<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 - Clang failed to inline memset for SSE2 and AVX2"
   href="https://bugs.llvm.org/show_bug.cgi?id=47200">47200</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Clang failed to inline memset for SSE2 and AVX2
          </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>Windows NT
          </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>zufuliu@163.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>following code (online at <a href="https://godbolt.org/z/9eWq78">https://godbolt.org/z/9eWq78</a>), when CNT is larger
than 1 (for both AVX2 and SSE2), clang emits call to memset.
gcc inline the memset call when buffer size is <= 256, e.g. CNT <= 8 for AVX2,
or CNT <= 16 for SSE2.


#include <string.h>
#include <immintrin.h>

#define CNT 2

int IsUTF7(const char *data, size_t length) {
#if defined(__AVX2__)
    char buffer[CNT*sizeof(__m256i)] = {0};
    memcpy(buffer, data, length);
    __m256i chunk = _mm256_loadu_si256((__m256i *)buffer);
    return _mm256_movemask_epi8(chunk) == 0;
#else
    char buffer[CNT*sizeof(__m128i)] = {0};
    memcpy(buffer, data, length);
    __m128i chunk = _mm_loadu_si128((__m128i *)buffer);
    return _mm_movemask_epi8(chunk) == 0;
#endif
}</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>