c - Running OpenCL using Visual Studio 2015 -

i'm newbie in opencl, far referred dr. dobbs tutorials opencl , few others , ran on ubuntu worked same codes won't/refuse work on windows using visual studio required environment variables set correctly. i'm using 980m cuda sdk 8 on vs 2015. have 2 files, 1 in c , kernel(cl) file. whenever add both .c & .cl files, program refuses run throwing errors can't find program files , things that. however, if write kernel file within c file, works 1 out of 3. same program works fine on pc running ubuntu 16 , pc amd card running on ubuntu 16. program i'm trying run vector addition written in c. i've attached link code. opencl vector addition

add_numbers.c

 #define program_file "add_numbers.cl"  #define kernel_func "vecadd"   #include <math.h>  #include <stdio.h>  #include <stdlib.h>  #include <string.h>  #include <time.h>  #ifdef __linux  #include <unistd.h>  #include <fcntl.h>    #endif // __linux   #ifdef mac #include <opencl/cl.h> #else #include <cl/cl.h> #endif  /* find gpu or cpu associated first available platform */ cl_device_id create_device() {     cl_platform_id platform;    cl_device_id dev;    int err;     /* identify platform */    err = clgetplatformids(1, &platform, null);    if(err < 0) {       perror("couldn't identify platform");       exit(1);    }      /* access device */    err = clgetdeviceids(platform, cl_device_type_cpu, 1, &dev, null);  if(err == cl_device_not_found) {       err = clgetdeviceids(platform, cl_device_type_gpu, 1, &dev, null);    }    if(err < 0) {       perror("couldn't access devices");       exit(1);       }     return dev; }  /* create program file , compile */ cl_program build_program(cl_context ctx, cl_device_id dev, const char* filename) {     cl_program program;    file *program_handle;    char *program_buffer, *program_log;    size_t program_size, log_size;    int err;     /* read program file , place content buffer */    program_handle = fopen(filename, "r");    if(program_handle == null) {       perror("couldn't find program file");       exit(1);    }    fseek(program_handle, 0, seek_end);    program_size = ftell(program_handle);    rewind(program_handle);    program_buffer = (char*)malloc(program_size + 1);    program_buffer[program_size] = '\0';    fread(program_buffer, sizeof(char), program_size, program_handle);    fclose(program_handle);     /* create program file */    program = clcreateprogramwithsource(ctx, 1,        (const char**)&program_buffer, &program_size, &err);    if(err < 0) {       perror("couldn't create program");       exit(1);    }    free(program_buffer);     /* build program */    err = clbuildprogram(program, 0, null, null, null, null);    if(err < 0) {        /* find size of log , print std output */       clgetprogrambuildinfo(program, dev, cl_program_build_log,              0, null, &log_size);       program_log = (char*) malloc(log_size + 1);       program_log[log_size] = '\0';       clgetprogrambuildinfo(program, dev, cl_program_build_log,              log_size + 1, program_log, null);       printf("%s\n", program_log);       free(program_log);       exit(1);    }     return program; }  int main() {     /* opencl structures */    cl_device_id device;    cl_context context;    cl_program program;    cl_kernel kernel;    cl_command_queue queue;    cl_device_type dev_type; //new   // cl_int i, j, err;    size_t local_size, global_size;      // vector add pgm // length of vectors     unsigned int n = 1000000;      // host input vectors     double *h_a;     double *h_b;     // host output vector     double *h_c;      // device input buffers     cl_mem d_a;     cl_mem d_b;     // device output buffer     cl_mem d_c;      // size, in bytes, of each vector     size_t bytes = n*sizeof(double);      // allocate memory each vector on host     h_a = (double *)malloc(bytes);     h_b = (double *)malloc(bytes);     h_c = (double *)malloc(bytes);      // initialize vectors on host     int i;     for( = 0; < n; i++ )     {         /*h_a[i] = sinf(i)*sinf(i);         h_b[i] = cosf(i)*cosf(i);*/         h_a[i] = i+1;          h_b[i] = i+2;      }    //  size_t globalsize, localsize;     cl_int err;      // number of work items in each local work group     local_size = 64;      // number of total work items - localsize must devisor     global_size = (n/local_size)*local_size;     /* create device , context */    device = create_device();    context = clcreatecontext(null, 1, &device, null, null, &err);    if(err < 0) {       perror("couldn't create context");       exit(1);       }     /* build program */    program = build_program(context, device, program_file);     /* create data buffer */      input_buffer = clcreatebuffer(context, cl_mem_read_only |          cl_mem_copy_host_ptr, array_size * sizeof(float), data, &err);    sum_buffer = clcreatebuffer(context, cl_mem_read_write |          cl_mem_copy_host_ptr, num_groups * sizeof(float), sum, &err);    if(err < 0) {       perror("couldn't create buffer");       exit(1);       };*/    //input buffers     d_a = clcreatebuffer(context, cl_mem_read_only, bytes, null, null);     d_b = clcreatebuffer(context, cl_mem_read_only, bytes, null, null);     d_c = clcreatebuffer(context, cl_mem_write_only, bytes, null, null);     /* create command queue */    queue = clcreatecommandqueue(context, device, 0, &err);    if(err < 0) {       perror("couldn't create command queue");       exit(1);       };     /* create kernel */    kernel = clcreatekernel(program, kernel_func, &err);    if(err < 0) {       perror("couldn't create kernel");       exit(1);    };    // newer args under test   err  = clsetkernelarg(kernel, 0, sizeof(cl_mem), &d_a);     err |= clsetkernelarg(kernel, 1, sizeof(cl_mem), &d_b);     err |= clsetkernelarg(kernel, 2, sizeof(cl_mem), &d_c);     err |= clsetkernelarg(kernel, 3, sizeof(unsigned int), &n);    if(err < 0) {       perror("couldn't create kernel argument");       exit(1);    }     /* enqueue kernel */    err = clenqueuendrangekernel(queue, kernel, 1, null, &global_size,           &local_size, 0, null, null);     if(err < 0) {       perror("couldn't enqueue kernel");       exit(1);    }     /* read kernel's output */         err = clenqueuereadbuffer(queue, d_c, cl_true, 0,                                 bytes, h_c, 0, null, null );     if(err < 0) {       perror("couldn't read buffer");       exit(1);    }    //cl_device_type dev_type; clgetdeviceinfo(device, cl_device_type, sizeof(dev_type), &dev_type, null); if (dev_type == cl_device_type_gpu) {     puts("i'm 100% sure device gpu");     }     else     puts("device cpu\n");  // sum calc.  double sum = 0;     for(i=0; i<n; i++)         //sum += h_c[i];        sum = h_a[i] + h_b[i];     printf("final result: %lf\n",(sum/n));      /* deallocate resources */    clreleasememobject(d_a);     clreleasememobject(d_b);     clreleasememobject(d_c);    clreleasekernel(kernel);    clreleasecommandqueue(queue);    clreleaseprogram(program);    clreleasecontext(context);    return 0; } 

add_number.cl kernel file

__kernel void vecadd(  __global double *a,                                            __global double *b,                                        __global double *c,                                             const unsigned int n)                         {               #pragma opencl extension cl_khr_fp64 :enable                                                         //get our global thread id                                    int id = get_global_id(0);                             //make sure not go out of bounds                           if (id < n)                                                     c[id] = a[id] + b[id];                                     }