safasf

__global__ void kernel_res_nested(TYPE *A, TYPE *B, TYPE *D, TYPE *result, TYPE size, TYPE resultSize){

    int i = blockDim.x * blockIdx.x + threadIdx.x;
    int j = blockDim.y * blockIdx.y + threadIdx.y;

    TYPE rtmp = result[i];

    if( i > 0 && i < resultSize - 1){

        TYPE start = (i >= size) ? (i % size ) + 1 : 0;
        TYPE end = (i + 1) / 2;

        if(j >= start && j <= end ){
            rtmp += ( A[j] + A[i - j] ) * ( B[j] + B[i - j] ) - ( D[j] + D[i - j] );
        }
    }

    result[i] = rtmp;
}