Thank you!

I made some test with the `parMap` template of the malebolgia library (trying 
different `bulkSize` and `ThreadPoolSize` values). It works but slower than the 
unparallelized version. It seems to me that my function is just too cheap to be 
parallelized. I think it is consistent with what is said in the _weave_ github 
page:

> Unfortunately existing framework requires computation to take 10000 cycles at 
> minimum (Intel TBB) which corresponds to 3.33 µs on a 3 GHz CPU to amortize 
> the cost of scheduling.

Reply via email to