Set calling convention for CUDA kernel

This patch sets target specific calling convention for CUDA kernels in IR.

Patch by Greg Rodgers.
Revised and lit test added by Yaxun Liu.

Differential Revision: https://reviews.llvm.org/D44747

llvm-svn: 328795

4 files changed, 16 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index 01caadba92d..148a12eac84 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -64,6 +64,7 @@ unsigned CodeGenTypes::ClangCallConvToLLVMCallConv(CallingConv CC) {
   case CC_PreserveMost: return llvm::CallingConv::PreserveMost;
   case CC_PreserveAll: return llvm::CallingConv::PreserveAll;
   case CC_Swift: return llvm::CallingConv::Swift;
+  case CC_CUDAKernel: return CGM.getTargetCodeGenInfo().getCUDAKernelCallingConv();
   }
 }
 
diff --git a/clang/lib/CodeGen/CGDebugInfo.cpp b/clang/lib/CodeGen/CGDebugInfo.cpp
index 77d832cc45b..42c0210e1df 100644
--- a/clang/lib/CodeGen/CGDebugInfo.cpp
+++ b/clang/lib/CodeGen/CGDebugInfo.cpp
@@ -1022,6 +1022,9 @@ static unsigned getDwarfCC(CallingConv CC) {
     return llvm::dwarf::DW_CC_LLVM_PreserveAll;
   case CC_X86RegCall:
     return llvm::dwarf::DW_CC_LLVM_X86RegCall;
+  case CC_CUDAKernel:
+    // ToDo: Add llvm::dwarf::DW_CC_LLVM_CUDAKernel;
+    return 0;
   }
   return 0;
 }
diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
index b6f265a3579..02dd21483b4 100644
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -431,6 +431,10 @@ unsigned TargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::SPIR_KERNEL;
 }
 
+unsigned TargetCodeGenInfo::getCUDAKernelCallingConv() const {
+  return llvm::CallingConv::C;
+}
+
 llvm::Constant *TargetCodeGenInfo::getNullPointer(const CodeGen::CodeGenModule &CGM,
     llvm::PointerType *T, QualType QT) const {
   return llvm::ConstantPointerNull::get(T);
@@ -7635,6 +7639,7 @@ public:
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
                            CodeGen::CodeGenModule &M) const override;
   unsigned getOpenCLKernelCallingConv() const override;
+  unsigned getCUDAKernelCallingConv() const override;
 
   llvm::Constant *getNullPointer(const CodeGen::CodeGenModule &CGM,
       llvm::PointerType *T, QualType QT) const override;
@@ -7722,6 +7727,10 @@ unsigned AMDGPUTargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::AMDGPU_KERNEL;
 }
 
+unsigned AMDGPUTargetCodeGenInfo::getCUDAKernelCallingConv() const {
+  return llvm::CallingConv::AMDGPU_KERNEL;
+}
+
 // Currently LLVM assumes null pointers always have value 0,
 // which results in incorrectly transformed IR. Therefore, instead of
 // emitting null pointers in private and local address spaces, a null
diff --git a/clang/lib/CodeGen/TargetInfo.h b/clang/lib/CodeGen/TargetInfo.h
index 533e14514ff..ab463c5dc6e 100644
--- a/clang/lib/CodeGen/TargetInfo.h
+++ b/clang/lib/CodeGen/TargetInfo.h
@@ -223,6 +223,9 @@ public:
   /// Get LLVM calling convention for OpenCL kernel.
   virtual unsigned getOpenCLKernelCallingConv() const;
 
+  /// Get LLVM calling convention for CUDA kernel.
+  virtual unsigned getCUDAKernelCallingConv() const;
+
   /// Get target specific null pointer.
   /// \param T is the LLVM type of the null pointer.
   /// \param QT is the clang QualType of the null pointer.