On 2012-01-21 00:00, RegB wrote:
> Do you have a (good) idea of where diminishing returns cuts in ?
> I imagine the number of cores (threads) doesn't help much above a
> fairly small number due to sequential dependencies ?
I'm pretty sure I hit the diminishing returns already.  ATLAS and R
(both in the critical path) are essentially built serially and together
take 22 minutes of the 27 minutes total build time.  So you could say
that everything *except* for ATLAS and R is neglegible.

> More memory is always "nice to have" but does it really help HERE ?
I think it helps a lot because of the file cache.  The build almost
never has to wait for the disk.

> Did you set the atlas_architecture environment variable to cut down on
> tuning time ?
No.

-- 
To post to this group, send an email to sage-devel@googlegroups.com
To unsubscribe from this group, send an email to 
sage-devel+unsubscr...@googlegroups.com
For more options, visit this group at http://groups.google.com/group/sage-devel
URL: http://www.sagemath.org

Reply via email to