<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/153375>153375</a>
        </td>
    </tr>

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

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

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

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

<pre>
    VectorCombine uses a global CostKind to drive the cost:benefit of the possible folds, although this is currently always TCK_RecipThroughput, but it does make it easy to experiment withe the other cost kinds.

For MinSize/-Os builds we should investigate using TCK_CodeSize instead.

NOTE: Not all targets are great at realistically modelling CostKinds other than TCK_RecipThroughput so this might unearth some weaknesses in some cost models.
</pre>
<img width="1" height="1" alt="" src="http://email.email.llvm.org/o/eJx8Uk1v2zgQ_TXUZRCDpiI7OujgddbAItgESIK9LihxLE5DkQZnZNf99QXlFEWBogdB5HA-3nvzLDONEbFTzV-qeazsLD7l7vXpjaYUqz65a_cfDpLyPk09RYSZkcHCGFJvA-wTyxNFB5LAZTojiEcYEouqdz1GPJJAOi7RU2KmPiAcU3CszB5sEJ_m0YN4YiCGYc4Zo4Qr2HCxV4b3_dP_rzjQ6d3nknmapRT2swAJuIQMk_3AckHL1wIDv54w04RR4EJlbvmSeMwLLvig6Hil9E7p3SFl-JfiG31DZQ53Lwz9TMExXBDYpzk4oHhGFhqtFO4UxwXTPjksVUCRBa377Pf88v63qnfwnARsCCA2jygMNiOMGa2AFchoA7HQYEO4wpQchlD6_tCSP9GKt_F3AgCnm2ATjV5gjmizeOA0IVzQfkTksiOKt9BCepnCq8p1tWvr1lbYrbdNo7eb1tSV745bXW_bZqPNYCxq3az7473WbYtH7WpnKuqMNo1-WNe6NUbXq3bd4IPVm7VrUW_6rbrXOFkKqxDO0yrlsSLmGbt1U9fbpgq2x8CLzYwpKareqXp3Xrw13LyljCkezF15v-vnkdW9LlLxz6ZCEha3_uJK1TzCP39e1DFlmChyOd-WXM05dF7kxAWLOShzGEn83K-GNClzWFDefnennL7gIMocFlaszOGT2Lkz3wMAAP__jP0fbg">