<html>
<head>
<base href="https://bugs.llvm.org/">
</head>
<body><table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Bug ID</th>
<td><a class="bz_bug_link
bz_status_NEW "
title="NEW - LegacyDivergenceAnalysis: sync dependence misses some divergent uses outside a loop"
href="https://bugs.llvm.org/show_bug.cgi?id=42741">42741</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>LegacyDivergenceAnalysis: sync dependence misses some divergent uses outside a loop
</td>
</tr>
<tr>
<th>Product</th>
<td>libraries
</td>
</tr>
<tr>
<th>Version</th>
<td>trunk
</td>
</tr>
<tr>
<th>Hardware</th>
<td>PC
</td>
</tr>
<tr>
<th>OS</th>
<td>Linux
</td>
</tr>
<tr>
<th>Status</th>
<td>NEW
</td>
</tr>
<tr>
<th>Severity</th>
<td>enhancement
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>Global Analyses
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>jay.foad@gmail.com
</td>
</tr>
<tr>
<th>CC</th>
<td>llvm-bugs@lists.llvm.org
</td>
</tr></table>
<p>
<div>
<pre>Created <span class=""><a href="attachment.cgi?id=22281" name="attach_22281" title="test case">attachment 22281</a> <a href="attachment.cgi?id=22281&action=edit" title="test case">[details]</a></span>
test case
See the attached test case,
test/Analysis/LegacyDivergenceAnalysis/AMDGPU/syncbug.ll.
%tmp7 is divergent because it's sync-dependent on the divergent loop exit
condition %tmp5, but LegacyDivergenceAnalysis does not mark it as divergent.
Quoting from LegacyDivergenceAnalysis.cpp:
// Propagation rule 2: if a value defined in a loop is used outside, the user
// is sync dependent on the condition of the loop exits that dominate the
// user. For example,
OK.
// The algorithm used here handles both natural and unstructured loops.
Given
// a branch TI, we first compute its influence region, the union of all
simple
// paths from TI to its immediate post dominator (IPostDom). Then, we search
// for all the values defined in the influence region but used outside. All
// these users are sync dependent on TI.
This algorithm doesn't appear to work. The influence region includes all blocks
from bb2 to bb8, so %tmp7 is never marked divergent by this algorithm because
it is not outside the influence region.
This might be related to 37185.</pre>
</div>
</p>
<hr>
<span>You are receiving this mail because:</span>
<ul>
<li>You are on the CC list for the bug.</li>
</ul>
</body>
</html>