diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1343,7 +1343,8 @@
 
 def D16PreservesUnusedBits :
   Predicate<"Subtarget->d16PreservesUnusedBits()">,
-  AssemblerPredicate<(all_of FeatureGFX9Insts, (not FeatureSRAMECC))>;
+  AssemblerPredicate<(all_of FeatureGFX9Insts, (not FeatureSRAMECC),
+    (not FeatureGFX90AInsts))>;
 
 def LDSRequiresM0Init : Predicate<"Subtarget->ldsRequiresM0Init()">;
 def NotLDSRequiresM0Init : Predicate<"!Subtarget->ldsRequiresM0Init()">;
diff --git a/llvm/lib/Target/AMDGPU/GCNSubtarget.h b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
--- a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -591,7 +591,9 @@
   }
 
   bool d16PreservesUnusedBits() const {
-    return hasD16LoadStore() && !TargetID.isSramEccOnOrAny();
+    // gff90a's d16 loads don't preserve unused bits
+    return hasD16LoadStore() && !TargetID.isSramEccOnOrAny() &&
+           !hasGFX90AInsts();
   }
 
   bool hasD16Images() const {