Control.Parallel.Strategies.parMap CPU usage
dons at galois.com
Mon Mar 30 13:01:01 EDT 2009
> having tried the 6.10.2rc1 release candidate, I still find that "parMap
> rnf xs" on a list of thunks xs does not optimally use all available
> processors. With N the number of cores, I still see that each block of N
> thunks (say: x_1 and x_2) has to be calculated before (x3 and x4) will be
> Would there be hope that compiling the latest head instead of 2009/03/14 (rc1) gives better results?
Yes, definitely. The HEAD implements all the `par` improvements
described in the recent "multicore runtime" paper, as well as giving
detailed runtime statistics on spark use.
More information about the Glasgow-haskell-users