Version 22 (modified by ajornet, 8 years ago) (diff) |
---|
ORCHIDEE performance (trunk revision 3623)
In order to test Orchidee performance several decisions have been done. Check the details below:
- Trunk
- Revision 3623
- In Curie
- Production mode
- XIOS
- IOIPSL
- Orchidee
- Real CPU Time
- XIOS library
Note: the total cpu time can be calculated by multiplying with the numbers of MPI used.
Table 1: Orchidee Scalability
Following table shows:
- Simulation length: 1Y
- FG2.CWRR configuration
- Output level
- monthly
- daily output
- MPI parallelization
- e.g: 64 Cores Simulation = 1 XIOS core + 63 Orchidee cores
- Forcing resolution vs number of cores
- Cell Format: out_orchidee_00XX (in seconds) / orchid_XXXXX.o
Note: no server is used for 1 MPI case
XIOS
XIOS only writes the history outputs files.
1 MPI | 4 MPI | 8 MPI | 16 MPI | 32 MPI | 64 MPI | 128 MPI | |
twodeg | 4928/1h25 | 1732/32m18 | 812/17m1 | 409/10m23 | 240/7m33 | 165/6m12 | 142/6m30 |
onedeg | Not possible | Mem limit | 2734/57m | 1334/33m40 | 710/23m07 | 436/18m32 | 398/17m50 |
halfdeg | Not possible | Mem limit | 10175/3h33 | 4772/2h03 | 2490/1h25 | 1404/1h05 | 1251/1h02 |
Folder output size :
- 2 deg: 2.6GB
- 1 deg: 10GB
- 0.5 deg: 30 GB
XIOS (restart)
1 MPI | 4 MPI | 8 MPI | 16 MPI | 32 MPI | 64 MPI | 128 MPI | |
twodeg | 4883/1h21 | 1741/29m | 807/13m45 | 409/7m06 | 242/4m24 | 166/3m11 | 160/3m20 |
onedeg | Mem limit | 5983/1h40 | 2773/47m03 | 1333/23m | 722/12m42 | 462/8m13 | 380/7m05 |
halfdeg | Not tested | Mem limit | 10135/2h50 | 4760/1h20 | 2462/42m07 | 1393/24m02 | 1174/20m36 |
IOIPSL
Only IOIPSL enabled.
1 MPI | 4 MPI | 8 MPI | 16 MPI | 32 MPI | 64 MPI | 128 MPI | |
twodeg | 5656/1h37 | 1552/29m | 819/16m36 | 441/10m20 | 267/7m30 | 177/5m59 | 135/5m21 |
onedeg | 19677/5h39 | 5841/1h48 | 3126/1h03 | 1723/36m44 | 1027/28m10 | 678/21m47 | 516/19m33 |
halfdeg | >16h40 (max limit) | 23974/7h21 | 13908/4h32 | 7702/2h49 | 4672/1h58 | 3036/1h32 | 2173/1h17 |
IOIPSL (restart)
1 MPI | 4 MPI | 8 MPI | 16 MPI | 32 MPI | 64 MPI | 128 MPI | |
twodeg | 5666/1h34 | 1557/26m04 | 812/13m39 | 443/7m31 | 265/4m40 | 182/3m15 | 147/2m38 |
onedeg | 21360/5h56 | 5637/1h34 | 3135/52m57 | 1720/28m54 | 1036/17m30 | 704/12m | 519/8m53 |
halfdeg | >16h40 (max limit) | 22985/6h23 | 13820/3h50 | 7679/2h08 | 4627/1h17 | 3014/50m34 | 2183/36m45 |
Table 2: Orchidee XIOS scalability (IO)
In this table the set up FG2.CWRR is used with 63MPI for orchidee_ol and 1MPI for the server XIOS. For the case with IOIPSL, then 64MPI are used for orchidee_ol. The first line describes different levels of output.
yearly with XIOS | monthly with XIOS | monthly and daily with XIOS | daily and 3hour with XIOS | daily and 3hour with IOIPSL | |
twodeg | |||||
onedeg | |||||
halfdeg |
FG2.CWRR
Description of the test case... to come