Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

updates for perlmutter #184

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

updates for perlmutter #184

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions machines/perlmutter/config_batch.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,11 +7,14 @@
<argument> --account $PROJECT </argument>
</submit_args>
<directives>
<directive>-C gpu </directive>
<directive>--constraint=cpu </directive>
</directives>
<queues>
<queue walltimemax="06:00:00" nodemin="1" nodemax="128">regular</queue>
<queue walltimemax="02:00:00" nodemin="1" nodemax="4" default="true">debug</queue>
<!-- Note: walltime is not the max walltime, but the default - see NERSC docs for Q limits, https://docs.nersc.gov/jobs/policy/ -->
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should the comment be "walltimemax is not the max walltime"

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sure I can update that when I am able to test. Meanwhile I'm going to make this a draft.

<queue walltimemax="00:30:00" nodemax="3072" default="true">regular</queue>
<queue walltimemax="00:30:00" nodemax="3072" strict="true">preempt</queue>
<queue walltimemax="00:30:00" nodemax="3072" strict="true">shared</queue>
<queue walltimemax="00:30:00" nodemax="8" strict="true">debug</queue>
</queues>
</batch_system>

65 changes: 40 additions & 25 deletions machines/perlmutter/config_machines.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
<machine MACH="perlmutter">
<DESC>NERSC EX AMD EPYC, os is CNL, 64 pes/node, batch system is Slurm</DESC>
<OS>CNL</OS>
<COMPILERS>gnu,cray,nvidia,aocc</COMPILERS>
<COMPILERS>intel,gnu,cray,nvidia,aocc</COMPILERS>
<MPILIBS>mpich</MPILIBS>
<PROJECT>mp9_g</PROJECT>
<CIME_OUTPUT_ROOT>$ENV{SCRATCH}</CIME_OUTPUT_ROOT>
Expand All @@ -25,7 +25,7 @@
<arg name="binding"> -c {{ srun_binding }}</arg>
</arguments>
</mpirun>
<module_system type="module">
<module_system type="module" allow_error="true">
<init_path lang="perl">/usr/share/lmod/lmod/init/perl</init_path>
<init_path lang="python">/usr/share/lmod/lmod/init/env_modules_python.py</init_path>
<init_path lang="sh">/usr/share/lmod/lmod/init/sh</init_path>
Expand All @@ -35,24 +35,36 @@
<cmd_path lang="sh">module</cmd_path>
<cmd_path lang="csh">module</cmd_path>
<modules>
<command name="rm">PrgEnv-nvidia</command>
<command name="rm">PrgEnv-cray</command>
<command name="rm">PrgEnv-aocc</command>
<command name="rm">PrgEnv-gnu</command>
<command name="rm">nvidia</command>
<command name="rm">cce</command>
<command name="rm">gnu</command>
<command name="rm">aocc</command>
<command name="rm">cray-parallel-netcdf</command>
<command name="rm">cray-hdf5-parallel</command>
<command name="rm">cray-libsci</command>
<command name="rm">cray-mpich</command>
<command name="rm">cray-hdf5</command>
<command name="rm">cray-netcdf-hdf5parallel</command>
<command name="rm">cray-netcdf</command>
<command name="rm">craype</command>
<command name="unload">cray-hdf5-parallel</command>
<command name="unload">cray-netcdf-hdf5parallel</command>
<command name="unload">cray-parallel-netcdf</command>
<command name="unload">cray-netcdf</command>
<command name="unload">cray-hdf5</command>
<command name="unload">PrgEnv-gnu</command>
<command name="unload">PrgEnv-intel</command>
<command name="unload">PrgEnv-nvidia</command>
<command name="unload">PrgEnv-cray</command>
<command name="unload">PrgEnv-aocc</command>
<command name="unload">gcc-native</command>
<command name="unload">intel</command>
<command name="unload">intel-oneapi</command>
<command name="unload">nvidia</command>
<command name="unload">aocc</command>
<command name="unload">cudatoolkit</command>
<command name="unload">climate-utils</command>
<command name="unload">cray-libsci</command>
<command name="unload">matlab</command>
<command name="unload">craype-accel-nvidia80</command>
<command name="unload">craype-accel-host</command>
<command name="unload">perftools-base</command>
<command name="unload">perftools</command>
<command name="unload">darshan</command>
</modules>

<modules compiler="intel">
<command name="load">PrgEnv-intel</command>
</modules>

<modules compiler="cray">
<command name="load">PrgEnv-cray</command>
<command name="switch">cce cce/12.0.3</command>
Expand All @@ -62,10 +74,8 @@

</modules>
<modules>
<command name="swap">craype craype/2.7.30</command>
</modules>
<modules>
<command name="switch">cray-libsci/23.12.5</command>
<command name="load">craype-x86-milan</command>
<command name="switch">cray-libsci/23.09.1.1</command>
</modules>
<modules>
<command name="load">cray-mpich/8.1.28</command>
Expand All @@ -83,12 +93,17 @@
<command name="load">cray-parallel-netcdf</command>
</modules>
<modules>
<command name="load">cmake/3.22.0</command>
<command name="load">cmake/3.24.3</command>
</modules>
</module_system>
<environment_variables>
<env name="OMP_STACKSIZE">256M</env>
<!-- <env name="OMP_PROC_BIND">spread</env>
<env name="OMP_PLACES">threads</env> -->
<env name="ESMFMKFILE">/global/cfs/cdirs/ccsm1/esmf//lib/libO/Unicos.intel.64.mpi.default/esmf.mk</env>
<env name="PIO_VERSION_MAJOR">2</env>
<env name="PIO_LIBDIR">/global/cfs/cdirs/ccsm1/parallelio/2.6.3/2023.2.0/8.1.28/lib</env>
<env name="PIO_INCDIR">/global/cfs/cdirs/ccsm1/parallelio/2.6.3/2023.2.0/8.1.28/include</env>
<env name="PIO_TYPENAME_VALID_VALUES">pnetcdf,netcdf,netcdf4p</env>
<env name="ESMF_RUNTIME_PROFILE">ON</env>
<env name="ESMF_RUNTIME_PROFILE_OUTPUT">SUMMARY</env>
</environment_variables>
</machine>