<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/58326>58326</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
Implement global-isel support for llvm.amdgcn.icmp and llvm.amdgcn.fcmp
</td>
</tr>
<tr>
<th>Labels</th>
<td>
backend:AMDGPU
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
Sisyph
</td>
</tr>
</table>
<pre>
Compares of 16 bit values need to be implemented in AMDGPUInstructionSelector::getV_CMPOpcode for globalisel to work for llvm.amdgcn.icmp. True16 version of compare instructions should be used on GFX11
llvm.amdgcn.fcmp whole implementation is TODO
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJxtUslu3DAM_Rr7IsSQ5GU8Bx2mGSTIIZgASYveCi0cW41sGVomyN-X9qRtUBQQJJEiH98jpbx5F7d-WmSASPyZsI4om8hFuoyOGcCQ5IkCYqfFwQRzQo-dyeHxeP_09WGOKWSdrJ-fwYFOPhT1AdcA6duP28en06K9AXL2gQzOK-lsBLcivvnwurmdu0yVnMyg58rqaanIS8iANC4QIuKupPSVINb9Uy6SOPrszEotR-SEkfd33xkr6LGgh-v-GfuM2ORt9O6TFLkiERvJy-l4uqaUIFjXtR2tu6YvjajNvt7LMtnkQDz8TvwQc7OpiXlZfEj_VUPkbMi_NMocnBhTWuLaLH6Ha7BpzKpCoWis8R_HzRL8T-wrmjZGHAle2r7mXTkKrvpG97XRVBrY9Wbf7aQ5d6ylitKmV6WTClwURful4FxJ_QqzwYrX0aGraI-lFZxyzijjbN9gVtVo1lGod9BKuuctKxoKk7Su2lT4MJRBbMxUHiI-4kRT_PsoY7QDfputKuLLnEYfxLON78tYbhrEJuAXOWjTpQ">