diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -302,7 +302,7 @@
 
   setOperationAction({ISD::FLOG, ISD::FLOG10, ISD::FEXP}, MVT::f32, Custom);
 
-  setOperationAction(ISD::FNEARBYINT, {MVT::f32, MVT::f64}, Custom);
+  setOperationAction(ISD::FNEARBYINT, {MVT::f16, MVT::f32, MVT::f64}, Custom);
 
   setOperationAction(ISD::FREM, {MVT::f16, MVT::f32, MVT::f64}, Custom);
 
diff --git a/llvm/test/CodeGen/AMDGPU/fnearbyint.ll b/llvm/test/CodeGen/AMDGPU/fnearbyint.ll
--- a/llvm/test/CodeGen/AMDGPU/fnearbyint.ll
+++ b/llvm/test/CodeGen/AMDGPU/fnearbyint.ll
@@ -5,6 +5,7 @@
 ; This should have the exactly the same output as the test for rint,
 ; so no need to check anything.
 
+declare half @llvm.nearbyint.f16(half) #0
 declare float @llvm.nearbyint.f32(float) #0
 declare <2 x float> @llvm.nearbyint.v2f32(<2 x float>) #0
 declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>) #0
@@ -13,6 +14,12 @@
 declare <4 x double> @llvm.nearbyint.v4f64(<4 x double>) #0
 
 
+define amdgpu_kernel void @fnearbyint_f16(half addrspace(1)* %out, half %in) #1 {
+  %1 = call half @llvm.nearbyint.f16(half %in)
+  store half %1, half addrspace(1)* %out
+  ret void
+}
+
 define amdgpu_kernel void @fnearbyint_f32(float addrspace(1)* %out, float %in) #1 {
 entry:
   %0 = call float @llvm.nearbyint.f32(float %in)