I have a cuda thrust program as
#include <stdio.h>
#include<iostream>
#include <cuda.h>
#include <thrust/sort.h>
// main routine that executes on the host
int main(void)
{
int *a_h, *a_d; // Pointer to host & device arrays
const int N = 10; // Number of elements in arrays
size_t size = N * sizeof(int);
a_h = (int *)malloc(size); // Allocate array on host
cudaMalloc((void **) &a_d, size);// Allocate array on device
std::cout<<"enter the 10 numbers";
// Initialize host array and copy it to CUDA device
for (int i=0; i<N; i++)
{
std::cin>>a_h[i];
}
for (int i=0; i<N; i++) printf("%d %d\n", i, a_h[i]);
cudaMemcpy(a_d, a_h, size, cudaMemcpyHostToDevice);
thrust::sort(a_d, a_d + N);
// Do calculation on device:
cudaMemcpy(a_h, a_d, sizeof(int)*N, cudaMemcpyDeviceToHost);
// Print results
for (int i=0; i<N; i++) printf("%d %d\n", i, a_h[i]);
// Cleanup
free(a_h); cudaFree(a_d);
}
but it is not running to give the desired output.
Are we supposed to use the host vector and device vector for sorting in thrust????