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

Update quickstart example config #3695

Merged
merged 3 commits into from
Nov 12, 2024
Merged

Update quickstart example config #3695

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
75e9df1
Correct typo with retries
ryanchard Nov 12, 2024
9c27645
Update quickstart example to just acquire one node in debug, rather t…
ryanchard Nov 12, 2024
869a2ad
Add necessary import statements to the quickstart PBS config.
ryanchard Nov 12, 2024
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
13 changes: 9 additions & 4 deletions docs/quickstart.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,12 +176,17 @@ This script runs on a system that must stay on-line until all of your tasks comp
much computing power, such as the login node for a supercomputer.

The :class:`~parsl.config.Config` object holds definitions of Executors and the Providers and Launchers they rely on.
An example which launches 512 workers on 128 nodes of the Polaris supercomputer looks like
An example which launches 4 workers on 1 node of the Polaris supercomputer looks like

.. code-block:: python

from parsl import Config
from parsl.executors import HighThroughputExecutor
from parsl.providers import PBSProProvider
from parsl.launchers import MpiExecLauncher

config = Config(
retires=1, # Restart task if they fail once
retries=1, # Restart task if they fail once
executors=[
HighThroughputExecutor(
available_accelerators=4, # Maps one worker per GPU
Expand All @@ -191,13 +196,13 @@ An example which launches 512 workers on 128 nodes of the Polaris supercomputer
account="example",
worker_init="module load conda; conda activate parsl",
walltime="1:00:00",
queue="prod",
queue="debug",
scheduler_options="#PBS -l filesystems=home:eagle", # Change if data on other filesystem
launcher=MpiExecLauncher(
bind_cmd="--cpu-bind", overrides="--depth=64 --ppn 1"
), # Ensures 1 manger per node and allows it to divide work to all 64 cores
select_options="ngpus=4",
nodes_per_block=128,
nodes_per_block=1,
cpus_per_node=64,
),
),
Expand Down
Loading