[clang] [llvm] [NVPTX] Add builtins and intrinsics for conversions of new FP types (PR #134345)

[Srinivasa Ravi via llvm-commits]

================
@@ -1548,6 +1548,45 @@ let TargetPrefix = "nvvm" in {
       Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
   def int_nvvm_e5m2x2_to_f16x2_rn_relu : ClangBuiltin<"__nvvm_e5m2x2_to_f16x2_rn_relu">,
       Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
+  
+  def int_nvvm_ff_to_e2m3x2_rn : ClangBuiltin<"__nvvm_ff_to_e2m3x2_rn">,
+      Intrinsic<[llvm_i16_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem, IntrNoCallback]>;
+  def int_nvvm_ff_to_e2m3x2_rn_relu : ClangBuiltin<"__nvvm_ff_to_e2m3x2_rn_relu">,
----------------
Wolfram70 wrote:

I chose this name for the intrinsics to maintain consistency since all other CVT intrinsics with two `llvm_float_ty` as inputs (like the `f32` to `e4m3x2`, `e5m2x2`, `f16x2` and `bf16x2` conversions) appear to use `ff` in the name instead of `f32x2`.

https://github.com/llvm/llvm-project/pull/134345