// Masks: comparisons of vectors, select, any/all/count, and the end of a list

fn relu(f32x8 v) -> f32x8 {
    return select(v > 0.0, v, 0.0)
}

// the sum of a list of any length: whole vectors, then the last piece with its missing lanes as 0
fn total([]f32 xs) -> f32 {
    acc := f32x8(0.0)
    i := 0
    while i < xs.len {
        acc = acc + f32x8(xs, i, 0.0)
        i += 8
    }
    return acc.sum()
}

// add 1 to every number of a list, in place, the last piece too
fn bump([]f32 xs) {
    i := 0
    while i < xs.len {
        (f32x8(xs, i, 0.0) + 1.0).store_part(xs, i)
        i += 8
    }
}

fn main() {
    v := f32x8(-2.0, -1.0, 0.0, 1.0, 2.0, 3.0, -4.0, 5.0)
    m := v > 0.0
    print(m, m.count(), m.any(), m.all(), m[3])
    print(relu(v), select(!m, v, -1.0))
    print((v >= -1.0) & (v < 3.0), (v == 0.0) | (v == 5.0), m ^ (v > 1.0))

    a := i32x4(1, 5, 3, 7)
    b := i32x4(4, 4, 4, 4)
    print(select(a > b, a, b), (a == a).all(), (a != b).all())
    u := u8x16(200)
    print((u > u8x16(100)).all(), i32x4(a > b), f32x4(a < b))
    k := i32x4(0, 2, 0, -1)
    print(boolx4(k), boolx4(true, false, true, false))

    []f32 xs
    for n in 0..13 {
        xs.push(f32(n))
    }
    print(total(xs))
    bump(xs)
    print(xs)
    print(f32x8(xs, 8, -1.0), f32x8(xs, 13, 9.0), f32x8(xs, 100, 7.0))
}