<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][SSE] Improve general memcmp support"
href="https://bugs.llvm.org/show_bug.cgi?id=33329">33329</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>[X86][SSE] Improve general memcmp support
</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>enhancement
</td>
</tr>
<tr>
<th>Priority</th>
<td>P
</td>
</tr>
<tr>
<th>Component</th>
<td>Backend: X86
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>llvm-dev@redking.me.uk
</td>
</tr>
<tr>
<th>CC</th>
<td>andrea.dibiagio@gmail.com, filcab@gmail.com, llvm-bugs@lists.llvm.org, spatel+llvm@rotateright.com
</td>
</tr></table>
<p>
<div>
<pre>Currently memcmp lowers to a libcall:
int cmp16(const char *a, const char *b) {
return __builtin_memcmp(a, b, 16);
}
cmp16(char const*, char const*):
movl $16, %edx
jmp memcmp
Which depending on the lib implementation/shim calls can be quite slow. A
possible alternative would be to vectorize this, using a more complex version
of what we do for 'equality' memcmp (<a class="bz_bug_link
bz_status_NEW "
title="NEW - [X86][SSE] Improve equality memcmp support"
href="show_bug.cgi?id=33325">Bug #33325</a>):
#include <x86intrin.h>
int cmp16(const char *a, const char *b) {
__m128i va = _mm_loadu_si128((const __m128i*)a);
__m128i vb = _mm_loadu_si128((const __m128i*)b);
unsigned eq = _mm_movemask_epi8(_mm_cmpeq_epi8(va, vb));
__m128i kSign = _mm_set1_epi8(0x80);
va = _mm_xor_si128(va, kSign);
vb = _mm_xor_si128(vb, kSign);
unsigned gt = _mm_movemask_epi8(_mm_cmpgt_epi8(va, vb));
unsigned lt = _mm_movemask_epi8(_mm_cmplt_epi8(va, vb));
unsigned cgt = __tzcnt_u32(gt);
unsigned clt = __tzcnt_u32(lt);
return ((eq == 0xFFFF) ? 0 : (clt - cgt));
}
clang -g0 -O3 -march=btver2
cmp16(char const*, char const*):
vmovdqu (%rdi), %xmm0
vmovdqu (%rsi), %xmm1
vpcmpeqb %xmm1, %xmm0, %xmm2
vpmovmskb %xmm2, %ecx
vmovdqa .LCPI0_0(%rip), %xmm2 # xmm2 =
[9259542123273814144,9259542123273814144]
vpxor %xmm2, %xmm0, %xmm0
vpxor %xmm2, %xmm1, %xmm1
vpcmpgtb %xmm1, %xmm0, %xmm2
vpcmpgtb %xmm0, %xmm1, %xmm0
vpmovmskb %xmm2, %eax
vpmovmskb %xmm0, %edx
tzcntl %eax, %eax
tzcntl %edx, %edx
subl %eax, %edx
xorl %eax, %eax
cmpl $65535, %ecx # imm = 0xFFFF
cmovnel %edx, %eax
retq</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>