[Yt-dev] Embedded yt and IPython

Stephen Skory stephenskory at yahoo.com
Sat Jun 6 13:31:37 PDT 2009


Matt,


> My thought process was that any domain decomp would serve to probably
> double the memory usage of any individual process -- and I want to try
> to avoid that.  But perhaps it's unavoidable.  I'll see if I can get a
> working implementation of this going sometime over the next little
> while.

Some of the memory duplication could be eliminated by turning off load balancing, of course. So for HOP a run could have the identical root-grid decomposition as enzo. However, that wouldn't help projections in quite the same way. With load balancing I agree that memory duplication would be a big issue. It may end up being worth it, anyway.

 _______________________________________________________
sskory at physics.ucsd.edu           o__  Stephen Skory
http://physics.ucsd.edu/~sskory/ _.>/ _Graduate Student
________________________________(_)_\(_)_______________



More information about the yt-dev mailing list