<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 - vpmovmskb+cmp equivalent to vmovmskps+cmp should maybe lower to vmovmskps"
href="https://bugs.llvm.org/show_bug.cgi?id=37087">37087</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>vpmovmskb+cmp equivalent to vmovmskps+cmp should maybe lower to vmovmskps
</td>
</tr>
<tr>
<th>Product</th>
<td>new-bugs
</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>enhancement
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>new bugs
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>gonzalobg88@gmail.com
</td>
</tr>
<tr>
<th>CC</th>
<td>llvm-bugs@lists.llvm.org
</td>
</tr></table>
<p>
<div>
<pre>This snippet of code (see it live: <a href="https://godbolt.org/g/NuiGgc">https://godbolt.org/g/NuiGgc</a>):
Generates:
wrong_instr: # @wrong_instr
vmovaps xmm0, xmmword ptr [rsi]
vcmpeqps xmm0, xmm0, xmmword ptr [rdi]
vpmovmskb eax, xmm0
cmp eax, 65535
sete al
ret
correct_instr: # @correct_instr
vmovaps xmm0, xmmword ptr [rsi]
vcmpeqps xmm0, xmm0, xmmword ptr [rdi]
vmovmskps eax, xmm0
cmp eax, 15
sete al
ret
Note how "wrong_istr" uses, as specified, pmovmskb. AFAICT both snippets are
semantically equivalent.
On broadwell and haswell these intrinsics have identical performance (from
Agner's tables):
PMOVMSKB r,v mops fused: 1 mops unfused: 1 ports: p0 latency: 3 throughput: 1
MOVMSKPS r32,x mops fused: 1 mops unfused: 1 ports: p0 latency: 3 throughput: 1
On skylake MOVMSKPS appears to be slightly better:
PMOVMSKB r,v mops fused: 1 mops unfused: 1 ports: p0 latency: 2-3 throughput:
1
MOVMSKPS r32,x mops fused: 1 mops unfused: 1 ports: p0 latency: 2 throughput:
1
Depending on the CPU, switching from operating on floating-point vectors to
operating on integer vectors might introduce extra latency in which case
movmskps would be preferable in this situation.</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>