<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 - Signed division with power of two can be faster"
   href="https://bugs.llvm.org/show_bug.cgi?id=43197">43197</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Signed division with power of two can be faster
          </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: X86
          </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>craig.topper@gmail.com, llvm-bugs@lists.llvm.org, llvm-dev@redking.me.uk, spatel+llvm@rotateright.com
          </td>
        </tr></table>
      <p>
        <div>
        <pre>int foo(int i) {
    return i/(1 << 4);
}

foo(int):                                # @foo(int)
        mov     eax, edi
        sar     eax, 31
        shr     eax, 28
        add     eax, edi
        sar     eax, 4
        ret

Dispatch Width:    6
uOps Per Cycle:    3.81
IPC:               2.86
Block RThroughput: 1.5

GCC:
foo(int):
        test    edi, edi
        lea     eax, [rdi+15]
        cmovns  eax, edi
        sar     eax, 4
        ret


Dispatch Width:    6
uOps Per Cycle:    4.38
IPC:               3.13
Block RThroughput: 1.2


GCC's perf is better, microbenchmark confirms it:
int main(void) {
    int s = 0;
    for (int i = -60000000; i < 1000000000; ++i)
        s+= i/(1 << 4);
    return s;
}

Compiled with -O1:

clang -O1 -march=native lop.c 
time ./a.out 

real    0m0,658s
user    0m0,655s
sys     0m0,004s

gcc-9 -O1 -march=native lop.c 
time ./a.out 

real    0m0,605s
user    0m0,605s
sys     0m0,000s</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>