<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] Improve HADD/HSUB shuffle combining"
   href="https://bugs.llvm.org/show_bug.cgi?id=41813">41813</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[X86] Improve HADD/HSUB shuffle combining
          </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>craig.topper@gmail.com, llvm-bugs@lists.llvm.org, llvm-dev@redking.me.uk, spatel+llvm@rotateright.com
          </td>
        </tr></table>
      <p>
        <div>
        <pre>As noted in <a href="https://reviews.llvm.org/D61308">https://reviews.llvm.org/D61308</a>, we should try harder to combine
shuffles on either side of a HADD/HSUB instruction - possibly removing it in
the process. This may be true for PACK in some cases as well.

define <4 x float> @PR22377(<4 x float> %a, <4 x float> %b) {
; AVX-LABEL: PR22377:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vhaddps %xmm0, %xmm0, %xmm1
; AVX-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,1]
; AVX-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX-NEXT:    retq
entry:
  %s1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 1, i32
3, i32 1, i32 3>
  %s2 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 0, i32
2, i32 0, i32 2>
  %r2 = fadd <4 x float> %s1, %s2
  %s3 = shufflevector <4 x float> %s2, <4 x float> %r2, <4 x i32> <i32 0, i32
4, i32 1, i32 5>
  ret <4 x float> %s3
}

Under some circumstances we could even shuffle in +0.0f values into some lanes
so the HADD becomes inert.</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>