[MITgcm-support] timing on ibm p690 with sp4+mpi_jump
Martin Losch
Martin.Losch at awi.de
Mon Mar 19 06:42:52 EDT 2007
Hi,
we are encountering poor (and unexpected) scaling behavior on a IBM
p690 (I think P5 processores) and xlf95 10.??, see attached plot and
comparison of 3 runs with 54/54 (tiles/processors), 216/54, 216/216
(from left to right). The model configuration is the high resolution
cubed sphere (with exch2), with 16 extra passive tracers and we used
tools/build_options/sp4+mpi_jump
What I find interesting is that the 54/54 is slower than the 216/54.
I would have expected a larger overhead because of more exchanges in
the second case, but apparently that's not the case (blocking
exchanges even takes less time in the 216/54 case).
I do not send timings from a 150 and a 360 cpu run, but the 360 cpu
run is actually SLOWER than the 216 cpu run.
"Blocking exchanges" takes much more time in 216/216 compared to
216/54. Other parts of the code, eg. exf_getforcing is very slow,
too, in the 216/216 case (I use singleCPUio, maybe not a good idea?).
I don't know exactly how this is handled but in the code I could not
find that exchanging between tiles on one cpu is any different from
exchanging between different cpus (the MPI_Isend command appears to
be the same, eg. in exch2_send_rl1.F). Can I interpret this
circumstance (slow blocking exchanges) as the exchange between
processors being slow in principle? Is there a way to maybe overcome
this problem, that is, are there parameters/CPP-flags that we can
tune/try?
Martin
-------------- next part --------------
A non-text attachment was scrubbed...
Name: code.tgz
Type: application/octet-stream
Size: 18177 bytes
Desc: not available
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20070319/25484968/attachment.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Skalierungstests.eps
Type: application/postscript
Size: 21189 bytes
Desc: not available
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20070319/25484968/attachment.eps>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: data.gz
Type: application/x-gzip
Size: 1457 bytes
Desc: not available
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20070319/25484968/attachment.gz>
-------------- next part --------------
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: Zeitvergleich.txt
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20070319/25484968/attachment.txt>
More information about the MITgcm-support
mailing list