<html>
    <head>
      <base href="https://llvm.org/bugs/" />
    </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] Failure to vectorize __builtin_sqrt/__builtin_sqrtf"
   href="https://llvm.org/bugs/show_bug.cgi?id=27435">27435</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[X86][SSE] Failure to vectorize __builtin_sqrt/__builtin_sqrtf
          </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>normal
          </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>llvm-bugs@lists.llvm.org
          </td>
        </tr>

        <tr>
          <th>Classification</th>
          <td>Unclassified
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Trunk fails to vectorize:

#include <x86intrin.h>

__m128d sqrtd2(double* v) {
  return _mm_setr_pd(__builtin_sqrt(v[0]), __builtin_sqrt(v[1]));
}

__m128 sqrtf4(float* v) {
  return _mm_setr_ps(__builtin_sqrtf(v[0]), __builtin_sqrtf(v[1]),
__builtin_sqrtf(v[2]), __builtin_sqrtf(v[3]));
}

clang -S -O3 test.c -o -

sqrtd2:
 vsqrtsd (%rdi), %xmm0, %xmm0
 vsqrtsd 8(%rdi), %xmm0, %xmm1
 vunpcklpd %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0],xmm1[0]
 retq

sqrtf4:
 vsqrtss (%rdi), %xmm0, %xmm0
 vsqrtss 4(%rdi), %xmm0, %xmm1
 vsqrtss 8(%rdi), %xmm0, %xmm2
 vsqrtss 12(%rdi), %xmm0, %xmm3
 vinsertps $16, %xmm1, %xmm0, %xmm0 # xmm0 = xmm0[0],xmm1[0],xmm0[2,3]
 vinsertps $32, %xmm2, %xmm0, %xmm0 # xmm0 = xmm0[0,1],xmm2[0],xmm0[3]
 vinsertps $48, %xmm3, %xmm0, %xmm0 # xmm0 = xmm0[0,1,2],xmm3[0]
 retq

Note that this is for __builtin_sqrt not ::sqrt()!

I'd expect:

sqrtd2:
 vsqrtpd (%rdi), %xmm0
 retq

sqrtf4:
 vsqrtps (%rdi), %xmm0
 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>