u64x8 iterator by zero-extending each byte in a [u8] slice

```rust
vec![0u8; 100000].iter().map(|&x| {
x as u64 * x as u64
}).sum::();
```
is essentially what I'd like to use this crate to SIMD-accelerate.

The issue I'm bumping into is reading the slice as `u8x8` such that I can then use [`>::from`](https://rust-lang-nursery.github.io/packed_simd/packed_simd/type.u8x8.html#impl-From%3Cu8x8%3E-7) to cast it.

What is the best way to do this currently?

Related to #8, #32 and #46.