AMDGPU: Handle structs directly in AMDGPUABIInfo

Structs are currently handled as pointer + byval, which makes AMDGPU
LLVM backend generate incorrect code when structs are used. This patch
changes struct argument to be handled directly and without flattening,
which Clover (Mesa 3D Gallium OpenCL state tracker) will be able to
handle. Flattening would expand the struct to individual elements and
pass each as a separate argument, which Clover can not
handle. Furthermore, such expansion does not fit the OpenCL
programming model which requires to explicitely specify each argument
index, size and memory location.

Patch by Vedran Miletić

llvm-svn: 279463

1 files changed, 41 insertions, 1 deletions

diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index bdf3e4b1eae..759e3d6f406 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -6876,10 +6876,50 @@ public:
 
 namespace {
 
+class AMDGPUABIInfo final : public DefaultABIInfo {
+public:
+  explicit AMDGPUABIInfo(CodeGen::CodeGenTypes &CGT) : DefaultABIInfo(CGT) {}
+
+private:
+  ABIArgInfo classifyArgumentType(QualType Ty) const;
+
+  void computeInfo(CGFunctionInfo &FI) const override;
+};
+
+void AMDGPUABIInfo::computeInfo(CGFunctionInfo &FI) const {
+  if (!getCXXABI().classifyReturnType(FI))
+    FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
+
+  unsigned CC = FI.getCallingConvention();
+  for (auto &Arg : FI.arguments())
+    if (CC == llvm::CallingConv::AMDGPU_KERNEL)
+      Arg.info = classifyArgumentType(Arg.type);
+    else
+      Arg.info = DefaultABIInfo::classifyArgumentType(Arg.type);
+}
+
+/// \brief Classify argument of given type \p Ty.
+ABIArgInfo AMDGPUABIInfo::classifyArgumentType(QualType Ty) const {
+  llvm::StructType *StrTy = dyn_cast<llvm::StructType>(CGT.ConvertType(Ty));
+  if (!StrTy) {
+    return DefaultABIInfo::classifyArgumentType(Ty);
+  }
+
+  // Coerce single element structs to its element.
+  if (StrTy->getNumElements() == 1) {
+    return ABIArgInfo::getDirect();
+  }
+
+  // If we set CanBeFlattened to true, CodeGen will expand the struct to its
+  // individual elements, which confuses the Clover OpenCL backend; therefore we
+  // have to set it to false here. Other args of getDirect() are just defaults.
+  return ABIArgInfo::getDirect(nullptr, 0, nullptr, false);
+}
+
 class AMDGPUTargetCodeGenInfo : public TargetCodeGenInfo {
 public:
   AMDGPUTargetCodeGenInfo(CodeGenTypes &CGT)
-    : TargetCodeGenInfo(new DefaultABIInfo(CGT)) {}
+    : TargetCodeGenInfo(new AMDGPUABIInfo(CGT)) {}
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
                            CodeGen::CodeGenModule &M) const override;
   unsigned getOpenCLKernelCallingConv() const override;