[PATCH] D22838: AMDGPU/SI: Implement amdgcn image intrinsics

[Nicolai Hähnle via llvm-commits]

nhaehnle added a comment.

Thanks for doing this. One comment below.


================
Comment at: include/llvm/IR/IntrinsicsAMDGPU.td:233
@@ +232,3 @@
+     llvm_i1_ty,         // r128(imm)
+     llvm_i1_ty,         // tfe(imm)
+     llvm_i1_ty,         // lwe(imm)
----------------
tfe should be dropped. AFAIU it changes the return type (5 return values instead of 4).


https://reviews.llvm.org/D22838