Score-P is a profiling software for parallel codes.

On Cooley

Do the usual configure –prefix=$PWD/install, make, make install.
export PATH=$PWD/install/bin:$PWD
Recompile the code you want to profile by replacing all gcc with scorep gcc everywhere (or g++ by scorep g++).
Score-P uses environment variables to control it. A full list is here.
- These two tell Score-P if it should do Profiling or Tracing. I don't think you can do both at the same time. I've had trouble getting Tracing to work, but if you can use it, it is the mode that produced output for Vampir. Tracing uses a lot of disk space. Profiling gives you information like global time spent in functions and rank-wise usage.
- SCOREP_ENABLE_PROFILING=true produces output for “Cube”
- SCOREP_ENABLE_TRACING=false produces output for “Vampir”.
- SCOREP_TOTAL_MEMORY=10G (default is 16M) this is the amount I had to use for Sherpa on Cooley.
- SCOREP_PROFILING_MAX_CALLPATH_DEPTH=50 (default is 30) Score-P complained that Sherpa had a depth of 38!!
Run your code…
You'll notice a scorep_<date>_<time>_<random number> folder in the run directory.
To view the profile.cubex ouput just run the cube executable in the Score-P install/bin folder.
Cube manual

ATLAS Support Center