<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/54693>54693</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [AMDGPU][MC][GFX810+] Incorrect error message "image data size does not match dmask and tfe"
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            backend:AMDGPU,
            mc
      </td>
    </tr>

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

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

<pre>
    d16 modifier also affects image data size.

For example, the following opcode is incorrect for GFX9:

    image_load v[5:6], v[1:4], s[8:15] dmask:0x3 unorm glc slc lwe da d16

Output:
    
    error: image data size does not match dmask and tfe

The same opcode without d16 is assembled fine:

    image_load v[5:6], v[1:4], s[8:15] dmask:0x3 unorm glc slc lwe da

</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJy9Uk2PmzAQ_TVwGTWyDSThwCHZKKseVu2hlXqrDB7AXRsj22y2_fUd52M32lsvRYD9POi9eW9onfrdKL4G65TuNXqQJjiQfY9dDKCtHBCUjBKC_oOrjB0ytru8j84Dvko7G8zEA8QRoXfGuJOeBnBz5xSCJoqpc94TG1U9PB5_1Fmxu-cBus46P42TCl6yal_RJ-usOiTehDnh8ooD4S1hXtEBKCvDMyH2WsAyOW9hMB0EeswpNQ7k7V7syxLnJb51kLTfd-i981T7aBuUwwCTi2Bl7MaLKMhJQezxnv0bZRCkxZv9k46jW2JqIkUhQ0DbGlTQ6wn_ZwwXiVw1haqLWuZRR4MNUeyeDo9fvyfOav_0cFlpRlvOMrFPzJ_fxndOByyGkMLJhPinlITIF2-aMcY5JOfiSPdA-SztqnOWgDEvt-XT7N0v0iSoQ1gw0KYq13WRj42qNxIrwbloeYl1hazclJ1c8w3bVn1b5ka2aEIyR6Kt7J5xUqR4dSpESo8W26V9dch1I5gQrGSc86IW5Yq3HHklRSm6fsN7lpUMrdRmlVpbOT_kvjl32S5DoKLRIYb3Ik1ZDxPitQM1e3Stl1c1udAv4ZvbaX7215zN_QVwnhMD">