[PATCH] D136592: [AMDGPU][GISel] Select llvm.amdgcn.fcmp intrinsics

[Jay Foad via Phabricator via llvm-commits]

foad added a comment.

Summary needs updating. Nits inline. LGTM apart from that.



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp:1296
+                     .addReg(Src1)
+                     .addImm(0); // omod
+  } else
----------------
This is clamp not omod.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp:1298
+  } else
+    SelectedMI = BuildMI(*BB, &I, DL, TII.get(Opcode), Dst)
+                     .add(I.getOperand(2))
----------------
Need braces around this block.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D136592/new/

https://reviews.llvm.org/D136592