<html>
    <head>
      <base href="http://llvm.org/bugs/" />
    </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 --- - using memory operand form of division would save on code size"
   href="http://llvm.org/bugs/show_bug.cgi?id=17286">17286</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>using memory operand form of division would save on code size
          </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>normal
          </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>kkhoo@perfwizard.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvmbugs@cs.uiuc.edu
          </td>
        </tr>

        <tr>
          <th>Classification</th>
          <td>Unclassified
          </td>
        </tr></table>
      <p>
        <div>
        <pre>The following x86 codegen uses 2 vector load instructions (vmovupd) followed by
a reg-reg vector division instruction (vdivpd). It would be better to use the
memory operand form of the division instruction to save on code size; there are
4 extra bytes for the redundant load instruction.

In more complicated scenarios, it could also ease register pressure.

According to "iaca" (
<a href="http://software.intel.com/en-us/articles/intel-architecture-code-analyzer">http://software.intel.com/en-us/articles/intel-architecture-code-analyzer</a> ),
the code should perform identically. However, based on my testing on a Sandy
Bridge system, the smaller code also benchmarks slightly faster (4% faster for
the smaller code).

$ ./clang -v
clang version 3.4 (trunk 190938)
Target: x86_64-apple-darwin11.4.2
Thread model: posix

$ cat div.c 
void foo(double *restrict x, double *restrict y) {
    int i;
    for (i=0; i<2; i++) {
        x[i] = x[i] / y[i];
    }
}

$ ./clang -S -o - -O3 -fomit-frame-pointer -march=corei7-avx div.c 
    .section    __TEXT,__text,regular,pure_instructions
    .globl    _foo
    .align    4, 0x90
_foo:                                   ## @foo
    .cfi_startproc
## BB#0:                                ## %entry
    vmovupd    (%rsi), %xmm0
    vmovupd    (%rdi), %xmm1
    vdivpd    %xmm0, %xmm1, %xmm0
    vmovupd    %xmm0, (%rdi)
    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>