[CUDA][Windows] Partial fix for bug 38811 (Step 1 of 3)

[emankov]

Summary

Partial fix for the clang Bug 38811 "Clang fails to compile with CUDA-9.x on Windows".

Adding defined(_WIN64) check along with existing #if defined(__LP64__) eliminates the below clang (64-bit) compilation error on Windows.

C:/GIT/LLVM/trunk/llvm-64-release-vs2017/dist/lib/clang/9.0.0\include\__clang_cuda_device_functions.h(1609,45): error GEF7559A7: no matching function for call to 'roundf'
 __DEVICE__ long lroundf(float __a) { return roundf(__a); }

[How to repro]

clang++.exe -x cuda "c:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\0_Simple\simplePrintf\simplePrintf.cu" -I"c:\ProgramData\NVIDIA Corporation\CUDA Samples\v8.0\common\inc" --cuda-gpu-arch=sm_50 --cuda-path="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0" -L"c:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\lib\x64" -lcudart.lib  -v

lib/Headers/__clang_cuda_device_functions.h

 __DEVICE__ int ilogb(double __a) { return __nv_ilogb(__a); }
 __DEVICE__ int ilogbf(float __a) { return __nv_ilogbf(__a); }
 __DEVICE__ double j0(double __a) { return __nv_j0(__a); }
 __DEVICE__ float j0f(float __a) { return __nv_j0f(__a); }
 __DEVICE__ double j1(double __a) { return __nv_j1(__a); }
 __DEVICE__ float j1f(float __a) { return __nv_j1f(__a); }
 __DEVICE__ double jn(int __n, double __a) { return __nv_jn(__n, __a); }
 __DEVICE__ float jnf(int __n, float __a) { return __nv_jnf(__n, __a); }
-#if defined(__LP64__)
+#if defined(__LP64__) || defined(_WIN64)
 __DEVICE__ long labs(long __a) { return llabs(__a); };
 #else
 __DEVICE__ long labs(long __a) { return __nv_abs(__a); };
 #endif
 __DEVICE__ double ldexp(double __a, int __b) { return __nv_ldexp(__a, __b); }
 __DEVICE__ float ldexpf(float __a, int __b) { return __nv_ldexpf(__a, __b); }
 __DEVICE__ double lgamma(double __a) { return __nv_lgamma(__a); }
 __DEVICE__ float lgammaf(float __a) { return __nv_lgammaf(__a); }

 __DEVICE__ float log2f(float __a) {
   return __FAST_OR_SLOW(__nv_fast_log2f, __nv_log2f)(__a);
 }
 __DEVICE__ double logb(double __a) { return __nv_logb(__a); }
 __DEVICE__ float logbf(float __a) { return __nv_logbf(__a); }
 __DEVICE__ float logf(float __a) {
   return __FAST_OR_SLOW(__nv_fast_logf, __nv_logf)(__a);
 }
-#if defined(__LP64__)
+#if defined(__LP64__) || defined(_WIN64)
 __DEVICE__ long lrint(double __a) { return llrint(__a); }
 __DEVICE__ long lrintf(float __a) { return __float2ll_rn(__a); }
 __DEVICE__ long lround(double __a) { return llround(__a); }
 __DEVICE__ long lroundf(float __a) { return llroundf(__a); }
 #else
 __DEVICE__ long lrint(double __a) { return (long)rint(__a); }
 __DEVICE__ long lrintf(float __a) { return __float2int_rn(__a); }
 __DEVICE__ long lround(double __a) { return round(__a); }