<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/138334>138334</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            Funnel shift in 64-bit doesn't get matched to an intrinsic
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
      </td>
    </tr>

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

    <tr>
      <th>Reporter</th>
      <td>
          AZero13
      </td>
    </tr>
</table>

<pre>
    Yes I know this has two cases of subpar optimization: One where the funnel shift is 64-bit based, and the other is left funnel shifts that can be converted to a right funnel shift. This one is about the latter. However, this was lifted from one of gcc's test suites. 

https://godbolt.org/z/Yd63ed3sv
</pre>
<img width="1" height="1" alt="" src="http://email.email.llvm.org/o/eJxckb2O2zAQhJ-GahYnyCTln0KFk0BIqjRpLh1_liITmjS4Kxu5pw9k3CFwKjYz-w1nDFFaCuIkxk9i_NKZlWNt0_kntrpTna3-z_SKBN_gd6l34JgIoiHgewVnCAlqAFrt1TSoV06X9GY41SLUGb4XhHvEhsARIaylYAaKKTAkgr1-sYnBGkIv5GcwxT90lSO2TZAx8JOLgKNhcKaARXC13LAxeuAKBlpa4rO8hx9b2lpwu2ZsXfkByIYZWw9f6x1v2Db241t3Q5BT2C6GVi8PYw2wOCfkgYCRGGhNjNSDGM5iOEfmKwl1FnIWcl6qtzVzX9si5Pwm5Pzq9wq9olvnJ-VP6mQ6nHYHvZe7_fGkuzgFtAqVCngM3h7xqNx4GIzzegx6RD10aZKDHIdxkHLY6VH3djhJ7fVhCM5ZvZNCD3gxKfc53y4bu0tEK047dVRKd9lYzPSxbps21YtdFxJ6yImY_vk4ccZpfpqpfMzkK1IR8sCwIMPFsIvvzRdIhVsqlFy3tjz9V0riuNre1YuQ84Z6f16urf5Cx0LOj7wk5Pwe-TbJvwEAAP__plfchg">