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
@@ -38,6 +38,7 @@
       FunctionType::get(Type::getVoidTy(M.getContext()), false),
       GlobalValue::WeakODRLinkage, 0, InitOrFiniKernelName, &M);
   InitOrFiniKernel->setCallingConv(CallingConv::AMDGPU_KERNEL);
+  InitOrFiniKernel->addFnAttr("amdgpu-flat-work-group-size", "1,1");
   if (IsCtor)
     InitOrFiniKernel->addFnAttr("device-init");
   else
@@ -58,6 +59,7 @@
 // void call_init_array_callbacks() {
 //   for (auto start = __init_array_start; start != __init_array_end; ++start)
 //     reinterpret_cast<InitCallback *>(*start)();
+// }
 static void createInitOrFiniCalls(Function &F, bool IsCtor) {
   Module &M = *F.getParent();
   LLVMContext &C = M.getContext();
diff --git a/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor-constexpr-alias.ll b/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor-constexpr-alias.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor-constexpr-alias.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-ctor-dtor-constexpr-alias.ll
@@ -64,5 +64,5 @@
 ; CHECK:       while.end:
 ; CHECK-NEXT:    ret void
 
-; CHECK: attributes #[[ATTR0:[0-9]+]] = { "device-init" }
-; CHECK: attributes #[[ATTR1:[0-9]+]] = { "device-fini" }
+; CHECK: attributes #[[ATTR0:[0-9]+]] = { "amdgpu-flat-work-group-size"="1,1" "device-init" }
+; CHECK: attributes #[[ATTR1:[0-9]+]] = { "amdgpu-flat-work-group-size"="1,1" "device-fini" }
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
@@ -58,5 +58,5 @@
   ret void
 }
 
-; CHECK: attributes #0 = { "device-init" }
-; CHECK: attributes #1 = { "device-fini" }
+; CHECK: attributes #0 = { "amdgpu-flat-work-group-size"="1,1" "device-init" }
+; CHECK: attributes #1 = { "amdgpu-flat-work-group-size"="1,1" "device-fini" }
diff --git a/llvm/test/CodeGen/AMDGPU/lower-multiple-ctor-dtor.ll b/llvm/test/CodeGen/AMDGPU/lower-multiple-ctor-dtor.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-multiple-ctor-dtor.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-multiple-ctor-dtor.ll
@@ -57,5 +57,5 @@
   ret void
 }
 
-; CHECK: attributes #0 = { "device-init" }
-; CHECK: attributes #1 = { "device-fini" }
+; CHECK: attributes #0 = { "amdgpu-flat-work-group-size"="1,1" "device-init" }
+; CHECK: attributes #1 = { "amdgpu-flat-work-group-size"="1,1" "device-fini" }