<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 - [ppc] crandc of two cmps is much slower than two cmp/br"
   href="https://bugs.llvm.org/show_bug.cgi?id=32320">32320</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[ppc] crandc of two cmps is much slower than two cmp/br
          </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>All
          </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: PowerPC
          </td>
        </tr>

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

        <tr>
          <th>Reporter</th>
          <td>carrot@google.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>Compile following source code with options -mvsx -mcpu=power8 -O2


struct S{
  struct S* next;
};

struct S* foo(struct S* p, struct S* e)
{
  struct S* n;
  for (; (n = p->next) !=0 && n < e; p = n);
  return n;
}

LLVM generates:

foo:                                    # @foo
.Lfunc_begin0:
# BB#0:                                 # %entry
        .p2align        5
.LBB0_1:                                # %for.cond
                                        # =>This Inner Loop Header: Depth=1
        ld 3, 0(3)
        cmpdi    3, 0            // (n = p->next) !=0
        cmpld 1, 3, 4            // n < e
        crandc 20, 4, 2          //    &&
        bc 12, 20, .LBB0_1
# BB#2:                                 # %for.end
        blr


It uses crandc to combine the previous two cmp results, and then branch. It is
much slower than 2 simple cmp/br on power8, because crandc has data dependence
on previous cmp instructions, they have 5 cycles latency. In an internal
bigtable benchmark, the crandc version has only half of the performance of the
simple cmp/br version, with a similar code pattern.</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>