<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 - x86: shld peephole missed with masked shift-counts"
href="https://bugs.llvm.org/show_bug.cgi?id=34641">34641</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>x86: shld peephole missed with masked shift-counts
</td>
</tr>
<tr>
<th>Product</th>
<td>clang
</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>LLVM Codegen
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedclangbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>peter@cordes.ca
</td>
</tr>
<tr>
<th>CC</th>
<td>llvm-bugs@lists.llvm.org
</td>
</tr></table>
<p>
<div>
<pre>unsigned shld_safe(unsigned a, unsigned b, unsigned n){
//n=13;
a <<= n&31;
b >>= (32-n)&31; // (32-n)&31
return a|b;
}
<a href="https://godbolt.org/g/MxuAht">https://godbolt.org/g/MxuAht</a>
clang 6.0.0 (trunk 313348) -march=skylake -O3
shlx ecx, edi, edx
neg edx # at least 32&31 optimized to 0
shrx eax, esi, edx
or eax, ecx
ret
It takes even more instructions without BMI2, of course.
Without the `&31`, this optimizes to SHLD, so the peephole needs to learn that
SHLD masks the shift-count with &31 for 32-bit or smaller operand-size. (Or
with &63 for 64-bit operand-size). <a href="http://felixcloutier.com/x86/SHLD.html">http://felixcloutier.com/x86/SHLD.html</a>.
mov ecx, edx
shld edi, esi, cl
mov eax, edi
ret
I didn't test with SHRD, but I assume it's the same.
BTW, this peephole activates even with `-march=znver1` or other AMD
architectures, where shld r,r,cl is 7 uops... SHLD may still be worth it
without BMI2 for the variable-count case, but probably not when BMI2 is
available and tuning for AMD.
SHLD is probably still a good idea for tune=generic, especially with
variable-count; it's great on Intel, and only slightly worse than the amount of
instructions it takes to work around it on AMD, unless VectorPath instructions
are really bad in the front-end.)</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>