[llvm] [AMDGPU] Expose RTZ version of f16 interpolation (PR #86614)

[via llvm-commits]

================
@@ -2066,6 +2066,24 @@ def int_amdgcn_interp_inreg_p2_f16 :
             [IntrNoMem, IntrSpeculatable,
              ImmArg<ArgIndex<3>>]>;
 
+// llvm.amdgcn.interp.inreg.p10.rtz.f16 <p>, <i>, <p0>, <high>
+// fp16 interpolation intrinsic, but round-toward-zero.
+// high selects whether high or low 16-bits are used for p and p0 operands
+def int_amdgcn_interp_inreg_p10_rtz_f16:
----------------
ruiling wrote:

Maybe we can drop the inreg suffix for the rtz version intrinsic name, there is no precedence of such rtz version, so we don't really need to have such suffix exposed. Any comment?

https://github.com/llvm/llvm-project/pull/86614