Opencl: incorrect results on phi

This kernel runs on host cpu but produces wrong outputs when run Phi. What's the issue witht the Phi here?

//KERNEL_SIMPLE

__kernel void Convolve(const __global  float * pInput,

                        __constant float * pFilter,

                        __global  float * pOutput,

                        const int nInWidth,

                        const int nFilterWidth)

{

    const int nWidth = get_global_size(0);

    const int xOut = get_global_id(0);

    const int yOut = get_global_id(1);

    const int xInTopLeft = xOut;

    const int yInTopLeft = yOut;

    float sum = 0;

    for (int r = 0; r < nFilterWidth; r++)

    {

        const int idxFtmp = r * nFilterWidth;

        const int yIn = yInTopLeft + r;

        const int idxIntmp = yIn * nInWidth + xInTopLeft;

        for (int c = 0; c < nFilterWidth; c++)

        {

            const int idxF  = idxFtmp  + c;

            const int idxIn = idxIntmp + c;

            sum += pFilter[idxF]*pInput[idxIn];

        }

    }

    const int idxOut = yOut * nWidth + xOut;

    pOutput[idxOut] = sum;

}

//KERNEL_SIMPLE