Add .stub to kernel stub function name so that it is different from kernel
name in device code. This is necessary to let debugger find correct symbol
for kernel.
Differential Revision: https://reviews.llvm.org/D58518
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@354948
91177308-0d34-0410-b5e6-
96231b3b80d8
void CGNVCUDARuntime::emitDeviceStub(CodeGenFunction &CGF,
FunctionArgList &Args) {
assert(getDeviceSideName(CGF.CurFuncDecl) == CGF.CurFn->getName() ||
+ getDeviceSideName(CGF.CurFuncDecl) + ".stub" == CGF.CurFn->getName() ||
CGF.CGM.getContext().getTargetInfo().getCXXABI() !=
CGF.CGM.getContext().getAuxTargetInfo()->getCXXABI());
// Keep the first result in the case of a mangling collision.
const auto *ND = cast<NamedDecl>(GD.getDecl());
- auto Result =
- Manglings.insert(std::make_pair(getMangledNameImpl(*this, GD, ND), GD));
+ std::string MangledName = getMangledNameImpl(*this, GD, ND);
+
+ // Postfix kernel stub names with .stub to differentiate them from kernel
+ // names in device binaries. This is to facilitate the debugger to find
+ // the correct symbols for kernels in the device binary.
+ if (auto *FD = dyn_cast<FunctionDecl>(GD.getDecl()))
+ if (getLangOpts().HIP && !getLangOpts().CUDAIsDevice &&
+ FD->hasAttr<CUDAGlobalAttr>())
+ MangledName = MangledName + ".stub";
+
+ auto Result = Manglings.insert(std::make_pair(MangledName, GD));
return MangledDeclNames[CanonicalGD] = Result.first->first();
}
--- /dev/null
+// RUN: echo "GPU binary would be here" > %t
+
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s \
+// RUN: -fcuda-include-gpubinary %t -o - -x hip\
+// RUN: | FileCheck -allow-deprecated-dag-overlap %s --check-prefixes=CHECK
+
+#include "Inputs/cuda.h"
+
+template<class T>
+__global__ void kernelfunc() {}
+
+// CHECK-LABEL: define{{.*}}@_Z8hostfuncv()
+// CHECK: call void @[[STUB:_Z10kernelfuncIiEvv.stub]]()
+void hostfunc(void) { kernelfunc<int><<<1, 1>>>(); }
+
+// CHECK: define{{.*}}@[[STUB]]
+// CHECK: call{{.*}}@hipLaunchByPtr{{.*}}@[[STUB]]
+
+// CHECK-LABEL: define{{.*}}@__hip_register_globals
+// CHECK: call{{.*}}@__hipRegisterFunction{{.*}}@[[STUB]]