[PATCH] D60141: [HIP-Clang] Fat binary should not be produced for non GPU code

[Aaron Enye Shi via Phabricator via cfe-commits]

ashi1 created this revision.
ashi1 added a reviewer: yaxunl.
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Do not produce Fat binary functions for HIP when no device code is present.


Repository:
  rC Clang

https://reviews.llvm.org/D60141

Files:
  lib/CodeGen/CGCUDANV.cpp
  test/CodeGenCUDA/device-stub.cu


Index: test/CodeGenCUDA/device-stub.cu
===================================================================
--- test/CodeGenCUDA/device-stub.cu
+++ test/CodeGenCUDA/device-stub.cu
@@ -228,14 +228,21 @@
 // device-side globals, but we still need to register GPU binary.
 // Skip GPU binary string first.
 // CUDANOGLOBALS: @{{.*}} = private constant{{.*}}
-// HIPNOGLOBALS: @{{.*}} = internal constant{{.*}}
+// HIPNOGLOBALS-NOT: @{{.*}} = internal constant{{.*}}
 // NOGLOBALS-NOT: define internal void @__{{.*}}_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
-// NOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
+// CUDANOGLOBALS: define internal void @__[[PREFIX:cuda|hip]]_module_ctor
+// CUDANOGLOBALS: call{{.*}}[[PREFIX]]RegisterFatBinary{{.*}}__[[PREFIX]]_fatbin_wrapper
 // NOGLOBALS-NOT: call void @__[[PREFIX]]_register_globals
-// NOGLOBALS: define internal void @__[[PREFIX]]_module_dtor
-// NOGLOBALS: call void @__[[PREFIX]]UnregisterFatBinary
+// 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
+

 // There should be no constructors/destructors if we have no GPU binary.
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_register_globals
 // NOGPUBIN-NOT: define internal void @__[[PREFIX]]_module_ctor
Index: lib/CodeGen/CGCUDANV.cpp
===================================================================
--- lib/CodeGen/CGCUDANV.cpp
+++ lib/CodeGen/CGCUDANV.cpp
@@ -472,13 +472,15 @@
   StringRef CudaGpuBinaryFileName = CGM.getCodeGenOpts().CudaGpuBinaryFileName;
   if (CudaGpuBinaryFileName.empty() && !IsHIP)
     return nullptr;
+  if (IsHIP && EmittedKernels.empty() && DeviceVars.empty())
+    return nullptr;

   // void __{cuda|hip}_register_globals(void* handle);
   llvm::Function *RegisterGlobalsFunc = makeRegisterGlobalsFn();
   // We always need a function to pass in as callback. Create a dummy
   // implementation if we don't need to register anything.
   if (RelocatableDeviceCode && !RegisterGlobalsFunc)
     RegisterGlobalsFunc = makeDummyFunction(getRegisterGlobalsFnTy());

   // void ** __{cuda|hip}RegisterFatBinary(void *);
   llvm::FunctionCallee RegisterFatbinFunc = CGM.CreateRuntimeFunction(


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D60141.193328.patch
Type: text/x-patch
Size: 2679 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20190402/ebfb328e/attachment-0001.bin>