Optimize live point computation

This is just replicating the previous algorithm, but taking advantage of the
bitset structures to optimize into tighter and better optimized loops.
Particularly advantageous on enormous MIR blocks, which are relatively rare in
practice.

compiler/rustc_index/src/lib.rs

@@ -3,7 +3,9 @@
 #![feature(extend_one)]
 #![feature(iter_zip)]
 #![feature(min_specialization)]
+#![feature(step_trait)]
 #![feature(test)]
+#![feature(let_else)]
 
 pub mod bit_set;
 pub mod vec;