Our hope is that systems programmers can let PSS do the hard work while they focus their time on sleeping (or, more importantly, their cats)

(See Voidy letting Vickie do the hard work)

Our evaluation covers three diverse scenarios: in-kernel page reclaim, PyPy JIT tuning, and hardware transactional lock elision, giving performance comparable to/better than the state of the art heuristics

(See Voidy fighting for the blanket like HTM)