GCHP Timing Tests
Contents
Overview
This page features reports of user run-times done with High Performance GEOS-Chem (GCHP). If you are running GCHP please add your own results below. You can sign up for a wiki account to edit this page or you can send your information to the GEOS-Chem Support Team.
Extracting GCHP Timing Information
Follow instructions on Getting Started with GCHP to get set up to run GCHP. GCHP timing information is displayed at the end of the GCHP.log log file. Please report the numbers for items in red below.
Total time for GEOS-Chem core components, in seconds:
Times for GIGCchem
TOTAL : 16195.289
INITIALIZE : 64.237
RUN : 16010.216
FINALIZE : 0.000
DO_CHEM : 15682.849
CP_BFRE : 7.515
CP_AFTR : 172.251
GC_CONV : 1062.171
GC_EMIS : 846.439
GC_DRYDEP : 5.876
GC_FLUXES : 0.000
GC_TURB : 802.816
GC_CHEM : 12009.869
GC_WETDEP : 729.897
GC_DIAGN : 0.000
GenInitTot : 49.299
--GenInitMine : 49.299
GenRunTot : 0.000
--GenRunMine : 0.000
GenFinalTot : 35.596
--GenFinalMine : 35.596
GenRecordTot : 25.848
--GenRecordMine : 25.845
GenRefreshTot : 0.000
--GenRefreshMine : 0.000
Total run-time, in seconds:
-----------------------------------------------------
Block User time System Time Total Time
-----------------------------------------------------
TOTAL 34848.6779 0.0000 34848.6779
COMM_TOTAL 552.8329 0.0000 552.8329
COMM_TRAC 552.8318 0.0000 552.8318
FV_TP_2D 6004.5731 0.0000 6004.5731
Total time for advection, in seconds:
Times for DYNAMICS
TOTAL : 7645.593
INITIALIZE : 1.029
RUN : 7645.563
FINALIZE : 0.000
GenInitTot : 0.012
--GenInitMine : 0.012
GenRunTot : 0.000
--GenRunMine : 0.000
GenFinalTot : 0.000
--GenFinalMine : 0.000
GenRecordTot : 0.008
--GenRecordMine : 0.006
GenRefreshTot : 0.000
--GenRefreshMine : 0.000
Total time for MAPL History, in seconds:
Times for HIST
TOTAL : 211.554
Initialize : 4.994
Finalize : 0.142
Run : 206.592
--Couplers : 54.423
--I/O : 152.310
----IO Create : 1.789
----IO Write : 152.310
-----IO Post : 5.638
-----IO Wait : 40.447
-----IO Write : 110.306
-ParserRun : 0.000
GenInitTot : 0.000
--GenInitMine : 0.000
GenRunTot : 0.000
--GenRunMine : 0.000
GenFinalTot : 0.002
--GenFinalMine : 0.002
GenRecordTot : 0.000
--GenRecordMine : 0.000
GenRefreshTot : 0.000
--GenRefreshMine : 0.000
Total time for MAPL ExtData, in seconds:
Times for EXTDATA
TOTAL : 2840.095
Initialize : 8.410
Run : 2831.698
-Read_Loop : 2800.662
--CheckUpd : 6.597
--Read : 2702.010
--Swap : 1.650
--Bracket : 99.195
-Interpolate : 31.540
GenInitTot : 0.007
--GenInitMine : 0.006
GenRunTot : 0.005
--GenRunMine : 0.003
GenFinalTot : 0.006
--GenFinalMine : 0.006
GenRecordTot : 0.000
--GenRecordMine : 0.000
GenRefreshTot : 0.000
--GenRefreshMine : 0.000
Reported Model Runs
If you are running GCHP we encourage you to report performance in this section. For optimal comparability we recommend doing a 7-day duration simulation but information for other durations is welcome as well. Run settings may vary considerably but we ask that the following be constant:
- Jobs start on model date 2016/07/01 00:00 GMT.
- The code was compiled from the standard GCHP run directory (gchp_standard) with the option make compile_clean.
Enter your system information in the top table to the best of your knowledge and your simulation information in the bottom table. Use a unique id to cross-reference between the two.
Enter your system information here:
ID | Organization | Cluster | Partition | OS | Network interconnect | CPU Vendor | CPU Model | CPU Speed [MHz] | Compiler | MPI | NetCDF | Filesystem info |
---|---|---|---|---|---|---|---|---|---|---|---|---|
000 | Harvard | Odyssey | huce_intel | CentOS 7 | Infiniband | Intel | Xeon | 2.10GHz | intel 17.0.4 | openmpi 3.1.1 | netcdf 4.1.3 | LFS |
001 | Harvard | Odyssey | huce_intel | CentOS 7 | Infiniband | Intel | Xeon | 2.10GHz | gcc 7.1.0 | openmpi 3.1.1 | netcdf 4.1.3 | LFS |
002 | Harvard | Odyssey | huce_intel | CentOS 7 | Infiniband | Intel | Xeon | 2.10GHz | gcc 8.2.0 | openmpi 3.1.1 | netcdf 4.1.3 | LFS |
003 | Harvard | Odyssey | huce_amd | CentOS 7 | Infiniband | AMD | Opteron | 2.3GHz | gcc 8.2.0 | openmpi 3.1.1 | netcdf 4.1.3 | LFS |
If you needed to change GCHP source code or make customized environment variables for a successful compilation and run on your system, please list the necessary changes here:
ID | Organization | OS | Compiler | MPI | Source Code Changes | Special Env Variables |
---|---|---|---|---|---|---|
Enter your simulation information here:
User | ID | GEOS-Chem Version | Total Nodes | Total Cores | Simulation | Duration | Met Source | Met Res | Grid Res | Dyn dt [min] | Chem dt [min] | Diagnostics* | Diag Freq | Diag Duration | Total Time (s) |
Dynamics (s) |
GIGCchem (s) |
History (s) |
ExtData (s)
|
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Bob Yantosca | 001 | 12.0.1 | 1 | 6 | standard | 6 hours | GEOS-FP | 0.25x0.3125 | c24 | 10 | 20 | default | 1hr | 1hr | 1080 (18.0 min) |
83 | 412 | 145 | 427 |
Bob Yantosca | 002 | 12.0.1 | 1 | 6 | standard | 6 hours | GEOS-FP | 0.25x0.3125 | c24 | 10 | 20 | default | 1hr | 1hr | 967 (16.1 min) |
73 | 351 | 125 | 406 |
Lizzie Lundgren | 000 | 12.0.1 | 3 | 48 | standard | 7 days | GEOS-FP | 0.25x0.3125 | c90 | 10 | 20 | default | daily | daily | 31644 (8.78 hrs) |
4753 | 16279 | 177 | 2961 |
Lizzie Lundgren | 001 | 12.0.1 | 3 | 48 | standard | 7 days | GEOS-FP | 0.25x0.3125 | c90 | 10 | 20 | default | daily | daily | 34848 (9.67 hrs) |
7645 | 16195 | 211 | 2840 |
Lizzie Lundgren | 002 | 12.0.1 | 3 | 48 | standard | 7 days | GEOS-FP | 0.25x0.3125 | c90 | 10 | 20 | default | daily | daily | 37283 (10.35 hrs) |
7345 | 17742 | 323 | 3140 |
Bob Yantosca | 003 | 12.0.1 | 1 | 6 | standard | 1 hour | GEOS-FP | 0.25x0.3125 | c24 | 10 | 20 | default | hourly | hourly | 1015 (17 min) |
28 | 269 | 47 | 693 |
Bob Yantosca | 002 | 12.0.1 | 1 | 6 | standard | 1 hour | GEOS-FP | 0.25x0.3125 | c24 | 10 | 20 | default | hourly | hourly | 525 (9 min) |
13 | 110 | 19 | 403 |
*Default diagnostics include the SpeciesConc and StateMet collections only.
Graphs of Model Run Times
These will be generated when we have a critical mass of data.
Archive of Previously Submitted Reports
Submission from Colin Lee, Dalhousie University:
Cluster name | Compilers | MPI | NetCDF library | # of Nodes | # of CPUs | GCHP version | Grid resolution | Duration [days-hrs] | Met source | Met resolution | Dynamic timestep [min] | Chemistry timestep [min] | Total run time [hrs] |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Graham | ifort 2016 | openmpi 2.1.1 | 4 | 1 | 24 | ??? | c24 | 31-0 | GEOS-FP | 2x25 | 10 | 20 | 14:22 |
Graham | ifort 2016 | openmpi 2.1.1 | 4 | 4 | 96 | ??? | c96 | 0-1 | GEOS-FP | 2x25 | 5 | 20 | 0:18 |
Graham | ifort 2016 | openmpi 2.1.1 | 4 | 4 | 96 | ??? | c96 | 0-1 | GEOS-FP | 0.25x0.3125 | 5 | 20 | 0:30 |
Graham | ifort 2016 | openmpi 2.1.1 | 4 | 72 | 864 | ??? | c360 | 0-1 | GEOS-FP | 2x2.5 | 5 | 20 | 1:30 |
Graham | ifort 2016 | openmpi 2.1.1 | 4 | 72 | 864 | ??? | c360 | 1-0 | GEOS-FP | 2x2.5 | 5 | 20 | 6:57 |
- Running on > approx. 1000 cores at c360 appears to cause a seg fault in call to SIN function around CubeToLaLon.F90:432
Submission from Sebastian Eastham, MIT (LAE)
Cluster name | Compilers | MPI | NetCDF library | # of Nodes | # or CPUs | GCHP version | Grid resolution | Duration [days-hrs] | Met source | Met resolution | Dynamic timestep [min] | Chemistry timestep [min] | Total run time [hrs] |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Nehalem | ifort 2015 | MPICH2 v3.3 | NetCDF C 4.4.1, NetCDF Fortran 4.4.4 | 2 | 36 | 11-02c | C90 | 31-0 | GEOS-FP | 0.25x0.3125 | 5 | 10 | 68 |
Notes: using 36 cores out of a total of 48 available from 2 nodes with a 10 GB direct ethernet connection.