AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update documentation (#53)

Browse Source 
- updated info about OMNITRACE_USE_MPI
- removed wiki links
- info about metadata.json
- update HW counters and fix typos
- fix update-docs.sh
This commit is contained in:
Jonathan R. Madsen
2022-05-08 02:51:35 -05:00
committed by GitHub
parent 134b33320d
commit bab90baf0b
5 changed files with 571 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files
source/docs/installation.md
+3 -3
View File
@@ -149,9 +149,9 @@ source ${OMNITRACE_ROOT}/share/omnitrace/setup-env.sh
#### MPI Support within Omnitrace
[Omnitrace](https://github.com/AMDResearch/omnitrace) can have full (`OMNITRACE_USE_MPI=ON`) or partial (`OMNITRACE_USE_MPI_HEADERS=ON`) MPI support.
The only difference between these two modes is whether or not the results collected via timemory can be aggregated into one output file. The primary
benefits of partial or full MPI support are the automatic wrapping of MPI functions and the ability to label output with suffixes which correspond to the
`MPI_COMM_WORLD` rank ID instead of using the system process identifier (i.e. PID).
The only difference between these two modes is whether or not the results collected via timemory and/or perfetto can be aggregated into a single
output file during finalization. The primary benefits of partial or full MPI support are the automatic wrapping of MPI functions and the ability
to label output with suffixes which correspond to the `MPI_COMM_WORLD` rank ID instead of using the system process identifier (i.e. PID).
In general, it is recommended to use partial MPI support with the OpenMPI headers as this is the most portable configuration.
If full MPI support is selected, make sure your target application is built against the same MPI distribution as omnitrace,
i.e. do not build omnitrace with MPICH and use it on a target application built against OpenMPI.