[CUDA] work around more __noinline__ conflicts with libc++

clang/lib/Headers/CMakeLists.txt

@@ -283,10 +283,12 @@ set(files
   )
 
 set(cuda_wrapper_files
+  cuda_wrappers/__config
   cuda_wrappers/algorithm
   cuda_wrappers/cmath
   cuda_wrappers/complex
   cuda_wrappers/new
+  cuda_wrappers/string
 )
 
 set(cuda_wrapper_bits_files

clang/lib/Headers/cuda_wrappers/__config

@@ -0,0 +1,10 @@
+// CUDA headers define __noinline__ which interferes with libc++'s use of
+// `__attribute((__noinline__))`. In order to avoid compilation error,
+// temporarily unset __noinline__ when we include affected libc++ header.
+
+#pragma push_macro("__noinline__")
+#undef __noinline__
+#define __noinline__ __noinline__
+#include_next <__config>
+
+#pragma pop_macro("__noinline__")

clang/lib/Headers/cuda_wrappers/string

@@ -0,0 +1,10 @@
+// CUDA headers define __noinline__ which interferes with libc++'s use of
+// `__attribute((__noinline__))`. In order to avoid compilation error,
+// temporarily unset __noinline__ when we include affected libc++ header.
+
+#pragma push_macro("__noinline__")
+#undef __noinline__
+#define __noinline__ __noinline__
+#include_next <string>
+
+#pragma pop_macro("__noinline__")