[HIP-Clang] Fat binary should not be produced for non GPU code 2

Also for CUDA, we need to disable producing these fat binary functions when there is no GPU code.

Reviewers: yaxunl, tra

Differential Revision: https://reviews.llvm.org/D60141


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@357526 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/CGCUDANV.cpp

@@ -468,11 +468,13 @@ llvm::Function *CGNVCUDARuntime::makeRegisterGlobalsFn() {
 /// \endcode
 llvm::Function *CGNVCUDARuntime::makeModuleCtorFunction() {
   bool IsHIP = CGM.getLangOpts().HIP;
+  bool IsCUDA = CGM.getLangOpts().CUDA;
   // No need to generate ctors/dtors if there is no GPU binary.
   StringRef CudaGpuBinaryFileName = CGM.getCodeGenOpts().CudaGpuBinaryFileName;
   if (CudaGpuBinaryFileName.empty() && !IsHIP)
     return nullptr;
-  if (IsHIP && EmittedKernels.empty() && DeviceVars.empty())
+  if ( (IsHIP || (IsCUDA && !RelocatableDeviceCode) )
+       && EmittedKernels.empty() && DeviceVars.empty())
     return nullptr;
 
   // void __{cuda|hip}_register_globals(void* handle);

test/CodeGenCUDA/device-stub.cu

@@ -227,20 +227,14 @@ void hostfunc(void) { kernelfunc<<<1, 1>>>(1, 1, 1); }
 // There should be no __[[PREFIX]]_register_globals if we have no
 // device-side globals, but we still need to register GPU binary.
 // Skip GPU binary string first.
-// CUDANOGLOBALS: @{{.*}} = private constant{{.*}}
+// CUDANOGLOBALS-NOT: @{{.*}} = private constant{{.*}}
 // HIPNOGLOBALS-NOT: @{{.*}} = internal constant{{.*}}
 // NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
-// CUDANOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
-// CUDANOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// NOGLOBALS-NOT: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// NOGLOBALS-NOT: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
 // NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
-// CUDANOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
-// CUDANOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
-
-// There should be no fat binary functions when no device-code is found for HIP.
-// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
-// HIPNOGLOBALS-NOT: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
-// HIPNOGLOBALS-NOT: define internal void @__[[PREFIX]]_module_dtor
-// HIPNOGLOBALS-NOT: call void @__[[PREFIX]]UnregisterFatBinary
+// NOGLOBALS-NOT: define internal void @__[[PREFIX]]_module_dtor
+// NOGLOBALS-NOT: call void @__[[PREFIX]]UnregisterFatBinary
 
 // There should be no constructors/destructors if we have no GPU binary.
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals