<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 - Use paddusb for saturated add/sub"
   href="https://bugs.llvm.org/show_bug.cgi?id=41248">41248</a>
          </td>
        </tr>

        <tr>
          <th>Summary</th>
          <td>Use paddusb for saturated add/sub
          </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>Code from other PR:

void add_clamp_2(unsigned char *ptr) {
    for (unsigned i = 0; i != 16; ++i) {
        unsigned char s = *ptr;
        *ptr++ = (s + HI) > 255 ? 255 : (s + HI);
    }
}

void add_clamp_3(unsigned char *ptr) {
    for (unsigned i = 0; i != 16; ++i) {
        unsigned char s = *ptr;
        *ptr++ = (s + HI) >= 255 ? 255 : (s + HI);
    }
}

add_clamp_2(unsigned char*):                      # @add_clamp_2(unsigned
char*)
        movdqu  xmm0, xmmword ptr [rdi]
        pminub  xmm0, xmmword ptr [rip + .LCPI2_0]
        paddb   xmm0, xmmword ptr [rip + .LCPI2_1]
        movdqu  xmmword ptr [rdi], xmm0
        ret

add_clamp_3(unsigned char*):                      # @add_clamp_3(unsigned
char*)
        movdqu  xmm0, xmmword ptr [rdi]
        pminub  xmm0, xmmword ptr [rip + .LCPI3_0]
        paddb   xmm0, xmmword ptr [rip + .LCPI3_1]
        movdqu  xmmword ptr [rdi], xmm0
        ret

ICC 19 uses paddusb here
add_clamp_2(unsigned char*):
        movdqu    xmm0, XMMWORD PTR [rdi]                       #22.29
        paddusb   xmm0, XMMWORD PTR .L_2il0floatpacket.1[rip]   #22.29
        movdqu    XMMWORD PTR [rdi], xmm0                       #22.10
        ret                                                     #24.1
add_clamp_3(unsigned char*):
        movdqu    xmm0, XMMWORD PTR [rdi]                       #29.30
        paddusb   xmm0, XMMWORD PTR .L_2il0floatpacket.1[rip]   #29.30
        movdqu    XMMWORD PTR [rdi], xmm0                       #29.10
        ret   

Maybe use paddusb as well?</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>