[llvm] [AMDGPU][CodeGen][True16] Track waitcnt of vgpr32 instead of vgpr16 for 16bit reg in GFX11 (PR #157795)

[Brox Chen via llvm-commits]

================
@@ -38,6 +38,10 @@ bool AMDGPUSubtarget::useRealTrue16Insts() const {
   return hasTrue16BitInsts() && EnableRealTrue16Insts;
 }
 
+bool AMDGPUSubtarget::has16bitD16HWBug() const {
+  return hasTrue16BitInsts() && useRealTrue16Insts() && Enable16bitD16HWBug;
----------------
broxigarchen wrote:

same as above

https://github.com/llvm/llvm-project/pull/157795