Modify Templating to Work with Omniperf and Rocprof

wilfonba commented 1 month ago

Description

Changes how profiling is added to the template so that profiling works with AMDs tools

Type of change

[x] Something else

Scope

[x] This PR comprises a set of related changes with a common goal

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

I tested this with ./mfc.sh run examples/1D_sodshocktube -n 1 --nsyson Wingtip and with./mfc.sh run examples/1D_sodshocktube -n 1 --omni` on Frontier.

Checklist

[x] New and existing tests pass locally with my changes, including with GPU capability enabled (both NVIDIA hardware with NVHPC compilers and AMD hardware with CRAY compilers) and disabled
[x] This PR does not introduce any repeated code (it follows the DRY principle)
[x] I cannot think of a way to condense this code and reduce any introduced additional line count

sbryngelson commented 1 month ago

Please sync w/ master

sbryngelson commented 1 month ago

I'm happy with this when @henryleberre is.

I would like the GPU benchmark to pass before merging, but all GPU Phoenix cases are failing right now because they cannot get on a node.

MFlowCode / MFC