diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
@@ -63,6 +63,13 @@
 
   for (Value *V : GA->operands()) {
     auto *CS = cast<ConstantStruct>(V);
+    if (auto *F = dyn_cast<Function>(CS->getOperand(1))) {
+      auto *GV = new GlobalVariable(
+          M, F->getType(), /*IsConstant=*/true, GlobalValue::InternalLinkage, F,
+          F->getName() + (IsCtor ? ".init" : ".fini"));
+      GV->setSection(IsCtor ? ".init_array" : ".fini_array");
+      appendToUsed(M, {GV});
+    }
     IRB.CreateCall(ConstructorTy, CS->getOperand(1));
   }
 
diff --git a/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll b/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
@@ -10,6 +10,9 @@
 
 ; CHECK-NOT: @llvm.global_ctors
 ; CHECK-NOT: @llvm.global_dtors
+; CHECK: @foo.init = internal constant ptr @foo, section ".init_array"
+; CHECK: @bar.fini = internal constant ptr @bar, section ".fini_array"
+; CHECK: @llvm.used = appending global [4 x ptr] [ptr @foo.init, ptr @amdgcn.device.init, ptr @bar.fini, ptr @amdgcn.device.fini]
 
 ; CHECK-LABEL: amdgpu_kernel void @amdgcn.device.init() #0
 ; CHECK-NEXT: call void @foo