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.

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

Add new XML variables for GPU options #25

Merged
merged 2 commits into from
Aug 15, 2023
Merged
Changes from 1 commit
Commits
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
42 changes: 40 additions & 2 deletions driver/cime_config/config_component.xml
Original file line number Diff line number Diff line change
Expand Up @@ -717,6 +717,34 @@
If TRUE, the component libraries are always built with OpenMP capability.</desc>
</entry>

<entry id="GPU_TYPE">
<type>char</type>
<valid_values></valid_values>
<default_value></default_value>
<group>build_def</group>
<file>env_build.xml</file>
<desc>If set will compile and submit with this gpu type enabled </desc>
</entry>

<entry id="GPU_OFFLOAD">
<type>char</type>
<valid_values></valid_values>
<default_value></default_value>
<group>build_def</group>
<file>env_build.xml</file>
<desc>If set will compile and submit with this gpu offload method enabled </desc>
</entry>

<entry id="MPI_GPU_WRAPPER_SCRIPT">
<type>char</type>
<valid_values></valid_values>
<default_value></default_value>
<group>build_def</group>
<file>env_build.xml</file>
<desc>If set will attach this script to the MPI run command, mapping
different MPI ranks to different GPUs within the same compute node</desc>
</entry>

<entry id="SMP_PRESENT">
<type>logical</type>
<valid_values>TRUE,FALSE</valid_values>
Expand Down Expand Up @@ -2380,12 +2408,22 @@
<desc>pes or cores per node for mpitasks </desc>
</entry>

<entry id="MAX_CPUTASKS_PER_GPU_NODE">
<type>integer</type>
<default_value>0</default_value>
<values>
<value compiler="nvhpc">1</value>
</values>
<group>mach_pes_last</group>
<file>env_mach_pes.xml</file>
<desc> Number of CPU cores per GPU node used for simulation </desc>
</entry>

<entry id="NGPUS_PER_NODE">
<type>integer</type>
<default_value>0</default_value>
<values>
<value compiler="pgi-gpu">1</value>
<value compiler="nvhpc-gpu">1</value>
<value compiler="nvhpc">1</value>
</values>
<group>mach_pes</group>
<file>env_mach_pes.xml</file>
Expand Down
Loading