<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 --- - Canonicalizing load -> store to use integer type confuses LICM"
href="http://llvm.org/bugs/show_bug.cgi?id=22460">22460</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>Canonicalizing load -> store to use integer type confuses LICM
</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>Windows NT
</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>Scalar Optimizations
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>michael.m.kuperstein@intel.com
</td>
</tr>
<tr>
<th>CC</th>
<td>chandlerc@gmail.com, llvmbugs@cs.uiuc.edu
</td>
</tr>
<tr>
<th>Classification</th>
<td>Unclassified
</td>
</tr></table>
<p>
<div>
<pre>The canonicalization committed in r226781 creates a pattern that confuses LICM.
The minimal reproducer I managed to come up with is below:
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-windows-msvc"
@in = internal unnamed_addr global i32* null, align 8
@out = internal unnamed_addr global i32* null, align 8
define i64 @bar(i32 %N) {
entry:
br label %do.body
do.body:
%i.0 = phi i32 [ 0, %entry ], [ %inc, %l2 ]
%total = phi i64 [ 0, %entry ], [ %next, %l2]
%c = icmp eq i32 %N, 6
br i1 %c, label %l1, label %l2
l1:
%v = load i32** @in, align 8
store i32* %v, i32** @out, align 8
br label %l2
l2:
%inval = load i32** @in, align 8
%int = ptrtoint i32* %inval to i64
%next = add i64 %total, %int
%inc = add nsw i32 %i.0, 1
%cmp = icmp slt i32 %inc, %N
br i1 %cmp, label %do.body, label %do.end
do.end:
ret i64 %total
}
Running opt -basicaa -gvn -licm produces this:
define i64 @bar(i32 %N) {
entry:
%c = icmp eq i32 %N, 6
%v = load i32** @in, align 8
%inval.pre = load i32** @in, align 8
br label %do.body
do.body: ; preds = %l2, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %l2 ]
%total = phi i64 [ 0, %entry ], [ %next, %l2 ]
br i1 %c, label %l1, label %do.body.l2_crit_edge
do.body.l2_crit_edge: ; preds = %do.body
br label %l2
l1: ; preds = %do.body
store i32* %v, i32** @out, align 8
br label %l2
l2: ; preds =
%do.body.l2_crit_edge, %l1
%inval = phi i32* [ %inval.pre, %do.body.l2_crit_edge ], [ %v, %l1 ]
%int = ptrtoint i32* %inval to i64
%next = add i64 %total, %int
%inc = add nsw i32 %i.0, 1
%cmp = icmp slt i32 %inc, %N
br i1 %cmp, label %do.body, label %do.end
do.end: ; preds = %l2
%total.lcssa = phi i64 [ %total, %l2 ]
ret i64 %total.lcssa
}
The load has been hoisted above the loop.
Adding instcombine before gvn gives us:
define i64 @bar(i32 %N) {
entry:
%c = icmp eq i32 %N, 6
%inval.pre = load i32** @in, align 8
br label %do.body
do.body: ; preds = %l2, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %l2 ]
%total = phi i64 [ 0, %entry ], [ %next, %l2 ]
br i1 %c, label %l1, label %do.body.l2_crit_edge
do.body.l2_crit_edge: ; preds = %do.body
br label %l2
l1: ; preds = %do.body
%v1 = load i64* bitcast (i32** @in to i64*), align 8
store i64 %v1, i64* bitcast (i32** @out to i64*), align 8
%0 = inttoptr i64 %v1 to i32*
br label %l2
l2: ; preds =
%do.body.l2_crit_edge, %l1
%inval = phi i32* [ %inval.pre, %do.body.l2_crit_edge ], [ %0, %l1 ]
%int = ptrtoint i32* %inval to i64
%next = add i64 %total, %int
%inc = add nsw i32 %i.0, 1
%cmp = icmp slt i32 %inc, %N
br i1 %cmp, label %do.body, label %do.end
do.end: ; preds = %l2
%total.lcssa = phi i64 [ %total, %l2 ]
ret i64 %total.lcssa
}</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>