<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/62575>62575</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [AArch64] v4f16 fcmp without full fp16 support is incorrectly cost modeled as scalarized
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            backend:AArch64
      </td>
    </tr>

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

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

<pre>
    LowerVSETCC promotes the other operands to vf432 and does the compare.

Found during implementation of https://reviews.llvm.org/D149572
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJxUkLGO2zAMhp9GXogLJNly7MFDeqmnbi26yxJtq5VNQaITXJ--SHptcQu5_D_I77OlhGVHHIT5JMy1sgevlAemlDC7aiL_NnyhO-bvXz9_e32FlGkjxgK8IhCvmIESZrv7Akxwm5tag909eHoPOdqSzXgS8irk5c8c6XhEjhz2BcKWIm64s-VAO9AMK3Mqor4IPQo9ZrwFvJdTjLftRHkReryqpjdnXfmh9n3d2woH1XZ1rXSvZLUOasK-V0771p6783zuXK9QTv2ESndOdlUYtNS1NNKozhglT1Pd923jZt21rVZGiUbiZkP8d7UKpRw4tNqcTRXthLE8nWk9WfcTdy_qy-WS3do2QuuHyjw8ui_TsRTRyBgK_2eoOHB8Sv_bMVe4NbNqYXZbgnvglQ6G-YgR5qRaKEdKlBlCgbA7yhkdxzdwVBg28hjRgy1QnI02h1_oqyPH4aPJJfB6TCdHm9Dj45X39ZIy_UDHQo9PyiL0-AT9HQAA___Tia-S">