Request for feedback on WG14 proposal N3849 (alloc_at_least)

[Wilco Dijkstra]

Hi Paul,

> Although the proposal's main motivation is runtime efficiency, it
> doesn't say what sort of efficiency improvements are likely in practice,
> so I can see an argument that it's not worth the complexity.
>
> Presumably the proposal entails efficiency costs and benefits; it'd be
> nice to see measurements of both.

I didn't find a clear motivation about performance in the proposal.
However realloc is *fast* if the size fits or is a little smaller: it takes 
less than 5 cycles on a modern CPU (over 550 million calls per second).

That's before we've optimized it - we could streamline it as a fast path.

Cheers,
Wilco