<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 - vector select optimization failures?"
href="https://bugs.llvm.org/show_bug.cgi?id=41429">41429</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>vector select optimization failures?
</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>Scalar Optimizations
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>lebedev.ri@gmail.com
</td>
</tr>
<tr>
<th>CC</th>
<td>llvm-bugs@lists.llvm.org
</td>
</tr></table>
<p>
<div>
<pre>From IRC:
<a href="https://godbolt.org/z/NgGuw9">https://godbolt.org/z/NgGuw9</a>
#include <immintrin.h>
#include <inttypes.h>
void test_restrict(__m256i * __restrict__ dest, const __m256i * __restrict__ a)
{
(*dest)[2] = (*a)[2];
(*dest)[3] = (*a)[3];
}
Currently results in:
define dso_local void @example2(<4 x i64>* noalias nocapture, <4 x i64>*
noalias nocapture readonly) local_unnamed_addr #0 {
%3 = load <4 x i64>, <4 x i64>* %1, align 32, !tbaa !2
%4 = load <4 x i64>, <4 x i64>* %0, align 32
%5 = shufflevector <4 x i64> %4, <4 x i64> %3, <4 x i32> <i32 0, i32 1, i32
6, i32 undef>
%6 = shufflevector <4 x i64> %5, <4 x i64> %3, <4 x i32> <i32 0, i32 1, i32
2, i32 7>
store <4 x i64> %6, <4 x i64>* %0, align 32
ret void
}
Since these are simple identity shuffles), can we combine this into a single
shuffle?
I'm guessing it is the `undef` that is the problem?
; Function Attrs: norecurse nounwind uwtable
define dso_local void @test_restrict(<4 x i64>* noalias nocapture, <4 x i64>*
noalias nocapture readonly) local_unnamed_addr #0 {
%3 = load <4 x i64>, <4 x i64>* %1, align 32, !tbaa !2
%4 = load <4 x i64>, <4 x i64>* %0, align 32
%5 = shufflevector <4 x i64> %4, <4 x i64> %3, <4 x i32> <i32 0, i32 1, i32
6, i32 7>
store <4 x i64> %5, <4 x i64>* %0, align 32
ret void
}
<a href="https://godbolt.org/z/NgGuw9">https://godbolt.org/z/NgGuw9</a>
The final x86 asm is identical.</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>