weird code in dbcsr
no... at bollweevil.gdbg.org
Fri Dec 30 16:28:09 UTC 2011
I'm trying to debug an intermittent crash, and in the process, I
noticed the following
dbcsr_lib/dbcsr_transformations.F, line 2586, calls mp_alltoall for
passing count=2. Not that send_count is allocated as (2,0:numnodes-1).
mp_alltoall_i22 in dbcsr_lib/dbcsr_message_passing_i.F, line 257, passes
count to mpi_alltoall. I would have expected size(sb) and size(rb).
Does this make sense, and if so, why?
I'm using, I believe, the latest cvs version of the code.
More information about the CP2K-user