Merge branch 'users/chapuni/cov/merge/region_segment' into users/chapuni/cov/merge/forfile-baseusers/chapuni/cov/merge/forfile-base

1 files changed, 37 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/Targets/SPIR.cpp b/clang/lib/CodeGen/Targets/SPIR.cpp
index a48fe9d..5c75e98 100644
--- a/clang/lib/CodeGen/Targets/SPIR.cpp
+++ b/clang/lib/CodeGen/Targets/SPIR.cpp
@@ -64,6 +64,8 @@ public:
   void setCUDAKernelCallingConvention(const FunctionType *&FT) const override;
   LangAS getGlobalVarAddressSpace(CodeGenModule &CGM,
                                   const VarDecl *D) const override;
+  void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
+                           CodeGen::CodeGenModule &M) const override;
   llvm::SyncScope::ID getLLVMSyncScopeID(const LangOptions &LangOpts,
                                          SyncScope Scope,
                                          llvm::AtomicOrdering Ordering,
@@ -245,6 +247,41 @@ SPIRVTargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
   return DefaultGlobalAS;
 }
 
+void SPIRVTargetCodeGenInfo::setTargetAttributes(
+    const Decl *D, llvm::GlobalValue *GV, CodeGen::CodeGenModule &M) const {
+  if (!M.getLangOpts().HIP ||
+      M.getTarget().getTriple().getVendor() != llvm::Triple::AMD)
+    return;
+  if (GV->isDeclaration())
+    return;
+
+  auto F = dyn_cast<llvm::Function>(GV);
+  if (!F)
+    return;
+
+  auto FD = dyn_cast_or_null<FunctionDecl>(D);
+  if (!FD)
+    return;
+  if (!FD->hasAttr<CUDAGlobalAttr>())
+    return;
+
+  unsigned N = M.getLangOpts().GPUMaxThreadsPerBlock;
+  if (auto FlatWGS = FD->getAttr<AMDGPUFlatWorkGroupSizeAttr>())
+    N = FlatWGS->getMax()->EvaluateKnownConstInt(M.getContext()).getExtValue();
+
+  // We encode the maximum flat WG size in the first component of the 3D
+  // max_work_group_size attribute, which will get reverse translated into the
+  // original AMDGPU attribute when targeting AMDGPU.
+  auto Int32Ty = llvm::IntegerType::getInt32Ty(M.getLLVMContext());
+  llvm::Metadata *AttrMDArgs[] = {
+      llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(Int32Ty, N)),
+      llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(Int32Ty, 1)),
+      llvm::ConstantAsMetadata::get(llvm::ConstantInt::get(Int32Ty, 1))};
+
+  F->setMetadata("max_work_group_size",
+                 llvm::MDNode::get(M.getLLVMContext(), AttrMDArgs));
+}
+
 llvm::SyncScope::ID
 SPIRVTargetCodeGenInfo::getLLVMSyncScopeID(const LangOptions &, SyncScope Scope,
                                            llvm::AtomicOrdering,