[Mlir-commits] [clang] [llvm] [mlir] [clang][NVPTX] Add support for pzo in f32 to f16/bf16 conversions (PR #214667)

[Durgadoss R]

================
@@ -1849,16 +1849,16 @@ let TargetPrefix = "nvvm" in {
     foreach relu = ["", "_relu"] in {
       foreach satfinite = ["", "_satfinite"] in {
         def int_nvvm_ff2bf16x2_ # rnd # relu # satfinite : NVVMBuiltin,
-            PureIntrinsic<[llvm_v2bf16_ty], [llvm_float_ty, llvm_float_ty]>;
+            PureIntrinsic<[llvm_v2bf16_ty], [llvm_float_ty, llvm_float_ty, llvm_i1_ty], [ImmArg<ArgIndex<2>, DefaultValue<0>>]>;
----------------
durga4github wrote:

May be move the properties to the next line..?

https://github.com/llvm/llvm-project/pull/214667