[CUDA] Implemented __nvvm_atom_*_gen_* builtins.
Integer variants are implemented as atomicrmw or cmpxchg instructions.
Atomic add for floating point (__nvvm_atom_add_gen_f()) is implemented
as a call to an overloaded @llvm.nvvm.atomic.load.add.f32.* LVVM
intrinsic.
Differential Revision: http://reviews.llvm.org/D10666
llvm-svn: 240669
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 8c62829..0dea3a8 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -2600,6 +2600,7 @@
llvm::Value *EmitPPCBuiltinExpr(unsigned BuiltinID, const CallExpr *E);
llvm::Value *EmitAMDGPUBuiltinExpr(unsigned BuiltinID, const CallExpr *E);
llvm::Value *EmitSystemZBuiltinExpr(unsigned BuiltinID, const CallExpr *E);
+ llvm::Value *EmitNVPTXBuiltinExpr(unsigned BuiltinID, const CallExpr *E);
llvm::Value *EmitObjCProtocolExpr(const ObjCProtocolExpr *E);
llvm::Value *EmitObjCStringLiteral(const ObjCStringLiteral *E);