<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 - wrong code with -disable-licm-promotion -enable-loop-distribute"
   href="https://bugs.llvm.org/show_bug.cgi?id=38699">38699</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>wrong code with -disable-licm-promotion -enable-loop-distribute
          </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>Loop Optimizer
          </td>
        </tr>

        <tr>
          <th>Assignee</th>
          <td>unassignedbugs@nondot.org
          </td>
        </tr>

        <tr>
          <th>Reporter</th>
          <td>paulsson@linux.vnet.ibm.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Created <span class=""><a href="attachment.cgi?id=20767" name="attach_20767" title="reduced testcase">attachment 20767</a> <a href="attachment.cgi?id=20767&action=edit" title="reduced testcase">[details]</a></span>
reduced testcase

Thanks to (for the) nice output of opt-viewer with the optimization remarks, I
tried the loop-distribute pass on a benchmark and got a huge speedup as
vectorization occurred (30%)  :-)

I then enabled this in csmith testing and found a wrong code bug which I
reduced to:

a, b, c, d, e;
main() {
  for (; b > -8; --b) {
    c = 0;
    for (; c != -14; c--) {
      if (b)
        break;
      --d;
    }
  }
  for (; e < 5; e++)
    a = c;
  printf("checksum = %X\n", a);
}

gcc -O1 -march=z10 -o a.out -w
gcc -O0 -march=z13 -o a.out -w
gcc -O1 -march=z13 -o a.out -w
clang -O0 -march=z10 -o a.out -w
clang -O0 -march=z13 -o a.out -w
clang -O3 -march=z10 -o a.out -w
clang -O3 -march=z13 -o a.out -w
clang -O3 -march=z13 -o a.out -w -mllvm -disable-licm-promotion -mllvm
-enable-loop-distribute

checksum = 0
checksum = 0
checksum = 0
checksum = 0
checksum = 0
checksum = 0
checksum = 0
checksum = 0
checksum = FFFFFFF2</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>