diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -299,8 +299,6 @@
     return;
   }
 
-  CC1Args.push_back("-internal-isystem");
-  CC1Args.push_back(DriverArgs.MakeArgString(getIncludePath()));
   CC1Args.push_back("-include");
   CC1Args.push_back("__clang_cuda_runtime_wrapper.h");
 }
@@ -867,6 +865,11 @@
 void CudaToolChain::AddClangSystemIncludeArgs(const ArgList &DriverArgs,
                                               ArgStringList &CC1Args) const {
   HostTC.AddClangSystemIncludeArgs(DriverArgs, CC1Args);
+
+  if (!DriverArgs.hasArg(options::OPT_nogpuinc) && CudaInstallation.isValid())
+    CC1Args.append(
+        {"-internal-isystem",
+         DriverArgs.MakeArgString(CudaInstallation.getIncludePath())});
 }
 
 void CudaToolChain::AddClangCXXStdlibIncludeArgs(const ArgList &Args,
diff --git a/clang/test/Driver/cuda-detect.cu b/clang/test/Driver/cuda-detect.cu
--- a/clang/test/Driver/cuda-detect.cu
+++ b/clang/test/Driver/cuda-detect.cu
@@ -179,10 +179,10 @@
 // LIBDEVICE50-SAME: libdevice.compute_50.10.bc
 // PTX42-SAME: "-target-feature" "+ptx42"
 // PTX60-SAME: "-target-feature" "+ptx60"
-// CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA{{[_0-9]+}}/usr/local/cuda/include"
-// NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
 // CUDAINC-SAME: "-include" "__clang_cuda_runtime_wrapper.h"
 // NOCUDAINC-NOT: "-include" "__clang_cuda_runtime_wrapper.h"
+// CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA{{[_0-9]+}}/usr/local/cuda/include"
+// NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
 // -internal-externc-isystem flags must come *after* the cuda include flags,
 // because we must search the cuda include directory first.
 // CUDAINC-SAME: "-internal-externc-isystem"