Skip to content

Spark hotfix #252

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

Merged
Jake-Verburgt merged 3 commits into from
Jun 11, 2026
Merged

Spark hotfix #252

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
25c20df
Removed ECE Specific section
verburgt Jun 11, 2026
4d6fd35
Added architecture FAQ
verburgt Jun 11, 2026
8370c71
small wording fix
verburgt Jun 11, 2026
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
23 changes: 10 additions & 13 deletions docs/userguides/scholar/scholar-spark.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,11 @@ authors:
date:
created: 2026-06-11
updated: 2026-06-11
search:
exclude: true
resource: Scholar
host: scholar.rcac.purdue.edu
search:
boost: 2
exclude: true
---

# Scholar Spark Nodes
Expand Down Expand Up @@ -64,16 +63,6 @@ The Spark nodes are are split into two partitions:
![Image showing a cluster layout, with the spark interactive and batch paritions specified](../../assets/images/userguides/scholar/spark/spark_structure.png)


### ECE Spark Nodes

<!-- !!! question
**TODO** If RCAC + ECE nodes are in the same interactive and batch partitions (per slack), I'm assuming that access to ECE nodes is managed by the reservations (as per the scholar spark expansion word doc)? -->


The 80 DGX Spark nodes within the `scholar-k` subcluster are for exclusive use by ECE researchers and courses at the Purdue Main Campus and Purdue Indianapolis. All eligible ECE users are added to reservations that will grant them access to these nodes, and will be automatically used for submitted jobs.

Of these, 10 (`scholar-kxxx`-`scholar-kxxx`) are exclusively for use by Purdue Main Campus, 10 (`scholar-kxxx`-`scholar-kxxx`) are exclusively for use by Purdue Indianapolis, with the remaining nodes existing within a shared pool.


## Accessing Spark Nodes

Expand Down Expand Up @@ -334,10 +323,18 @@ module load modtree/spark

If you have built or downloaded your own applications, please rebuild any applications on a Spark node, or check for an `aarch64` distribution of your software.

### How can I check the architecture of the node I'm running on?

Since Scholar has nodes with `x86_64` architecture and `aarch64` architecture, it is important to pay attention to what the architecture is on the node you plan to build or run software on. You can use the following command to print the architecture of the node you are currently running on.

```bash linenums="0"
uname -m
```


### How can I separate my `x86_64` applications from `aarch64` applications?

If you plan on working on both `aarch64` and `x86_64` nodes, we strongly reccomend separating applications and configurations in separate directories.
If you plan on working on both `aarch64` and `x86_64` nodes, we strongly recommend separating applications and configurations in separate directories.

For example, you may choose to make separate `bin` directories for `x86_64` and `aarch64` applications. In your `~/.bash_profile` file, you can then source the correct applications based on the architecture:

Expand Down