#include <stdio.h>

#include "helper_cuda.h"
#include <cuda_runtime.h>

template<typename T> __global__ void vector_projection(T *dx, int n) {
	int tid;
	tid = threadIdx.x + blockIdx.x * blockDim.x;
	if (tid < n) {
		if (dx[tid] < 0)
			dx[tid] = (T) 0;
	}
}

double X[10] = {1,-2,3,-4,5,-6,7,-8,9,-10};


int main(void) {
	int i;

	double *dev_X;
	checkCudaErrors(cudaMalloc(&dev_X, 10*sizeof(double)));
	checkCudaErrors(cudaMemcpy(dev_X, X, 10*sizeof(double), cudaMemcpyHostToDevice));

	vector_projection<double><<<1,10>>>(dev_X, 10);
	getLastCudaError("vector_projection");

	checkCudaErrors(cudaMemcpy(X, dev_X, 10*sizeof(double), cudaMemcpyDeviceToHost));
	for (i=0; i<10; i++)
	{
		printf("proj(X) = %g\n", i, X[i]);
	}

	return 0;
}