[NVPTX] Implement __nvvm_atom_add_gen_d builtin.
Summary:
This just seems to have been an oversight. We already supported the f64
atomic add with an explicit scope (e.g. "cta"), but not the scopeless
version.
Reviewers: tra
Subscribers: jholewinski, sanjoy, cfe-commits, llvm-commits, hiraditya
Differential Revision: https://reviews.llvm.org/D39638
llvm-svn: 317623
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index f1b8e2e..369240f 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -9554,6 +9554,16 @@
return Builder.CreateCall(FnALAF32, {Ptr, Val});
}
+ case NVPTX::BI__nvvm_atom_add_gen_d: {
+ Value *Ptr = EmitScalarExpr(E->getArg(0));
+ Value *Val = EmitScalarExpr(E->getArg(1));
+ // atomicrmw only deals with integer arguments, so we need to use
+ // LLVM's nvvm_atomic_load_add_f64 intrinsic.
+ Value *FnALAF64 =
+ CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_add_f64, Ptr->getType());
+ return Builder.CreateCall(FnALAF64, {Ptr, Val});
+ }
+
case NVPTX::BI__nvvm_atom_inc_gen_ui: {
Value *Ptr = EmitScalarExpr(E->getArg(0));
Value *Val = EmitScalarExpr(E->getArg(1));