Index: lib/CodeGen/PPCGCodeGeneration.cpp
===================================================================
--- lib/CodeGen/PPCGCodeGeneration.cpp
+++ lib/CodeGen/PPCGCodeGeneration.cpp
@@ -1419,7 +1419,7 @@
   Builder.SetInsertPoint(&HostInsertPoint);
   Value *Parameters = createLaunchParameters(Kernel, F, SubtreeValues);
 
-  std::string Name = "kernel_" + std::to_string(Kernel->id);
+  std::string Name = S.getFunction().getName().str() + "_kernel_" + std::to_string(Kernel->id);
   Value *KernelString = Builder.CreateGlobalStringPtr(ASMString, Name);
   Value *NameString = Builder.CreateGlobalStringPtr(Name, Name + "_name");
   Value *GPUKernel = createCallGetKernel(KernelString, NameString);
@@ -1460,7 +1460,7 @@
 GPUNodeBuilder::createKernelFunctionDecl(ppcg_kernel *Kernel,
                                          SetVector<Value *> &SubtreeValues) {
   std::vector<Type *> Args;
-  std::string Identifier = "kernel_" + std::to_string(Kernel->id);
+  std::string Identifier = S.getFunction().getName().str() + "_kernel_" + std::to_string(Kernel->id);
 
   for (long i = 0; i < Prog->n_array; i++) {
     if (!ppcg_kernel_requires_array_argument(Kernel, i))
Index: test/GPGPU/cuda-annotations.ll
===================================================================
--- test/GPGPU/cuda-annotations.ll
+++ test/GPGPU/cuda-annotations.ll
@@ -4,11 +4,11 @@
 
 ; REQUIRES: pollyacc
 
-; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n) #0 {
+; KERNEL: define ptx_kernel void @foo_kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n) #0 {
 
 ; KERNEL: !nvvm.annotations = !{!0}
 
-; KERNEL: !0 = !{void (i8 addrspace(1)*, i64)* @kernel_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
+; KERNEL: !0 = !{void (i8 addrspace(1)*, i64)* @foo_kernel_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
Index: test/GPGPU/cuda-managed-memory-simple.ll
===================================================================
--- test/GPGPU/cuda-managed-memory-simple.ll
+++ test/GPGPU/cuda-managed-memory-simple.ll
@@ -54,7 +54,7 @@
 ; CHECK-NEXT:  %22 = getelementptr [4 x i8*], [4 x i8*]* %polly_launch_0_params, i64 0, i64 3
 ; CHECK-NEXT:  %23 = bitcast i32* %polly_launch_0_param_size_1 to i8*
 ; CHECK-NEXT:  store i8* %23, i8** %22
-; CHECK-NEXT:  %24 = call i8* @polly_getKernel(i8* getelementptr inbounds ([750 x i8], [750 x i8]* @kernel_0, i32 0, i32 0), i8* getelementptr inbounds ([9 x i8], [9 x i8]* @kernel_0_name, i32 0, i32 0))
+; CHECK-NEXT:  %24 = call i8* @polly_getKernel(i8* getelementptr inbounds ([780 x i8], [780 x i8]* @copy_kernel_0, i32 0, i32 0), i8* getelementptr inbounds ([14 x i8], [14 x i8]* @copy_kernel_0_name, i32 0, i32 0))
 ; CHECK-NEXT:  call void @polly_launchKernel(i8* %24, i32 2, i32 1, i32 32, i32 1, i32 1, i8* %polly_launch_0_params_i8ptr)
 ; CHECK-NEXT:  call void @polly_freeKernel(i8* %24)
 ; CHECK-NEXT:  call void @polly_synchronizeDevice()
Index: test/GPGPU/host-control-flow.ll
===================================================================
--- test/GPGPU/host-control-flow.ll
+++ test/GPGPU/host-control-flow.ll
@@ -42,7 +42,7 @@
 ; IR-NEXT:   %polly.loop_cond = icmp sle i64 %polly.indvar_next, 99
 ; IR-NEXT:   br i1 %polly.loop_cond, label %polly.loop_header, label %polly.loop_exit
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %c0)
+; KERNEL-IR: define ptx_kernel void @foo_kernel_0(i8 addrspace(1)* %MemRef_A, i64 %c0)
 ; KERNEL-IR-LABEL: entry:
 ; KERNEL-IR-NEXT:   %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-IR-NEXT:   %b0 = zext i32 %0 to i64
Index: test/GPGPU/kernel-params-only-some-arrays.ll
===================================================================
--- test/GPGPU/kernel-params-only-some-arrays.ll
+++ test/GPGPU/kernel-params-only-some-arrays.ll
@@ -21,7 +21,7 @@
 ; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A)
+; KERNEL: define ptx_kernel void @kernel_params_only_some_arrays_kernel_0(i8 addrspace(1)* %MemRef_A)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
@@ -36,7 +36,7 @@
 ; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_1(i8 addrspace(1)* %MemRef_B)
+; KERNEL: define ptx_kernel void @kernel_params_only_some_arrays_kernel_1(i8 addrspace(1)* %MemRef_B)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
Index: test/GPGPU/kernel-params-scop-parameter.ll
===================================================================
--- test/GPGPU/kernel-params-scop-parameter.ll
+++ test/GPGPU/kernel-params-scop-parameter.ll
@@ -9,7 +9,7 @@
 ;        A[i] += 42;
 ;    }
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n)
+; KERNEL-IR: define ptx_kernel void @kernel_params_scop_parameter_kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n)
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"