Quick note: the magic "help JS function" is literally just a double->int conversion that uses the x86 sentinel values and rounding modes. The effect on JS is that it removes a set of branches following ((int)someDouble) that are needed to match the x86 semantics that JS mandates. The instruction is not magically faster than x86. In fact more or less by definition it's just doing what x86 does.

I am tired of people bringing up that instruction as though it's magically making JS faster compared to intel. At best it's a leveling the playing field instruction.

Implementing TSO isn't "cheating", it's hard work that other companies aren't willing to do.

Ref counting isn't magically faster than other GC methods - there's arguments that it is slower - it does however use much less memory than pretty much any other GC scheme, hence the lower memory needs on iOS vs Android.