r357520 - [HIP-Clang] Fat binary should not be produced for non GPU code
Aaron Enye Shi via cfe-commits
cfe-commits at lists.llvm.org
Tue Apr 2 13:10:19 PDT 2019
Author: aaronenyeshi
Date: Tue Apr 2 13:10:18 2019
New Revision: 357520
URL: http://llvm.org/viewvc/llvm-project?rev=357520&view=rev
Log:
[HIP-Clang] Fat binary should not be produced for non GPU code
Skip producing the fat binary functions for HIP when no device code is present.
Reviewers: yaxunl
Differential Review: https://reviews.llvm.org/D60141
Modified:
cfe/trunk/lib/CodeGen/CGCUDANV.cpp
cfe/trunk/test/CodeGenCUDA/device-stub.cu
Modified: cfe/trunk/lib/CodeGen/CGCUDANV.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/CodeGen/CGCUDANV.cpp?rev=357520&r1=357519&r2=357520&view=diff
==============================================================================
--- cfe/trunk/lib/CodeGen/CGCUDANV.cpp (original)
+++ cfe/trunk/lib/CodeGen/CGCUDANV.cpp Tue Apr 2 13:10:18 2019
@@ -472,6 +472,8 @@ llvm::Function *CGNVCUDARuntime::makeMod
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();
Modified: cfe/trunk/test/CodeGenCUDA/device-stub.cu
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGenCUDA/device-stub.cu?rev=357520&r1=357519&r2=357520&view=diff
==============================================================================
--- cfe/trunk/test/CodeGenCUDA/device-stub.cu (original)
+++ cfe/trunk/test/CodeGenCUDA/device-stub.cu Tue Apr 2 13:10:18 2019
@@ -228,13 +228,19 @@ void hostfunc(void) { kernelfunc<<<1, 1>
// 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
More information about the cfe-commits
mailing list