<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 --- - AVX-512: Missed opportunity of folding masked-loads"
   href="https://llvm.org/bugs/show_bug.cgi?id=31657">31657</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>AVX-512: Missed opportunity of folding masked-loads
          </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>zvi.rackover@intel.com
          </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>For the following case:

define <16 x float> @masked_loads_add(<16 x float>* %pA, <16 x float>* %pB, <16
x float>* %pC, i16 %D) {
   %Mask = bitcast i16 %D to <16 x i1>
   %wide.masked.load = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16
x float>* %pA, i32 4, <16 x i1> %Mask, <16 x float> undef)
   %wide.masked.load11 = call <16 x float>
@llvm.masked.load.v16f32.p0v16f32(<16 x float>* %pB, i32 4, <16 x i1> %Mask,
<16 x float> undef)
   %Add = fadd <16 x float> %wide.masked.load, %wide.masked.load11
   ret <16 x float> %Add
}

llc -mcpu=skylake-avx512 generates:
        kmovw   %ecx, %k1
        vmovups (%rdi), %zmm0 {%k1} {z}
        vmovups (%rsi), %zmm1 {%k1} {z}
        vaddps  %zmm1, %zmm0, %zmm0
        retq

We could do better if we folded the masked-load into the add:
        kmovw   %ecx, %k1
        vmovaps (%rdi), %zmm0 {%k1} {z}
        vaddps  (%rsi), %zmm0, %zmm0 {%k1} {z}
        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>