Search found 10 matches

by ce107
Sat Nov 13, 2010 3:18 am
Forum: ROMS Problems
Topic: ROMS not running on 1024 cores for 17532 iterations
Replies: 12
Views: 11009

Re: ROMS not running on 1024 cores for 17532 iterations

well it looks as if you're having trouble creating your history file - does it work fine for less processor cores? Are you using parallel NetCDF output? In any case, your benchmark numbers so far show that you're spending (even for this number of timesteps) an inordinate amount of time for initializ...
by ce107
Mon Sep 27, 2010 11:45 am
Forum: ROMS Problems
Topic: Intel’s new i7 980x CPU gives disappointing speedup
Replies: 48
Views: 81179

Re: Intel’s new i7 980x CPU gives disappointing speedup

Furthermore, to my experience, the i7-family CPUs machines (by at least a factor of 2) outperform all previous generations of CPUs, including Core 2 and 5400-series Xeons (that is ROMS running 8 theads on a Core i7 920 is faster than on 8 threads dual-quad Xeon 5420s). This is a statement that hold...
by ce107
Fri Apr 30, 2010 2:37 pm
Forum: ROMS Discussion
Topic: does parallel IO work with pnetcdf?
Replies: 5
Views: 3178

Re: does parallel IO work with pnetcdf?

I have not examined the NetCDF 4.1.1 library. As far as I know, UNIDATA NetCDF does not support neither distribute the pnetcdf library. NetCDF 4.1.1 allows pnetcdf to be used when using the classic v3 mode - the configure script has a --with-pnetcdf= option - UNIDATA does not distribute the pnetcdf...
by ce107
Tue Jun 30, 2009 2:46 pm
Forum: ROMS Tools and Techniques
Topic: Issues with installing OCTANT on Linux x64
Replies: 6
Views: 4589

Re: Issues with installing OCTANT on Linux x64

More generally speaking this error is due to a mixing of PIC and non-PIC objects when the target executable is expected to have more than 2GB of address space extent. It is a "feature" of AMD64/EM64T that AMD introduced by employing 4 different 64bit addressing models (kernel, small (defau...
by ce107
Tue Feb 19, 2008 3:33 am
Forum: ROMS Discussion
Topic: Sorting routine in MPI & adding new CFL routine to ROMS
Replies: 2
Views: 2857

Re: Sorting routine in MPI & adding new CFL routine to R

(2) Find its maximum and then its corresponding U-, V- and W- components, (3) From (2) find the (I,J,K) grid locations as to where this maximum CFL occurs and, [snip] I do not know how to code up (1)-(4) in MPI code because of steps (2) and (3) where we need to do some sorting to find the correspon...
by ce107
Wed Nov 28, 2007 6:08 pm
Forum: ROMS Discussion
Topic: Query: GPU Offload "Math Co-Processor" with ROMS ?
Replies: 3
Views: 4120

My boss is looking to get such a test system to play with. He says they are good at single precision floating point, but double precision is not so fast. I think the people who would get the easiest benefit are using libraries such as lapack where you just change your function calls or the library ...
by ce107
Mon Dec 05, 2005 3:39 pm
Forum: ROMS Benchmarks
Topic: Benchmarks
Replies: 31
Views: 60976

It is strange but true that on Intel x86-family CPUs a serial run will normally go faster if there are multiple tiles. Actually one would expect this type of behaviour on all cache-based processors (possibly including cache-based vector processors like the later Cray ones - though things could be d...
by ce107
Fri Sep 23, 2005 6:45 pm
Forum: ROMS Problems
Topic: oceanS on SGI
Replies: 5
Views: 5158

I can't imagine that UPWELLING is big enough for you to need a larger stacksize. It must be something else - I will try it on an SGI. Edit: I tried it on: IRIX64 video2 6.5 10070055 IP27 and could not reproduce the problem. I did run into linker troubles from mp_numthreads and another similar funct...
by ce107
Mon Sep 19, 2005 2:20 pm
Forum: ROMS Problems
Topic: oceanS on SGI
Replies: 5
Views: 5158

A very basic question: Have you tried resetting the stack limit to unlimited?

For the Bourne shell family:
ulimit -s unlimited
For the C-shell family:
unlimit stacksize

In many cases this solves the problem.

Constantinos
by ce107
Mon Jan 03, 2005 9:48 pm
Forum: ROMS Discussion
Topic: Interconnect speed for MPI: Gigabit, Myrinet and Infiniband
Replies: 5
Views: 7694

I would not expect anywhere near a factor of 7 (or even of 2) performance difference (for a program spending 50% of its time communicating exclusively very large messages - a rather unlikely configuration - 7 times higher bandwidth would at best buy you 43% less wallclock time). ROMS' (as well as ot...