<html>
    <head>
      <base href="http://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] Failure to use HADDPS for partial register result"
   href="http://bugs.llvm.org/show_bug.cgi?id=32433">32433</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[X86] Failure to use HADDPS for partial register result
          </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>llvm-bugs@lists.llvm.org, spatel+llvm@rotateright.com
          </td>
        </tr></table>
      <p>
        <div>
        <pre>While the 256-bit horizontal pair sums work fine (both on btver2 and btver1),
the 128-bit version completely fails:

#include <x86intrin.h>
void sum_pairs_128(__m128 f, float *p) {
  p[0] = f[0] + f[1];
  p[1] = f[2] + f[3];
}
void sum_pairs_256(__m256 f, float *p) {
  p[0] = f[0] + f[1];
  p[1] = f[2] + f[3];
  p[2] = f[4] + f[5];
  p[3] = f[6] + f[7];
}

clang -O3 -march=btver2

sum_pairs_128(float __vector(4), float*):
        vmovshdup       %xmm0, %xmm1    # xmm1 = xmm0[1,1,3,3]
        vaddss  %xmm1, %xmm0, %xmm1
        vmovss  %xmm1, (%rdi)
        vpermilpd       $1, %xmm0, %xmm1 # xmm1 = xmm0[1,0]
        vpermilps       $231, %xmm0, %xmm0 # xmm0 = xmm0[3,1,2,3]
        vaddss  %xmm0, %xmm1, %xmm0
        vmovss  %xmm0, 4(%rdi)
        retq

sum_pairs_256(float __vector(8), float*):
        vextractf128    $1, %ymm0, %xmm1
        vhaddps %xmm1, %xmm0, %xmm0
        vmovups %xmm0, (%rdi)
        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>