Weighted sum as division

weighted_sum.cc

// Algorithm
Expr numerator = f32(u32(input_a_(x, y)) * u32(coeff_a_(x, y)) +
                 u32(input_b_(x, y)) * u32(coeff_b_(x, y)));
Expr denominator = u16(coeff_a_(x, y)) + u16(coeff_b_(x, y));
output_(x, y) = u8_sat(numerator / denominator + 0.5f);

// Schedule
Var xi("xi"), yi("yi");
output_.compute_root()
    .split(y, y, yi, 32, TailStrategy::ShiftInwards)
    .split(x, x, xi, 16, TailStrategy::ShiftInwards)
    .vectorize(xi)
    .reorder(xi, x, yi, y)
    .parallel(y);