This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
library:computing:xios_impi_troubles [2017/08/04 14:26] 84.88.184.232 [Issue 3:] |
library:computing:xios_impi_troubles [2024/06/24 18:04] 84.88.52.107 old revision restored (2024/05/22 04:09) |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== NEMO-XIOS | + | ====== NEMO-XIOS Intel MPI issues |
===== NEMO-XIOS @ MN3 ===== | ===== NEMO-XIOS @ MN3 ===== | ||
- | **Environment: | + | **Environment: |
* Intel 13.0.1 & Intel MPI 4.1.3.049 | * Intel 13.0.1 & Intel MPI 4.1.3.049 | ||
Line 136: | Line 136: | ||
**Diagnosis: | **Diagnosis: | ||
- | **Solution: | + | **Solution: |
**More information: | **More information: | ||
Line 196: | Line 196: | ||
- | **Actions taken:** Given that the error is a floating invalid we disabled the -fpe0 flag, but we still were having the same problem. Then we disabled compiler optimizations (use -O0) and the problem disappeared, | + | **Actions taken:** Given that the error is a floating invalid we disabled the -fpe0 flag, but we still were having the same problem. Then we disabled compiler optimizations (use -O0) and the problem disappeared, |
- | **Diagnosis: | + | Update: Using the new NetCDF 4.2 installed by Ops and key netcdf_par for XIOS2 the model can run using O3. We have to investigate further this issue. |
+ | |||
+ | **Diagnosis: | ||
- | **Solution: | + | **Solution: |
- | ==== Issue 3: ==== | + | ==== Issue 3: MPI kills XIOS when writing model output |
**Environment: | **Environment: | ||
Line 212: | Line 214: | ||
* Flags: -O0 | * Flags: -O0 | ||
- | **Problem: | + | **Problem: |
__ocean.output__: | __ocean.output__: | ||
Line 257: | Line 259: | ||
**Actions taken:** A similar error was observed with NEMO standalone v3.6r6499. In that case, Ops told us to use the //fabric// module, which selects //ofi// as internode fabrics, similarly to the solution used in MN3 (see above). Using this module solved the problem for NEMO standalone, although it had the collateral effect that jobs were never ending. In coupled EC-Earth this module produced a dead lock, commented below. | **Actions taken:** A similar error was observed with NEMO standalone v3.6r6499. In that case, Ops told us to use the //fabric// module, which selects //ofi// as internode fabrics, similarly to the solution used in MN3 (see above). Using this module solved the problem for NEMO standalone, although it had the collateral effect that jobs were never ending. In coupled EC-Earth this module produced a dead lock, commented below. | ||
- | We tried an alternative solution, which was to increment | + | We tried an alternative solution, which was to __increment |
- | **Diagnosis: | + | **Diagnosis: |
- | **Solution: | + | **Solution: |
About Intel Communication Fabrics control: | About Intel Communication Fabrics control: | ||
[[https:// | [[https:// | ||
- | ==== Issue 4: ==== | + | |
+ | Ips_proto.c source code: | ||
+ | |||
+ | [[https:// | ||
+ | ==== Issue 4: EC-Earth enters in a dead lock when using fabric (OFA network fabrics) module | ||
**Environment: | **Environment: | ||
Line 276: | Line 282: | ||
* Flags: -O0 & -O3 | * Flags: -O0 & -O3 | ||
- | **Problem: | + | **Problem: |
- | **Actions taken:** | + | **Actions taken: |
**Diagnosis: | **Diagnosis: | ||
- | **Solution: | + | **Solution: |