[clang] [llvm] [clang][NVPTX] Add support for scaled::n1::ue8m0 in FP8, FP6 and FP4 conversions (PR #227652)

[Durgadoss R via llvm-commits]

================
@@ -2101,15 +2101,28 @@ let TargetPrefix = "nvvm" in {
             PureIntrinsic<[llvm_i16_ty],
                           [llvm_float_ty, llvm_float_ty, llvm_i1_ty],
                           [ImmArg<ArgIndex<2>, DefaultValue<0>>]>;
+        def int_nvvm_ff_to_ # type # _ # rnd # relu # _scale_n1_ue8m0 : NVVMBuiltin,
+            PureIntrinsic<[llvm_i16_ty],
+                          [llvm_float_ty, llvm_float_ty, llvm_i16_ty, llvm_i1_ty],
+                          [ImmArg<ArgIndex<3>, DefaultValue<0>>]>;
----------------
durga4github wrote:

nit:
it would be nicer to pretty-print "pzo" on these booleans .. but that can be a separate PR later

https://github.com/llvm/llvm-project/pull/227652