Comment by fl0ki

If I can suggest, the next big breakthrough in this space would be generalizing niche filling optimization. Every thread about this seems to fizzle out, to the point that I couldn't even find which one is the latest any more.

Today most data-carrying enums decay into the lowest common denominator of a 1-byte discriminant padded by 7 more bytes before any variant's data payload can begin. This really adds up when enums are nested, not just blowing out the calling register set but also making each data structure a swiss cheese of padding bytes.

Even a few more improvements in that space would have enormous impact, compounding with other optimizations like better calling conventions.