[CUDA] Implement atomicInc and atomicDec builtins

These functions cannot be implemented as atomicrmw or cmpxchg
instructions, so they are implemented as a call to the NVVM intrinsics
@llvm.nvvm.atomic.load.inc.32.p0i32 and
@llvm.nvvm.atomic.load.dec.32.p0i32.

Patch by Jason Henline.

Reviewers: jlebar

Differential Revision: http://reviews.llvm.org/D18322

llvm-svn: 264009

1 files changed, 16 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 858a62d04b0..bebd78c2937 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -7439,6 +7439,22 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
     return Builder.CreateCall(FnALAF32, {Ptr, Val});
   }
 
+  case NVPTX::BI__nvvm_atom_inc_gen_ui: {
+    Value *Ptr = EmitScalarExpr(E->getArg(0));
+    Value *Val = EmitScalarExpr(E->getArg(1));
+    Value *FnALI32 =
+        CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_inc_32, Ptr->getType());
+    return Builder.CreateCall(FnALI32, {Ptr, Val});
+  }
+
+  case NVPTX::BI__nvvm_atom_dec_gen_ui: {
+    Value *Ptr = EmitScalarExpr(E->getArg(0));
+    Value *Val = EmitScalarExpr(E->getArg(1));
+    Value *FnALD32 =
+        CGM.getIntrinsic(Intrinsic::nvvm_atomic_load_dec_32, Ptr->getType());
+    return Builder.CreateCall(FnALD32, {Ptr, Val});
+  }
+
   default:
     return nullptr;
   }