<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/72240>72240</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            Add documentation for Linalg Ops
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            new issue
      </td>
    </tr>

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

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

<pre>
    Many of the operations currently are blank. Some have fairly unintuitive semantics, like the max and sum pool ops that take a tensor not for its contents but for its shape specification. Also, some seem to only be possible to lower using the transform dialect, not a linalg pass. It would be great to have some short descriptions of what each of the parameters is and what the recommended way to lower them is.

Similar in spirit to #44864
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJxEksGOvDYMxp8GLtYiCMzscOAw7WqkSq162CcwxAzpJnEUOzudt69g-tdeQLKTz798n1HE3SPRVJ1-q04fNRbdOE9SEmXPqWz1zPY5_YXxCbyCbgScKKM6jgJLyZmi-idgJpg9xq8GPjkQbPhNsKLL_gkluqjFqfsmEAoY1S1Smd_Buy86JAP-CxgtSAmQmD1wEtANFRS_CBCUonCGyAorZ3AqsHBUiiowl5-ibJgIJNHiVrcclA1cvfA-TnYwIQqgDBz9E2aCxCJu9rTXPD8oQxEX7weWZoyycg5gHXpadFfZGRC8i-jvkFCkgT8UHly83fXumXZsfjnwGrlxVrAkS3bpZRyv8NifR7hsv3xNmDGQUhZwcthxHNlbmRYOgaIlCw98_rDqRgGcNFX7UbXX1_fTBecxg4sgyWV30FSmH4bLeajt1NuxH7GmqTuP43gazTDU23QixG4e26XrLrbr23E-nfueTm3fv49osHaTaU3fdd3QtaehHZrV0sVe1uXS2vPQv_fV0FJA5xvvv0PD-V47kULTuzFDW3ucycuxZsZEesDRrIzZty5P-523udylGlrvROVHRZ16mq7WguWlBIp65Hpk_ucrhr-T1CX7aVNNUvXXytwqc7s73crcLBwqc9vl_v-9pcz_HGneDgipzO2A_C8AAP__q9sL_w">