Index: llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUCtorDtorLowering.cpp
@@ -67,6 +67,8 @@
   }
 
   appendToUsed(M, {InitOrFiniKernel});
+
+  GV->eraseFromParent();
   return true;
 }
 
Index: llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
+++ llvm/test/CodeGen/AMDGPU/lower-ctor-dtor.ll
@@ -1,15 +1,25 @@
-; RUN: opt -S -mtriple=amdgcn--  -amdgpu-lower-ctor-dtor < %s | FileCheck %s
-; RUN: opt -S -mtriple=amdgcn--  -passes=amdgpu-lower-ctor-dtor < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-ctor-dtor < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-ctor-dtor < %s | FileCheck %s
+
+; Make sure we get the same result if we run multiple times
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-ctor-dtor,amdgpu-lower-ctor-dtor < %s | FileCheck %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readelf -s - 2>&1 | FileCheck %s -check-prefix=CHECK-VIS
 
 @llvm.global_ctors = appending addrspace(1) global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 1, void ()* @foo, i8* null }]
 @llvm.global_dtors = appending addrspace(1) global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 1, void ()* @bar, i8* null }]
 
+; CHECK-NOT: @llvm.global_ctors
+; CHECK-NOT: @llvm.global_dtors
+
 ; CHECK-LABEL: amdgpu_kernel void @amdgcn.device.init() #0
 ; CHECK-NEXT: call void @foo
+; CHECK-NEXT: ret void
 
 ; CHECK-LABEL: amdgpu_kernel void @amdgcn.device.fini() #1
 ; CHECK-NEXT: call void @bar
+; CHECK-NEXT: ret void
+
+; CHECK-NOT: amdgcn.device.
 
 ; CHECK-VIS: FUNC   GLOBAL PROTECTED {{.*}} amdgcn.device.init
 ; CHECK-VIS: OBJECT GLOBAL DEFAULT {{.*}} amdgcn.device.init.kd