[CUDA][HIP] Externalize kernels in anonymous name space

kernels in anonymous name space needs to have unique name
to avoid duplicate symbols.

Fixes: https://github.com/llvm/llvm-project/issues/54560

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D123353

diff --git a/clang/include/clang/AST/ASTContext.h b/clang/include/clang/AST/ASTContext.h
index b00472e..490128a 100644 (file)
--- a/clang/include/clang/AST/ASTContext.h
+++ b/clang/include/clang/AST/ASTContext.h
@@ -3289,11 +3289,11 @@ public:
   /// Return a new OMPTraitInfo object owned by this context.
   OMPTraitInfo &getNewOMPTraitInfo();
 
-  /// Whether a C++ static variable may be externalized.
-  bool mayExternalizeStaticVar(const Decl *D) const;
+  /// Whether a C++ static variable or CUDA/HIP kernel may be externalized.
+  bool mayExternalize(const Decl *D) const;
 
-  /// Whether a C++ static variable should be externalized.
-  bool shouldExternalizeStaticVar(const Decl *D) const;
+  /// Whether a C++ static variable or CUDA/HIP kernel should be externalized.
+  bool shouldExternalize(const Decl *D) const;
 
   StringRef getCUIDHash() const;
 

diff --git a/clang/lib/AST/ASTContext.cpp b/clang/lib/AST/ASTContext.cpp
index eeaff7d..036f970 100644 (file)
--- a/clang/lib/AST/ASTContext.cpp
+++ b/clang/lib/AST/ASTContext.cpp
@@ -11328,7 +11328,7 @@ static GVALinkage adjustGVALinkageForAttributes(const ASTContext &Context,
     // name between the host and device compilation which is the same for the
     // same compilation unit whereas different among different compilation
     // units.
-    if (Context.shouldExternalizeStaticVar(D))
+    if (Context.shouldExternalize(D))
       return GVA_StrongExternal;
   }
   return L;
@@ -12277,7 +12277,7 @@ operator<<(const StreamingDiagnostic &DB,
   return DB << "a prior #pragma section";
 }
 
-bool ASTContext::mayExternalizeStaticVar(const Decl *D) const {
+bool ASTContext::mayExternalize(const Decl *D) const {
   bool IsStaticVar =
       isa<VarDecl>(D) && cast<VarDecl>(D)->getStorageClass() == SC_Static;
   bool IsExplicitDeviceVar = (D->hasAttr<CUDADeviceAttr>() &&
@@ -12285,14 +12285,16 @@ bool ASTContext::mayExternalizeStaticVar(const Decl *D) const {
                              (D->hasAttr<CUDAConstantAttr>() &&
                               !D->getAttr<CUDAConstantAttr>()->isImplicit());
   // CUDA/HIP: static managed variables need to be externalized since it is
-  // a declaration in IR, therefore cannot have internal linkage.
-  return IsStaticVar &&
-         (D->hasAttr<HIPManagedAttr>() || IsExplicitDeviceVar);
+  // a declaration in IR, therefore cannot have internal linkage. Kernels in
+  // anonymous name space needs to be externalized to avoid duplicate symbols.
+  return (IsStaticVar &&
+          (D->hasAttr<HIPManagedAttr>() || IsExplicitDeviceVar)) ||
+         (D->hasAttr<CUDAGlobalAttr>() && D->isInAnonymousNamespace());
 }
 
-bool ASTContext::shouldExternalizeStaticVar(const Decl *D) const {
-  return mayExternalizeStaticVar(D) &&
-         (D->hasAttr<HIPManagedAttr>() ||
+bool ASTContext::shouldExternalize(const Decl *D) const {
+  return mayExternalize(D) &&
+         (D->hasAttr<HIPManagedAttr>() || D->hasAttr<CUDAGlobalAttr>() ||
           CUDADeviceVarODRUsedByHost.count(cast<VarDecl>(D)));
 }
 

diff --git a/clang/lib/CodeGen/CGCUDANV.cpp b/clang/lib/CodeGen/CGCUDANV.cpp
index 187817d..4390228 100644 (file)
--- a/clang/lib/CodeGen/CGCUDANV.cpp
+++ b/clang/lib/CodeGen/CGCUDANV.cpp
@@ -281,13 +281,13 @@ std::string CGNVCUDARuntime::getDeviceSideName(const NamedDecl *ND) {
     DeviceSideName = std::string(ND->getIdentifier()->getName());
 
   // Make unique name for device side static file-scope variable for HIP.
-  if (CGM.getContext().shouldExternalizeStaticVar(ND) &&
+  if (CGM.getContext().shouldExternalize(ND) &&
       CGM.getLangOpts().GPURelocatableDeviceCode &&
       !CGM.getLangOpts().CUID.empty()) {
     SmallString<256> Buffer;
     llvm::raw_svector_ostream Out(Buffer);
     Out << DeviceSideName;
-    CGM.printPostfixForExternalizedStaticVar(Out);
+    CGM.printPostfixForExternalizedDecl(Out, ND);
     DeviceSideName = std::string(Out.str());
   }
   return DeviceSideName;

diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index da03235..4efcc84 100644 (file)
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -1376,10 +1376,10 @@ static std::string getMangledNameImpl(CodeGenModule &CGM, GlobalDecl GD,
     }
 
   // Make unique name for device side static file-scope variable for HIP.
-  if (CGM.getContext().shouldExternalizeStaticVar(ND) &&
+  if (CGM.getContext().shouldExternalize(ND) &&
       CGM.getLangOpts().GPURelocatableDeviceCode &&
       CGM.getLangOpts().CUDAIsDevice && !CGM.getLangOpts().CUID.empty())
-    CGM.printPostfixForExternalizedStaticVar(Out);
+    CGM.printPostfixForExternalizedDecl(Out, ND);
   return std::string(Out.str());
 }
 
@@ -1446,8 +1446,7 @@ StringRef CodeGenModule::getMangledName(GlobalDecl GD) {
   // static device variable depends on whether the variable is referenced by
   // a host or device host function. Therefore the mangled name cannot be
   // cached.
-  if (!LangOpts.CUDAIsDevice ||
-      !getContext().mayExternalizeStaticVar(GD.getDecl())) {
+  if (!LangOpts.CUDAIsDevice || !getContext().mayExternalize(GD.getDecl())) {
     auto FoundName = MangledDeclNames.find(CanonicalGD);
     if (FoundName != MangledDeclNames.end())
       return FoundName->second;
@@ -1467,7 +1466,7 @@ StringRef CodeGenModule::getMangledName(GlobalDecl GD) {
   // directly between host- and device-compilations, the host- and
   // device-mangling in host compilation could help catching certain ones.
   assert(!isa<FunctionDecl>(ND) || !ND->hasAttr<CUDAGlobalAttr>() ||
-         getLangOpts().CUDAIsDevice ||
+         getContext().shouldExternalize(ND) || getLangOpts().CUDAIsDevice ||
          (getContext().getAuxTargetInfo() &&
           (getContext().getAuxTargetInfo()->getCXXABI() !=
            getContext().getTargetInfo().getCXXABI())) ||
@@ -6772,7 +6771,8 @@ bool CodeGenModule::stopAutoInit() {
   return false;
 }
 
-void CodeGenModule::printPostfixForExternalizedStaticVar(
-    llvm::raw_ostream &OS) const {
-  OS << "__static__" << getContext().getCUIDHash();
+void CodeGenModule::printPostfixForExternalizedDecl(llvm::raw_ostream &OS,
+                                                    const Decl *D) const {
+  OS << (isa<VarDecl>(D) ? "__static__" : ".anon.")
+     << getContext().getCUIDHash();
 }

diff --git a/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
index b6166a7..1ba592b 100644 (file)
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -1457,9 +1457,10 @@ public:
                                            TBAAAccessInfo *TBAAInfo = nullptr);
   bool stopAutoInit();
 
-  /// Print the postfix for externalized static variable for single source
-  /// offloading languages CUDA and HIP.
-  void printPostfixForExternalizedStaticVar(llvm::raw_ostream &OS) const;
+  /// Print the postfix for externalized static variable or kernels for single
+  /// source offloading languages CUDA and HIP.
+  void printPostfixForExternalizedDecl(llvm::raw_ostream &OS,
+                                       const Decl *D) const;
 
 private:
   llvm::Constant *GetOrCreateLLVMFunction(

diff --git a/clang/test/CodeGenCUDA/kernel-in-anon-ns.cu b/clang/test/CodeGenCUDA/kernel-in-anon-ns.cu
new file mode 100644 (file)
index 0000000..4243cec
--- /dev/null
+++ b/clang/test/CodeGenCUDA/kernel-in-anon-ns.cu
@@ -0,0 +1,24 @@
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fcuda-is-device -cuid=abc \
+// RUN:   -aux-triple x86_64-unknown-linux-gnu -std=c++11 -fgpu-rdc \
+// RUN:   -emit-llvm -o - -x hip %s > %t.dev
+
+// RUN: %clang_cc1 -triple x86_64-gnu-linux -cuid=abc \
+// RUN:   -aux-triple amdgcn-amd-amdhsa -std=c++11 -fgpu-rdc \
+// RUN:   -emit-llvm -o - -x hip %s > %t.host
+
+// RUN: cat %t.dev %t.host | FileCheck %s
+
+#include "Inputs/cuda.h"
+
+// CHECK: define weak_odr {{.*}}void @[[KERN:_ZN12_GLOBAL__N_16kernelEv\.anon\.b04fd23c98500190]](
+// CHECK: @[[STR:.*]] = {{.*}} c"[[KERN]]\00"
+// CHECK: call i32 @__hipRegisterFunction({{.*}}@[[STR]]
+
+namespace {
+__global__ void kernel() {
+}
+}
+
+void test() {
+  kernel<<<1, 1>>>();
+}