Skynet 1M Fiber microbenchmark in D

[Nordlöw]

On Wednesday, 18 October 2017 at 11:52:08 UTC, Biotronic wrote:
> It seems to make very little difference in terms of run time, 
> though. I tried using a mix of these approaches - parallel at 
> low depth, basically just to fill up the cores, and serial 
> closer to the leaves. The difference is still negligible, so I 
> assume the losses are elsewhere.
>
> --
>   Biotronic

Thanks!

Further, are we forced to use the GC for Fiber allocation or can 
a sub-class of Fibers implement its own allocation strategy?