<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 - Wrong register in result asm when using inline asm with movups"
   href="https://bugs.llvm.org/show_bug.cgi?id=33785">33785</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Wrong register in result asm when using inline asm with movups
          </td>
        </tr>

        <tr>
          <th>Product</th>
          <td>clang
          </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>enhancement
          </td>
        </tr>

        <tr>
          <th>Priority</th>
          <td>P
          </td>
        </tr>

        <tr>
          <th>Component</th>
          <td>LLVM Codegen
          </td>
        </tr>

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

        <tr>
          <th>Reporter</th>
          <td>ilia.taraban@intel.com
          </td>
        </tr>

        <tr>
          <th>CC</th>
          <td>llvm-bugs@lists.llvm.org
          </td>
        </tr></table>
      <p>
        <div>
        <pre>==================== copy-asm.c =================
#include <stdio.h>
#define N 2


float  __declspec(align(64)) farray[4 * N];
float  __declspec(align(64)) fdest[4 * N];


void copy_from_arr_to_dest()
{
    long long int i;

    for (i = 0; i < sizeof(farray); i += 4) {
        __asm {
            mov  rax, i
            movups xmm1, [farray+rax]
            movups [fdest+rax], xmm1
        }
    }
}


int
main()
{
    int i;
    for (i = 0; i < 4 * N; ++i) {
        farray[i] = (float)i;
    }

    copy_from_arr_to_dest();
    //check second pack of floats
    if (fdest[4] != farray[4]) {
       printf("FAILED\n");
       return 1;
    }
    printf("PASSED!\n");
    return 0;
}
====================================================

<span class="quote">>>> clang -v</span >
clang version 5.0.0 (cfe/trunk 307600)
...

<span class="quote">>>> clang -o copy-asm.exe copy-asm.c -fms-extensions
>>> ./copy-asm.exe</span >
FAILED


=============== generated-assembler =================
...
        movq    -8(%rbp), %rax           # mov  rax, i
        movups  farray(%rip), %xmm1      # movups xmm1, [farray+rax]
        movups  %xmm1, fdest(%rip)       # movups [fdest+rax], xmm1
...
=====================================================

Now, if we change rip to rax(which we use in inline asm block):

=============== new-assembler =================
...
        movq    -8(%rbp), %rax           # mov  rax, i
        movups  farray(%rax), %xmm1      # movups xmm1, [farray+rax]
        movups  %xmm1, fdest(%rax)       # movups [fdest+rax], xmm1
...
=====================================================
<span class="quote">>>> clang -o fixed-copy-asm.exe fixed-copy-asm.s
>>> ./fixed-copy-asm.exe</span >
PASSED!

Same problem with movaps, movdqa32, movdqu32
------------------------
Intel Software Engineer
Ilia Taraban</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>