<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 - avx512 - codegen regression"
href="https://bugs.llvm.org/show_bug.cgi?id=46899">46899</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>avx512 - codegen regression
</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>Backend: X86
</td>
</tr>
<tr>
<th>Assignee</th>
<td>unassignedbugs@nondot.org
</td>
</tr>
<tr>
<th>Reporter</th>
<td>david.bolvansky@gmail.com
</td>
</tr>
<tr>
<th>CC</th>
<td>craig.topper@gmail.com, llvm-bugs@lists.llvm.org, llvm-dev@redking.me.uk, spatel+llvm@rotateright.com
</td>
</tr></table>
<p>
<div>
<pre>typedef unsigned char uint8_t;
static inline uint8_t x264_clip_uint8( int x )
{
return x&(~63) ? (-x)>>7 : x;
}
void mc_weight( uint8_t *__restrict dst, uint8_t *__restrict src)
{
for( int x = 0; x < 16; x++ )
dst[x] = x264_clip_uint8(src[x]);
}
Clang 9 -Ofast -march=skylake-avx512
mc_weight(unsigned char*, unsigned char*):
vmovdqu xmm0, xmmword ptr [rsi]
vpmovzxbd zmm1, xmm0
vpcmpnleub k1, xmm0, xmmword ptr [rip + .LCPI0_0]
vpxor xmm0, xmm0, xmm0
vpsubd zmm0, zmm0, zmm1
vpsrld zmm1 {k1}, zmm0, 7
vpmovdb xmmword ptr [rdi], zmm1
vzeroupper
ret
Clang trunk -Ofast -march=skylake-avx512
mc_weight(unsigned char*, unsigned char*):
vmovdqu xmm0, xmmword ptr [rsi]
vpbroadcastq xmm1, qword ptr [rsi + 8]
vpmovzxbd ymm1, xmm1
vpcmpltub k1, xmm0, xmmword ptr [rip + .LCPI0_0]
vpxor xmm2, xmm2, xmm2
vpsubd ymm3, ymm2, ymm1
vpsrld ymm3, ymm3, 7
kshiftrw k2, k1, 8
vmovdqa32 ymm3 {k2}, ymm1
vpmovzxbd ymm0, xmm0
vpsubd ymm1, ymm2, ymm0
vpsrld ymm1, ymm1, 7
vpmovdb xmm2, ymm3
vmovdqa32 ymm1 {k1}, ymm0
vpmovdb xmm0, ymm1
vpunpcklqdq xmm0, xmm0, xmm2
vmovdqu xmmword ptr [rdi], xmm0
vzeroupper
ret
Godbolt: <a href="https://godbolt.org/z/P4bWYb">https://godbolt.org/z/P4bWYb</a></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>