Compilation error of C++ program in CUDA

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi All,
I have made installation of the CUDA SDK, CUDA Toolkit, Drivers, Visual C++ 2005.
And I try compile such sample of C++ program

#include
global void VecAdd(int* A, int* B, int* C)
{
int i=threadIdx.x;
C[i]=A[i]+B[i];
}

int main(int argc, char *argv)
{
int N=5;
int A[5]={1,2,3,4,5}, B[5]={6,7,8,9,10}, C[5];
VecAdd<<<1, N>>>(A, B, C);
cout<<C[0]<<C[1]<<C[2]<<C[3]<<C[4];
system(“PAUSE”);
return 0;}

After beginning of compilation
Compiling with CUDA Build Rule…

I have such error
nvcc fatal : Could not open input file C:\DOCUME~1\┬╚╩╥╬╨\LOCALS~1\Temp/tmpxft_00000088_00000000-1

I have such error stable on all samples.
Maybe it is necessary to set some parameters in Visual C++ .

            Thank you in advance for your attention and help.
          Best regards,
              Victor
2

Hi All,
I have made installation of the CUDA SDK, CUDA Toolkit, Drivers, Visual C++ 2005.
And I try compile such sample of C++ program

#include
global void VecAdd(int* A, int* B, int* C)
{
int i=threadIdx.x;
C[i]=A[i]+B[i];
}

int main(int argc, char *argv)
{
int N=5;
int A[5]={1,2,3,4,5}, B[5]={6,7,8,9,10}, C[5];
VecAdd<<<1, N>>>(A, B, C);
cout<<C[0]<<C[1]<<C[2]<<C[3]<<C[4];
system(“PAUSE”);
return 0;}

After beginning of compilation
Compiling with CUDA Build Rule…

I have such error
nvcc fatal : Could not open input file C:\DOCUME~1\┬╚╩╥╬╨\LOCALS~1\Temp/tmpxft_00000088_00000000-1

I have such error stable on all samples.
Maybe it is necessary to set some parameters in Visual C++ .

            Thank you in advance for your attention and help.
          Best regards,
              Victor