source: CIVL/examples/translation/openclversion2.1/square.cvl@ b89e408

#include "openCLshared.cvl"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

$input int NUM_DEVICES;
$input int MAX_NUM_DEVICES;
$assume 0 < NUM_DEVICES && NUM_DEVICES < MAX_NUM_DEVICES;

//kernel
void square(int workgroup, int global_id, int local_id, int* input, int* output, const unsigned int count)
{
  //int i = get_global_id(0);
  int i = global_id;
  if (i < count)
  {
    output[i] = input[i] * input[i];
    //printf("output[%d] is %d\n", i, output[i]);
  }
}
/*
void workfunc(size_t local, size_t global, kernel param)
{
  for(int i = local * param.workgroup; i < local * param.workgroup + local; i++)
  {
    param.local_id = i % local;
    param.global_id = i;
    //printf("My workgroup id is %d, my global id is %d, my local id is %d\n", param.workgroup, param.global_id, param.local_id);
    square(param.workgroup, param.global_id, param.local_id, param.input, param.output, param.count);
  }
}
*/
int main(int argc, char** argv)
{
  float data[DATA_SIZE];              // original data set given to device
  float results[DATA_SIZE];           // results returned from device
  unsigned int correct;               // number of correct results returned
  
  size_t global;                      // global domain size for our calculation
  size_t local;                       // local domain size for our calculation
  
  cl_device_id device_id;             // compute device id 
  cl_context context;                 // compute context
  cl_command_queue commands;          // compute command queue
  cl_program program;                 // compute program
  cl_kernel kernel;                   // compute kernel
    
  cl_mem input;                       // device memory used for the input array
  cl_mem output;                      // device memory used for the output array

  
  int err = clGetDeviceIDs(1, &device_id);
  
  return 0;
}