[PATCH] D60220: [CUDA][Windows] Final fix for bug 38811 (Step 3 of 3)

[Evgeny Mankov via Phabricator via cfe-commits]

emankov added a comment.

In D60220#1725633 <https://reviews.llvm.org/D60220#1725633>, @dim wrote:

>   $ cat check-isnan.cpp
>   #include <math.h>
>  
>   int check_isnan(double d)
>   {
>     return ::__isnan(d);
>   }
>   $ clang -c check-isnan.cpp
>   Why can't the regular `isnan` be used instead?  Or is this a CUDA-specific requirement?  (Apologies, but I know next to nothing about CUDA :) )




1. `#include "cuda_runtime.h"`
2. as long as `__isnan` is a devide function, it should be called from `__devide__` or `__global__` function
3. `clang -c check-isnan.cpp -x cuda`


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60220/new/

https://reviews.llvm.org/D60220