about output handling in cp2k
akoh... at gmail.com
Thu Jul 12 16:40:33 UTC 2007
On Jul 12, 1:51 am, Teodoro Laino <teodor... at gmail.com> wrote:
> Unfortunately there are no memory leaks.. ;-) (99.99999 % sure)..
it need not be a memory leak in cp2k!
> to deallocate the structure of the input file in memory use the keyword:http://cp2k.berlios.de/input/
does not help. running out of memory in a different routine
(realloc). anyways, the problem is ubiquitous and shows up
for ridiculously small inputs. it would not be the first
bug that i stumbled over in cray's malloc support. :-)
> This is a typical problem of XT3/4 (where the amount of memory
> required is ~1.5 than on normal linux, maybe due to the catamount
> Moreover, in the dual-core version the max amount of memory per node
> is ~850MB per proc (even less if you use more than 100MB for the IO
> buffer(that is the default on our configuration))..
> I'm just a little bit surprised because 850 MB should be more than
> enough for each proc for this input file..
> how much memory can you really access per proc on your machine?
the same (2GB per dual-core node). the same input works fine with
an older version. i still have to check whether i get the same
problem, if i compile the older sources with the newer tools.
More information about the CP2K-user