mul matrix in cuda dont work true and return 0.0000000

#include <stdio.h>
#include <conio.h>
 __global__ void kernelFunc(float* ad, float* bd, float* cd, int n) {
    int x = (blockIdx.x * blockDim.x) + threadIdx.x;
    int y = (blockIdx.y * blockDim.y) + threadIdx.y;
    
    if(x < n && y < n) {   
        float v = 0.0f;
        for(int i=0; i<n;>            v += ad[y * n + i] * bd[i * n + x];
        cd[y * n + x] = v;
    }
}

void main() {

int ii,jj,k;
    float* ad;
    float* bd;
    float* cd;
    int n=64;
	float a[64][64];
	float b[64][64];
	float c[64][64];

	for(ii=0;ii<n;ii++)>
	{
	for(jj=0;jj<n;jj++)>
	{
	a[ii][jj]=2;//ii+jj;
	b[ii][jj]=3;//ii+jj;
	//c[ii][jj]=4;
	}

	}
	
    cudaMalloc((void**)&ad, n * n * sizeof(float));
    cudaMalloc((void**)&bd, n * n * sizeof(float));
    cudaMalloc((void**)&cd, n * n * sizeof(float));
    
    cudaMemcpy(ad, a, n * n * sizeof(float), cudaMemcpyHostToDevice);
    cudaMemcpy(bd, b, n * n * sizeof(float), cudaMemcpyHostToDevice);
	cudaMemcpy(cd, c, n * n * sizeof(float), cudaMemcpyHostToDevice);
    dim3 block(1, 1);           
    dim3 grid(1, 1);
    
    kernelFunc<<<grid,>>>(ad, bd, cd, n);

    cudaMemcpy(c, cd, n * n * sizeof(float), cudaMemcpyDeviceToHost);

	for(ii=0;ii<n;ii++)>
	{
	printf("\n ");
	for(jj=0;jj<n;jj++)>
	{
	printf("%f ",c[ii][jj]);

	

	}

	}
    
    cudaFree(ad);
    cudaFree(bd);
    cudaFree(cd);

}