<html>
<head>
<base href="http://llvm.org/bugs/" />
</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 --- - ISel DAG: HandleMergeInputChains is overly conservative"
href="http://llvm.org/bugs/show_bug.cgi?id=19237">19237</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>ISel DAG: HandleMergeInputChains is overly conservative
</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>All
</td>
</tr>
<tr>
<th>Status</th>
<td>NEW
</td>
</tr>
<tr>
<th>Severity</th>
<td>normal
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>Common Code Generator Code
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>qcolombet@apple.com
</td>
</tr>
<tr>
<th>CC</th>
<td>llvmbugs@cs.uiuc.edu
</td>
</tr>
<tr>
<th>Classification</th>
<td>Unclassified
</td>
</tr></table>
<p>
<div>
<pre>Created <span class=""><a href="attachment.cgi?id=12277" name="attach_12277" title="Testcase that show a missed folding because of the overly conservative check">attachment 12277</a> <a href="attachment.cgi?id=12277&action=edit" title="Testcase that show a missed folding because of the overly conservative check">[details]</a></span>
Testcase that show a missed folding because of the overly conservative check
During the select phase of the isel process, SelectionDAGISel performs a check
to see if a load is foldable into another node (for node supporting that
feature of course).
In particular, it checks that folding the load into the related node will not
create a cycle in the DAG.
This check is done by HandleMergeInputChains.
HandleMergeInputChains is not actually checking that a cycle will be created if
something is folded into something else.
In particular, it is not checking for reachability but instead relies on
heuristics to give a quick answer. This answer is conservatively correct:
- No: no cycle will be created.
- Yes: a cycle *may* be created.
I believe this limitation is intended for three reasons:
1. to avoid costly reachability checks.
2. to handle only the rewriting of token factor from the not-yet-matched nodes
to the matched node.
3. everything that has been matched is ready to schedule.
The risk with this approximation is twofold:
- The lowering phase may rely on this folding to happen. As a result "cannot
select" cases may happen like what we fixed in r204631.
- Although this may not impact the performance, the generated code looks bad,
and the code size is impacted.
* STEPS TO REPRODUCE
llc -mattr=+avx2 testcase.ll -o - -O3
* RESULTS
The fallback pattern is used for the broadcast instruction:
movb (%rdi), %al
vmovd %eax, %xmm1
vpbroadcastb %xmm1, %xmm1
Whereas the folding pattern would have match if the cycle detection was
correct:
vpbroadcastb (%rdi), %xmm1</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>