<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] prefetch instruction blocks the optimization of st/ld with same address"
   href="https://bugs.llvm.org/show_bug.cgi?id=32365">32365</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[ppc] prefetch instruction blocks the optimization of st/ld with same address
          </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>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 the following source code with options -m64 -O2 -mvsx -mcpu=power8

struct C { 
  struct C *next_;
  int length_;
};
int foo(struct C* c){ 
  struct C* next = c->next_->next_;
  c->next_ = next; 
  c->length_--;
  __builtin_prefetch(next, 0, 0); 
  return c->length_;
}

LLVM generates:

foo:                                    # @foo
.Lfunc_begin0:
# BB#0:                                 # %entry
        ld 4, 0(3)
        lwz 5, 8(3)
        ld 4, 0(4)
        addi 5, 5, -1
        stw 5, 8(3)            // store length_
        std 4, 0(3)
        dcbt 0, 4
        ori 2, 2, 0
        lwa 3, 8(3)            // load length_
        blr

The lwa instruction is not necessary since the value of length_ is already in
r5. This problem impacts the performance of tcmalloc.</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>