Hacker News Reader

actually comparing jitted vm's without a warmup is extremly dump.

Second: using the default thread dispatcher for this kind of scenario is pretty dumb on scala (also I think erlang could be made faster, too. but since I'm not an erlang guy...) Fixed Thread Pool (GOMAXPROCS vs ForkJoin)

View on HN

I agree that using the default thread dispatcher is not how this should be used. The application's actors should create and use its own ExecutionContext.

/cc @atemerev

All timers are started after the warmup.

No? In the scala code the timer is started and Actors are created. No warmup anywhere. https://github.com/atemerev/skynet/blob/master/scala/src/mai...

How do you know when warmup is finished?

Warmup's a tricky issue, see this brand new paper: http://arxiv.org/abs/1602.00602

There's an update for Akka version, which measures 12/8/4.4 seconds on subsequent attempts, so yes, warmup is important... but somehow that seems kinda unfair for other languages too.

Reply on news.ycombinator.com