.com" target="_blank">evan.cheng@apple.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word">Do you have more detailed information on how this change is causing performance regression?<div>
<br></div><div>Evan</div><div><br><div><div><div><div>On Feb 6, 2014, at 11:19 AM, Gerolf Hoflehner <<a href="mailto:ghoflehner@apple.com" target="_blank">ghoflehner@apple.com</a>> wrote:</div><br></div></div>
<blockquote type="cite"><div><div><div style="word-wrap:break-word">Hi Chandler<div><br></div><div>your commit seems to cause a major regression (>20%) on loop_unroll and other benchmarks as well. This is ( at least) on x86 under -O3 -flto and seems to be due to the loss of LICM. Please take a look.</div>
<div><br></div><div>Cheers</div><div>Gerolf</div><div><br></div><div><div style="margin:0px;font-size:18px;font-family:Menlo">------------------------------------------------------------------------</div><div style="margin:0px;font-size:18px;font-family:Menlo">
r200067 | chandlerc | 2014-01-24 20:07:24 -0800 (Fri, 24 Jan 2014) | 44 lines</div><div style="margin:0px;font-size:18px;font-family:Menlo;min-height:21px"><br></div><div style="margin:0px;font-size:18px;font-family:Menlo">
[LPM] Make LCSSA a utility with a FunctionPass that applies it to all</div><div style="margin:0px;font-size:18px;font-family:Menlo">the loops in a function, and teach LICM to work in the presance of</div><div style="margin:0px;font-size:18px;font-family:Menlo">
LCSSA.</div></div><div><br></div></div></div></div>_______________________________________________<br>llvm-commits mailing list<br><a href="mailto:llvm-commits@cs.uiuc.edu" target="_blank">llvm-commits@cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a><br></blockquote></div><br></div></div><br>_______________________________________________<br>
llvm-commits mailing list<br>
<a href="mailto:llvm-commits@cs.uiuc.edu" target="_blank">llvm-commits@cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a><br>
<br></blockquote></div><br></div>
</div></div></blockquote></div><br></div>