Index: include/clang/Driver/CC1Options.td
===================================================================
--- include/clang/Driver/CC1Options.td
+++ include/clang/Driver/CC1Options.td
@@ -287,9 +287,13 @@
   HelpText<"Emit complete constructors and destructors as aliases when possible">;
 def mlink_bitcode_file : Separate<["-"], "mlink-bitcode-file">,
   HelpText<"Link the given bitcode file before performing optimizations.">;
-def mlink_cuda_bitcode : Separate<["-"], "mlink-cuda-bitcode">,
+
+def mlink_builtin_bitcode : Separate<["-"], "mlink-builtin-bitcode">,
   HelpText<"Link and internalize needed symbols from the given bitcode file "
            "before performing optimizations.">;
+def mlink_cuda_bitcode : Separate<["-"], "mlink-cuda-bitcode">,
+  Alias<mlink_builtin_bitcode>;
+
 def vectorize_loops : Flag<["-"], "vectorize-loops">,
   HelpText<"Run the Loop vectorization passes">;
 def vectorize_slp : Flag<["-"], "vectorize-slp">,
Index: lib/Driver/ToolChains/Cuda.cpp
===================================================================
--- lib/Driver/ToolChains/Cuda.cpp
+++ lib/Driver/ToolChains/Cuda.cpp
@@ -621,7 +621,7 @@
     return;
   }
 
-  CC1Args.push_back("-mlink-cuda-bitcode");
+  CC1Args.push_back("-mlink-builtin-bitcode");
   CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
 
   // Libdevice in CUDA-7.0 requires PTX version that's more recent than LLVM
@@ -667,7 +667,7 @@
       SmallString<128> LibOmpTargetFile(LibraryPath);
       llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
       if (llvm::sys::fs::exists(LibOmpTargetFile)) {
-        CC1Args.push_back("-mlink-cuda-bitcode");
+        CC1Args.push_back("-mlink-builtin-bitcode");
         CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
         FoundBCLibrary = true;
         break;
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -912,10 +912,10 @@
   Opts.RelaxELFRelocations = Args.hasArg(OPT_mrelax_relocations);
   Opts.DebugCompilationDir = Args.getLastArgValue(OPT_fdebug_compilation_dir);
   for (auto *A :
-       Args.filtered(OPT_mlink_bitcode_file, OPT_mlink_cuda_bitcode)) {
+       Args.filtered(OPT_mlink_bitcode_file, OPT_mlink_builtin_bitcode)) {
     CodeGenOptions::BitcodeFileToLink F;
     F.Filename = A->getValue();
-    if (A->getOption().matches(OPT_mlink_cuda_bitcode)) {
+    if (A->getOption().matches(OPT_mlink_builtin_bitcode)) {
       F.LinkFlags = llvm::Linker::Flags::LinkOnlyNeeded;
       // When linking CUDA bitcode, propagate function attributes so that
       // e.g. libdevice gets fast-math attrs if we're building with fast-math.
Index: test/CodeGenCUDA/link-device-bitcode.cu
===================================================================
--- test/CodeGenCUDA/link-device-bitcode.cu
+++ test/CodeGenCUDA/link-device-bitcode.cu
@@ -11,13 +11,19 @@
 //
 // Make sure function in device-code gets linked in and internalized.
 // RUN: %clang_cc1 -triple nvptx-unknown-cuda -fcuda-is-device \
+// RUN:    -mlink-builtin-bitcode %t.bc  -emit-llvm \
+// RUN:    -disable-llvm-passes -o - %s \
+// RUN:    | FileCheck %s -check-prefix CHECK-IR
+
+// Make sure legacy flag name works
+// RUN: %clang_cc1 -triple nvptx-unknown-cuda -fcuda-is-device \
 // RUN:    -mlink-cuda-bitcode %t.bc  -emit-llvm \
 // RUN:    -disable-llvm-passes -o - %s \
 // RUN:    | FileCheck %s -check-prefix CHECK-IR
 //
 // Make sure we can link two bitcode files.
 // RUN: %clang_cc1 -triple nvptx-unknown-cuda -fcuda-is-device \
-// RUN:    -mlink-cuda-bitcode %t.bc -mlink-cuda-bitcode %t-2.bc \
+// RUN:    -mlink-builtin-bitcode %t.bc -mlink-builtin-bitcode %t-2.bc \
 // RUN:    -emit-llvm -disable-llvm-passes -o - %s \
 // RUN:    | FileCheck %s -check-prefix CHECK-IR -check-prefix CHECK-IR-2
 //
@@ -30,7 +36,7 @@
 //
 // Make sure NVVMReflect pass is enabled in NVPTX back-end.
 // RUN: %clang_cc1 -triple nvptx-unknown-cuda -fcuda-is-device \
-// RUN:    -mlink-cuda-bitcode %t.bc -S -o /dev/null %s \
+// RUN:    -mlink-builtin-bitcode %t.bc -S -o /dev/null %s \
 // RUN:    -mllvm -debug-pass=Structure 2>&1 \
 // RUN:    | FileCheck %s -check-prefix CHECK-REFLECT
 
Index: test/CodeGenCUDA/propagate-metadata.cu
===================================================================
--- test/CodeGenCUDA/propagate-metadata.cu
+++ test/CodeGenCUDA/propagate-metadata.cu
@@ -1,5 +1,5 @@
 // Check that when we link a bitcode module into a file using
-// -mlink-cuda-bitcode, we apply the same attributes to the functions in that
+// -mlink-builtin-bitcode, we apply the same attributes to the functions in that
 // bitcode module as we apply to functions we generate.
 //
 // In particular, we check that ftz and unsafe-math are propagated into the
@@ -14,17 +14,17 @@
 // RUN: %clang_cc1 -x c++ -emit-llvm-bc -ftrapping-math -DLIB \
 // RUN:   %s -o %t.bc -triple nvptx-unknown-unknown
 
-// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-cuda-bitcode %t.bc -o - \
+// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-builtin-bitcode %t.bc -o - \
 // RUN:   -fno-trapping-math -fcuda-is-device -triple nvptx-unknown-unknown \
 // RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=NOFTZ --check-prefix=NOFAST
 
-// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-cuda-bitcode %t.bc \
+// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-builtin-bitcode %t.bc \
 // RUN:   -fno-trapping-math -fcuda-flush-denormals-to-zero -o - \
 // RUN:   -fcuda-is-device -triple nvptx-unknown-unknown \
 // RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=FTZ \
 // RUN:   --check-prefix=NOFAST
 
-// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-cuda-bitcode %t.bc \
+// RUN: %clang_cc1 -x cuda %s -emit-llvm -mlink-builtin-bitcode %t.bc \
 // RUN:   -fno-trapping-math -fcuda-flush-denormals-to-zero -o - \
 // RUN:   -fcuda-is-device -menable-unsafe-fp-math -triple nvptx-unknown-unknown \
 // RUN: | FileCheck %s --check-prefix=CHECK --check-prefix=FAST
Index: test/Driver/cuda-detect.cu
===================================================================
--- test/Driver/cuda-detect.cu
+++ test/Driver/cuda-detect.cu
@@ -145,8 +145,8 @@
 
 // COMMON: "-triple" "nvptx-nvidia-cuda"
 // COMMON-SAME: "-fcuda-is-device"
-// LIBDEVICE-SAME: "-mlink-cuda-bitcode"
-// NOLIBDEVICE-NOT: "-mlink-cuda-bitcode"
+// LIBDEVICE-SAME: "-mlink-builtin-bitcode"
+// NOLIBDEVICE-NOT: "-mlink-builtin-bitcode"
 // LIBDEVICE20-SAME: libdevice.compute_20.10.bc
 // LIBDEVICE30-SAME: libdevice.compute_30.10.bc
 // LIBDEVICE35-SAME: libdevice.compute_35.10.bc
Index: test/Driver/openmp-offload-gpu.c
===================================================================
--- test/Driver/openmp-offload-gpu.c
+++ test/Driver/openmp-offload-gpu.c
@@ -152,7 +152,7 @@
 // RUN:   -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
 // RUN:   | FileCheck -check-prefix=CHK-BCLIB %s
 
-// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-cuda-bitcode{{.*}}libomptarget-nvptx-sm_20.bc
+// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-sm_20.bc
 // CHK-BCLIB-NOT: {{error:|warning:}}
 
 /// ###########################################################################