<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 - Missed tail cail optimization when copying arrays"
   href="https://bugs.llvm.org/show_bug.cgi?id=41047">41047</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Missed tail cail optimization when copying arrays
          </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>Scalar Optimizations
          </td>
        </tr>

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

        <tr>
          <th>Reporter</th>
          <td>david.bolvansky@gmail.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>-03, Haswell.

void memcpy_tail_call (int *__restrict__ p, int *__restrict__ q, int N)
{
  p[0] = q[N-1];
  for (int i = 1; i < N; i++)
    {
      p[i] = q[i-1];
    }
}

memcpy_tail_call(int*, int*, int):              # @memcpy_tail_call(int*, int*,
int)
        lea     eax, [rdx - 1]
        movsxd  rcx, eax
        mov     ecx, dword ptr [rsi + 4*rcx]
        mov     dword ptr [rdi], ecx
        cmp     edx, 2
        jl      .LBB0_2
        push    rax
        add     rdi, 4
        mov     edx, eax
        shl     rdx, 2
        call    memcpy
        add     rsp, 8
.LBB0_2:
        ret


GCC generates:
memcpy_tail_call(int*, int*, int):
        movsx   rax, edx
        mov     eax, DWORD PTR [rsi-4+rax*4]
        mov     DWORD PTR [rdi], eax
        cmp     edx, 1
        jle     .L3
        lea     eax, [rdx-2]
        add     rdi, 4
        lea     rdx, [4+rax*4]
        jmp     memcpy
.L3:
        ret</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>