<html>
    <head>
      <base href="https://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 --- - [SSE] scalar intrinsics don't fold loads"
   href="https://llvm.org/bugs/show_bug.cgi?id=23349">23349</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>[SSE] scalar intrinsics don't fold loads
          </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>spatel+llvm@rotateright.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>#include <xmmintrin.h>
__m128 add_fold(__m128 x, float *y) {
        __m128 ld = _mm_load_ss(y);
        return _mm_add_ss(x, ld);
}

or IR test case for llc:

define <4 x float> @add_fold(<4 x float> %x, float* %y) #0 {
  %0 = load float, float* %y, align 1, !tbaa !2
  %vecext1.i = extractelement <4 x float> %x, i32 0
  %add.i = fadd float %vecext1.i, %0
  %vecins.i = insertelement <4 x float> %x, float %add.i, i32 0
  ret <4 x float> %vecins.i
}


----------------------------------------------------------------------------

The load should be folded into the math op, but:

$ clang -O1 addfold.c -S -o -
...
    movss    (%rdi), %xmm1           ## xmm1 = mem[0],zero,zero,zero
    addss    %xmm1, %xmm0

----------------------------------------------------------------------------

The load does get folded with non-intrinsic C (IR won't have extract/insert in
this case) or with vector ops:

float add_fold2(float x, float *y) {
        return x + *y;
}

__m128 add_fold3(__m128 x, float *y) {
        __m128 ld = _mm_load_ps(y);
        return _mm_add_ps(x, ld);
}

...

    addss    (%rdi), %xmm0
...
    addps    (%rdi), %xmm0</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>