[CodeGen] NVPTX: Switch from atomic.load.add.f32 to atomicrmw fadd

llvm-svn: 365798

1 files changed, 3 insertions, 15 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 52e2d5bfb91..086785fdbac 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -13472,24 +13472,12 @@ CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID, const CallExpr *E) {
     // success flag.
     return MakeAtomicCmpXchgValue(*this, E, /*ReturnBool=*/false);
 
-  case NVPTX::BI__nvvm_atom_add_gen_f: {
-    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_f32 intrinsic for that.
-    Function *FnALAF32 =
-        CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_add_f32, Ptr->getType());
-    return Builder.CreateCall(FnALAF32, {Ptr, Val});
-  }
-
+  case NVPTX::BI__nvvm_atom_add_gen_f:
   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.
-    Function *FnALAF64 =
-        CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_add_f64, Ptr->getType());
-    return Builder.CreateCall(FnALAF64, {Ptr, Val});
+    return Builder.CreateAtomicRMW(llvm::AtomicRMWInst::FAdd, Ptr, Val,
+                                   AtomicOrdering::SequentiallyConsistent);
   }
 
   case NVPTX::BI__nvvm_atom_inc_gen_ui: {