[llvm] [LLVM][NVPTX]Add BF16 vector instruction and fix lowering rules (PR #69415)

[Han Shen via llvm-commits]

================
@@ -741,12 +753,14 @@ NVPTXTargetLowering::NVPTXTargetLowering(const NVPTXTargetMachine &TM,
   // These map to conversion instructions for scalar FP types.
   for (const auto &Op : {ISD::FCEIL, ISD::FFLOOR, ISD::FNEARBYINT, ISD::FRINT,
                          ISD::FROUNDEVEN, ISD::FTRUNC}) {
-    setOperationAction(Op, MVT::bf16, Legal);
+    setBF16OperationAction(Op, MVT::bf16, Legal, Promote);
----------------
shenh10 wrote:

I think there should be a check for sm_80 and sm_90 for bf16 instruction, isn't it?

https://github.com/llvm/llvm-project/pull/69415