<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/153376>153376</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [SLP] Investigate using TCK_CodeSize for minsize builds
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            llvm:SLPVectorizer
      </td>
    </tr>

    <tr>
      <th>Assignees</th>
      <td>
      </td>
    </tr>

    <tr>
      <th>Reporter</th>
      <td>
          RKSimon
      </td>
    </tr>
</table>

<pre>
    Similar to #153375 - SLP currently always uses TCK_RecipThroughput (although it tends to be used locally instead of as a common global costkind value like VectorCombine), but for minsize builds we should consider using TCK_CodeSize instead to allow us to make use of vectorisation to compact code.
</pre>
<img width="1" height="1" alt="" src="http://email.email.llvm.org/o/eJxskk9v2zwMxj-NfCEa2HIcxwcf-qYI8KI9FHWx60BLrM1VFgP9SZF--sHuhh22kyCQon7P8xBj5MkT9ar5TzUPBeY0S-hfHgdexBej2Fs_8MIOAyQBpeuqqeu2gTsYnp7B5BDIJ3cDdB94i5AjRXg9PX5_IcOX1zlInuZLTqD0EV2a1ytwgkTexnXiSOsbC04MOncD9jERWpA3wAgIRpZFPExORnRgJKZ39hau6DKB43eCb2SShJMsI3tSulP6BGNO8CYBFvaRPwnGzM5G-CCIs2RnwYiPbClAjuynjfgkloa1-TdCEkDn5APyRrrg-8a6ol23PzliYvFr0chyQZPAiKVdYfvadnWHBfVV2zRl21bHrpj7I5I90LHGsWktHt40tvtDUzaHkqqqwn3BvS51Ux6ruuz0QXc7XWNb7UdTYWnasavVvqQF2e2cuy47CVPBMWbqt1QOhcORXNzC1HptUfX98PT8ZRF_UlBarzGHfi3ejXmKal86jin-mZg4uW0hhqdn1TzA__5KMfGEif5l198-Fzm4fk7pElV9r_RZ6fPEac7jzsii9HkD-zruLkF-kElKnzchUenzLy3XXv8MAAD__xsW4Z4">