OpenCL

  __global__ void
  vectorAdd(const float * a, const float * b, float * c)
  {
      // Indice do vetor
      int nIndex = blockIdx.x * blockDim.x + threadIdx.x;
      c[nIndex] = a[nIndex] + b[nIndex];
  }

  __kernel void
  vectorAdd(__global const float * a,
            __global const float * b,
            __global       float * c)
  {
      // Indice do vetor
      int nIndex = get_global_id(0);
      c[nIndex] = a[nIndex] + b[nIndex];
  }

/* main routine that executes on the host */
int main(void)
{
 float *a_h, *a_d; // Pointer to host & device arrays
 const int N = 10; // Number of elements in arrays
 size_t size = N * sizeof(float);
 a_h = (float *)malloc(size); // Allocate array on host
 cudaMalloc((void **) &a_d, size); // Allocate array on device
 // Initialize host array and copy it to CUDA device
 for (int i=0; i<N; i++) a_h[i] = (float)i;
 cudaMemcpy(a_d, a_h, size, cudaMemcpyHostToDevice);
 // Do calculation on device:
 int block_size = 3;
 int n_blocks = N/block_size + (N % block_size == 0 ? 0:1);
 square_array <<< n_blocks, block_size >>> (a_d, N);
 // Retrieve result from device and store it in host array
 cudaMemcpy(a_h, a_d, sizeof(float)*N, cudaMemcpyDeviceToHost);
 // Print results
 for (int i=0; i<N; i++) printf("%d %f\n", i, a_h[i]);
 // Cleanup
 free(a_h); cudaFree(a_d);
}

# include <stdio.h>
# include <cl.h>
int main(void){ // main routine that executes on the host
 float *a_h; // Pointer to host & device arrays
 const int N = 10; // Number of elements in arrays
 size_t size = N * sizeof(float);
 a_h = (float *)malloc(size); // Allocate array on host
 // Initialize host array and copy it to CUDA device
 for (int i=0; i<N; i++) a_h[i] = (float)i;
 // create the OpenCL context on a GPU device
 cl_context context = clCreateContextFromType(0, // (must be 0)
                      CL_DEVICE_TYPE_ GPU, NULL, // error callback
                      NULL, // user data
                      NULL); // error code
 // get the list of GPU devices associated with context
 size_t cb;
 clGetContextInfo(context, CL_CONTEXT_DEVICES, 0, NULL, &cb);
 cl_device_id *devices = malloc(cb);
 clGetContextInfo(context, CL_CONTEXT_DEVICES, cb, devices, NULL);
 // create a command-queue
 cl_cmd_queue cmd_queue = clCreateCommandQueue(context,
                          devices[0], 0, // default options
                          NULL); // error code
 cl_mem memobjs[1];
 // allocate input buffer memory objects
 memobjs[0] = clCreateBuffer(context,
              CL_MEM_READ_ONLY | // flags
              CL_MEM_COPY_HOST_PTR,
              sizeof(cl_float)*n, // size
              a_h, // host pointer
              NULL); // error code
 // create the program
 cl_program program = clCreateProgramWithSource(
                      context,
                      1, // string count
                      &program_source, // program strings
                      NULL, // string lengths
                      NULL); // error code
 // build the program
 cl_int err = clBuildProgram(program,
              0, // num devices in device list
              NULL, // device list
              NULL, // options
              NULL, // notifier callback function ptr
              NULL); // error code
 // create the kernel
 cl_kernel kernel = clCreateKernel(program, “square_array”, NULL);
 // set “a” vector argument
 err = clSetKernelArg(kernel,
       0, // argument index
       (void *)&memobjs[0], // argument data
       sizeof(cl_mem)); // argument data size
 size_t global_work_size[1] = n; // set work-item dimensions
 // execute kernel
 err = clEnqueueNDRangeKernel(cmd_queue, kernel,
       1, // Work dimensions
       NULL, // must be NULL (work offset)
       global_work_size,
       NULL, // automatic local work size
       0, // no events to wait on
       NULL, // event list
       NULL); // event for this kernel
 // read output array
 err = clEnqueueReadBuffer( context, memobjs[0],
       CL_TRUE, // blocking
       0, // offset
       n*sizeof(cl_float), // size
       a_h, // pointer
       0, NULL, NULL); // events
 // Print results
 for (int i=0; i<N; i++) printf("%d %f\n", i, a_h[i]);
 // Cleanup Host Memory
 free(a_h);
}