<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/193202>193202</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
[AMDGPU] Convert mul24 sdwa detection to tablegen predicates
</td>
</tr>
<tr>
<th>Labels</th>
<td>
backend:AMDGPU
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
RKSimon
</td>
</tr>
</table>
<pre>
#193033 allowed detection of operands to a mul24 node that would probably fold using SDWA patterns to prevent folding to mad24 (which can't use SDWA) - but its SelectionDAG-only.
This ticket tracks conversion to a purely-tabelgen predicate to allow us to remove the AMDGPUDAGToDAGISel::isSDWAOperand hook and support globalisel as well (with suitable additional test coverage).
</pre>
<img width="1" height="1" alt="" src="http://email.email.llvm.org/o/eJxUksGumzwQhZ_GbEaJYIDkZsGC_48SVVXVqrlV14M9ATcGI3ucKG9fwY3UdgWS59jnO3MoRttPzI2q_1P1MaMkgw_N988XO_op67x5NgrL4lDmZQnknH-wAcPCWqyfwF_BzxxoMhHEA8GYHFYwecMgAwk8fHIG5uA76twTrt4ZSNFOPVyOP1uYSYTDtIrnwHeeZJ1ZBsTDSAYrUPj2GKweQNOkcC-QIq9yhQfYQJcErES4sPtwdWzPGz-551blrcrb98FGEKtvLCCB9C2C9tOdQ1wIVtdzCuyeG6GOXc_TYsVYTcLr8UINafUYePT3BY2h_XI8f_txbM_v_tieP13YqbJVZWvjYu3rRyoweH-D5SemefZBoHe-I2cjO6AID3Zu5bMyQExWqHMMZIxdQMiBcBTQ_s6BelZ42GamKc2hPFDGTbHf7_Z7rLHIhsbs8-7KnOdXxpzQlNcrl4Zwp4tqr6nObIM57vIKi6Koayy2h6p625mOitroQtedqnIeybqtc_dx60Of2RgTN8WhxBwzt6QT16YgdqRvPBlVth85KMSlP6FZtJsu9VFVubNR4p_bxIpbm_aS1Ef4f12EvGoTzYP-Kpd4WPP4ZyMxS8E1g8gcl7zxpPDUWxlSt9V-VHhannt9NnPwv1iLwtNKEhWeXjD3Bn8HAAD__5pI_wA">