how to use bind a 1D array to a texture object

I want to use texture memory of GPU for a 1D array and use it in a kernal. I create a texture object and and assigned resDesc.res.linear.devPtr to a device array to bind my desired array to texture object. The problem is that when I fetch the data, it is different from the data I bounded to the texture memory. The output of this code should be 1, 4, 9, ... while it is 0,0,0,....

#include<cuda.h>
#include<cuda_runtime.h>
#include<iostream>
#include<stdio.h>
using namespace std;
// Simple transformation kernel
__global__ void squareKernel(float* output,float *dh, int size,  cudaTextureObject_t texObj) {
    unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
    if(x>size)return;
    float y=tex1D<float>(texObj, x);
    printf("%d, %f, %f\n", x, y, dh[x]);
    output[x]=y*y;
}
#define width 10
int main() {
    cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc(width, 0, 0, 0,
            cudaChannelFormatKindFloat);
    float *hA=(float *)malloc(width*sizeof(float));
    for(int i=0;i<width;i++){
        hA[i]=i;
    }
    float *dA;
    cudaMalloc((void **)&dA, width*sizeof(float));
    cudaMemcpy(dA, hA, width*sizeof(float), cudaMemcpyHostToDevice);
    
    cudaResourceDesc resDesc;
    memset(&resDesc, 0, sizeof(resDesc));

    resDesc.resType = cudaResourceTypeLinear;
    resDesc.res.linear.devPtr=dA;
    resDesc.res.linear.sizeInBytes=width*sizeof(float);
    
    // Specify texture object parameters
    cudaTextureDesc texDesc;
    memset(&texDesc, 0, sizeof(texDesc));

    texDesc.filterMode = cudaFilterModeLinear;
    texDesc.readMode = cudaReadModeElementType;
    texDesc.normalizedCoords = 0;
    // Create texture object
    cudaTextureObject_t texObj = 0;
    cudaCreateTextureObject(&texObj, &resDesc, &texDesc, NULL);



    float* output;
    cudaMalloc(&output, width * sizeof(float));
    squareKernel<<<1, width>>>(output, dA, width,texObj);
    cudaMemcpy(hA, output, width*sizeof(float), cudaMemcpyDeviceToHost);
    for(int i=0; i<width;i++){
        cout<<i<<","<<hA[i]<<endl;
    }
    
    // Destroy texture object
    cudaDestroyTextureObject(texObj);
    // Free device memory

    cudaFree(dA);
    free(hA);
    return 0;
}