[HIP] Fix regression about `__fp16` args and return value

[yaxunl]

Summary

HIP allows __fp16 as function arguments and return value by passing
-fallow-half-arguments-and-returns to clang through hipcc.

https://reviews.llvm.org/D133885 removed -fallow-half-arguments-and-returns
and add a TargetInfo member to control it.

This caused regressions in some HIP apps (https://github.com/ROCm-Developer-Tools/HIP/issues/3178).

clang/lib/Basic/Targets/AMDGPU.cpp

if (getMaxPointerWidth() == 64) {
     SizeType = UnsignedLong;
     PtrDiffType = SignedLong;
     IntPtrType = SignedLong;
   }
 
   MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64;
   CUMode = !(GPUFeatures & llvm::AMDGPU::FEATURE_WGP);
   ReadOnlyFeatures.insert("image-insts");
+  HalfArgsAndReturns = true;
 }
 
 void AMDGPUTargetInfo::adjust(DiagnosticsEngine &Diags, LangOptions &Opts) {
   TargetInfo::adjust(Diags, Opts);
   // ToDo: There are still a few places using default address space as private
   // address space in OpenCL, which needs to be cleaned up, then Opts.OpenCL
   // can be removed from the following line.
   setAddressSpaceMap(/*DefaultIsPrivate=*/Opts.OpenCL ||

clang/test/SemaCUDA/fp16-arg-return.cu

+// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn-amd-amdhsa -fcuda-is-device -fsyntax-only -verify %s
+
+// expected-no-diagnostics
+
+__fp16 testFP16AsArgAndReturn(__fp16 x) {
+  return x;
+}