#define CUDATOOLS_IMPLEMENTATION
#include <Core.h>

class intPair {
    DEVICE_CLASS(intPair)
  public:
    int x, y;

    intPair(const int x_, const int y_) : x(x_), y(y_) {
        allocateDevice(); // Allocates memory for this intPair on the device.
        updateDevice()
            .wait(); // Copies the memory on the host to the device and waits until finished.
    };

    HD void swap() {
        int swap = x;
        x = y;
        y = swap;
    };
};

KERNEL(swap, intPair* const pair) { pair->swap(); }

int main() {
    intPair pair(1, 2);
    printf("Before: %u, %u\n", pair.x, pair.y); // Prints 1, 2.

    CudaTools::Kernel::launch(swap, CudaTools::Kernel::basic(1), pair.that()).wait();
    pair.updateHost()
        .wait(); // Copies the memory from the device back to the host and waits until finished.

    printf("After: %u, %u\n", pair.x, pair.y); // Prints 2, 1.
    return 0;
}