4 files changed, 11 insertions, 12 deletions
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index b1feefe9f0d..c70a447303f 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -2620,8 +2620,8 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
         Arg));
   }
   case Builtin::BIprintf:
-    if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice)
-      return EmitCUDADevicePrintfCallExpr(E, ReturnValue);
+    if (getTarget().getTriple().isNVPTX())
+      return EmitNVPTXDevicePrintfCallExpr(E, ReturnValue);
     break;
   case Builtin::BI__builtin_canonicalize:
   case Builtin::BI__builtin_canonicalizef:
diff --git a/clang/lib/CodeGen/CGCUDABuiltin.cpp b/clang/lib/CodeGen/CGGPUBuiltin.cpp
index 44dd003757a..48156b1b26b 100644
--- a/clang/lib/CodeGen/CGCUDABuiltin.cpp
+++ b/clang/lib/CodeGen/CGGPUBuiltin.cpp
@@ -1,4 +1,4 @@
-//===----- CGCUDABuiltin.cpp - Codegen for CUDA builtins ------------------===//
+//===------ CGGPUBuiltin.cpp - Codegen for GPU builtins -------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -7,8 +7,8 @@
 //
 //===----------------------------------------------------------------------===//
 //
-// Generates code for built-in CUDA calls which are not runtime-specific.
-// (Runtime-specific codegen lives in CGCUDARuntime.)
+// Generates code for built-in GPU calls which are not runtime-specific.
+// (Runtime-specific codegen lives in programming model specific files.)
 //
 //===----------------------------------------------------------------------===//
 
@@ -67,10 +67,9 @@ static llvm::Function *GetVprintfDeclaration(llvm::Module &M) {
 // Note that by the time this function runs, E's args have already undergone the
 // standard C vararg promotion (short -> int, float -> double, etc.).
 RValue
-CodeGenFunction::EmitCUDADevicePrintfCallExpr(const CallExpr *E,
-                                              ReturnValueSlot ReturnValue) {
-  assert(getLangOpts().CUDA);
-  assert(getLangOpts().CUDAIsDevice);
+CodeGenFunction::EmitNVPTXDevicePrintfCallExpr(const CallExpr *E,
+                                               ReturnValueSlot ReturnValue) {
+  assert(getTarget().getTriple().isNVPTX());
   assert(E->getBuiltinCallee() == Builtin::BIprintf);
   assert(E->getNumArgs() >= 1); // printf always has at least one arg.
 
diff --git a/clang/lib/CodeGen/CMakeLists.txt b/clang/lib/CodeGen/CMakeLists.txt
index 4fbf9f22a98..1e9a43af522 100644
--- a/clang/lib/CodeGen/CMakeLists.txt
+++ b/clang/lib/CodeGen/CMakeLists.txt
@@ -36,7 +36,6 @@ add_clang_library(clangCodeGen
   CGAtomic.cpp
   CGBlocks.cpp
   CGBuiltin.cpp
-  CGCUDABuiltin.cpp
   CGCUDANV.cpp
   CGCUDARuntime.cpp
   CGCXX.cpp
@@ -55,6 +54,7 @@ add_clang_library(clangCodeGen
   CGExprComplex.cpp
   CGExprConstant.cpp
   CGExprScalar.cpp
+  CGGPUBuiltin.cpp
   CGLoopInfo.cpp
   CGObjC.cpp
   CGObjCGNU.cpp
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 8d7fd3f80ba..098767e23e7 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -3106,8 +3106,8 @@ public:
   RValue EmitCUDAKernelCallExpr(const CUDAKernelCallExpr *E,
                                 ReturnValueSlot ReturnValue);
 
-  RValue EmitCUDADevicePrintfCallExpr(const CallExpr *E,
-                                      ReturnValueSlot ReturnValue);
+  RValue EmitNVPTXDevicePrintfCallExpr(const CallExpr *E,
+                                       ReturnValueSlot ReturnValue);
 
   RValue EmitBuiltinExpr(const FunctionDecl *FD,
                          unsigned BuiltinID, const CallExpr *E,