Merge branch 'main' into v2.19.0

globus · Apr 25, 2024 · d779b69 · d779b69
2 parents d178102 + f43e024
commit d779b69
Show file tree

Hide file tree

Showing 13 changed files with 47 additions and 231 deletions.
diff --git a/docs/_static/images/31174D02-Cooley800.jpg b/docs/_static/images/31174D02-Cooley800.jpg
diff --git a/docs/_static/images/ALCF-Theta_111016-1000px.jpg b/docs/_static/images/ALCF-Theta_111016-1000px.jpg
diff --git a/docs/_static/images/stampede2.jpg b/docs/_static/images/stampede2.jpg
diff --git a/docs/configs/cooley.yaml b/docs/configs/cooley.yaml
diff --git a/docs/configs/expanse.yaml b/docs/configs/expanse.yaml
@@ -1,6 +1,7 @@
-display_name: SDSC Expanse
+display_name: Expanse@SDSC
+
 engine:
-    type: HighThroughputEngine
+    type: GlobusComputeEngine
     max_workers_per_node: 2
     worker_debug: False
 
@@ -25,7 +26,11 @@ engine:
         # e.g., "module load anaconda3; source activate gce_env"
         worker_init: {{ COMMAND }}
 
-        init_blocks: 1
+        # Command to be run before starting a worker
+        # e.g., "module load anaconda3; source activate gce_env"
+        worker_init: "source ~/setup.sh"
+
+        init_blocks: 0
         min_blocks: 0
         max_blocks: 1
 

diff --git a/docs/configs/frontera.yaml b/docs/configs/frontera.yaml
@@ -1,5 +1,7 @@
+display_name: Frontera@TACC
+
 engine:
-    type: HighThroughputEngine
+    type: GlobusComputeEngine
     max_workers_per_node: 2
     worker_debug: False
 

diff --git a/docs/configs/midway.yaml b/docs/configs/midway.yaml
@@ -1,3 +1,5 @@
+display_name: [email protected]
+
 engine:
     type: HighThroughputEngine
     max_workers_per_node: 2

diff --git a/docs/configs/perlmutter.yaml b/docs/configs/perlmutter.yaml
@@ -1,17 +1,15 @@
+display_name: Permutter@NERSC
 engine:
-    type: HighThroughputEngine
+    type: GlobusComputeEngine
     worker_debug: False
 
-    strategy:
-        type: SimpleStrategy
-        max_idletime: 300
-
     address:
         type: address_by_interface
         ifname: hsn0
 
     provider:
         type: SlurmProvider
+        partition: debug
 
         # We request all hyperthreads on a node.
         # GPU nodes have 128 threads, CPU nodes have 256 threads
@@ -21,8 +19,9 @@ engine:
 
         # string to prepend to #SBATCH blocks in the submit
         # script to the scheduler
-        # For GPUs in the debug qos eg: "#SBATCH --constraint=gpu -q debug"
+        # For GPUs in the debug qos eg: "#SBATCH --constraint=gpu"
         scheduler_options: {{ OPTIONS }}
+
         # Your NERSC account, eg: "m0000"
         account: {{ NERSC_ACCOUNT }}
 

diff --git a/docs/configs/polaris.yaml b/docs/configs/polaris.yaml
@@ -1,40 +1,38 @@
-engine:
-    type: HighThroughputEngine
-    max_workers_per_node: 1
+display_name: Polaris@ALCF
 
-    # Un-comment to give each worker exclusive access to a single GPU
-    # available_accelerators: 4
+engine:
+  type: GlobusComputeEngine
+  max_workers_per_node: 4
 
-    strategy:
-        type: SimpleStrategy
-        max_idletime: 300
+  # Un-comment to give each worker exclusive access to a single GPU
+  # available_accelerators: 4
 
-    address:
-        type: address_by_interface
-        ifname: bond0
+  address:
+    type: address_by_interface
+    ifname: bond0
 
-    provider:
-        type: PBSProProvider
+  provider:
+    type: PBSProProvider
 
-        launcher:
-            type: MpiExecLauncher
-            # Ensures 1 manger per node, work on all 64 cores
-            bind_cmd: --cpu-bind
-            overrides: --depth=64 --ppn 1
+    launcher:
+      type: MpiExecLauncher
+      # Ensures 1 manger per node, work on all 64 cores
+      bind_cmd: --cpu-bind
+      overrides: --depth=64 --ppn 1
 
-        account: {{ YOUR_POLARIS_ACCOUNT }}
-        queue: preemptable
-        cpus_per_node: 32
-        select_options: ngpus=4
+    account: {{ YOUR_POLARIS_ACCOUNT }}
+    queue: debug-scaling
+    cpus_per_node: 32
+    select_options: ngpus=4
 
-        # e.g., "#PBS -l filesystems=home:grand:eagle\n#PBS -k doe"
-        scheduler_options: "#PBS -l filesystems=home:grand:eagle"
+    # e.g., "#PBS -l filesystems=home:grand:eagle\n#PBS -k doe"
+    scheduler_options: "#PBS -l filesystems=home:grand:eagle"
 
-        # Node setup: activate necessary conda environment and such
-        worker_init: {{ COMMAND }}
+    # Node setup: activate necessary conda environment and such
+    worker_init: {{ COMMAND }}
 
-        walltime: 01:00:00
-        nodes_per_block: 1
-        init_blocks: 0
-        min_blocks: 0
-        max_blocks: 2
+    walltime: 01:00:00
+    nodes_per_block: 1
+    init_blocks: 0
+    min_blocks: 0
+    max_blocks: 2
diff --git a/docs/configs/stampede2.yaml b/docs/configs/stampede2.yaml
diff --git a/docs/configs/theta.yaml b/docs/configs/theta.yaml
diff --git a/docs/configs/theta_singularity.yaml b/docs/configs/theta_singularity.yaml
diff --git a/docs/configuring.rst b/docs/configuring.rst
@@ -108,37 +108,6 @@ The KubernetesProvider exploits the Python Kubernetes API, which assumes that yo
    :language: yaml
 
 
-Theta (ALCF)
-^^^^^^^^^^^^
-
-.. image:: _static/images/ALCF-Theta_111016-1000px.jpg
-
-The following snippet shows an example configuration for executing on Argonne Leadership Computing Facility's
-**Theta** supercomputer. This example uses the ``HighThroughputEngine`` and connects to Theta's Cobalt scheduler
-using the ``CobaltProvider``. This configuration assumes that the script is being executed on the login nodes of Theta.
-
-.. literalinclude:: configs/theta.yaml
-   :language: yaml
-
-The following configuration is an example to use singularity container on Theta.
-
-.. literalinclude:: configs/theta_singularity.yaml
-   :language: yaml
-
-
-Cooley (ALCF)
-^^^^^^^^^^^^^
-
-.. image:: _static/images/31174D02-Cooley800.jpg
-
-The following snippet shows an example configuration for executing on Argonne Leadership Computing Facility's
-**Cooley** cluster. This example uses the ``HighThroughputEngine`` and connects to Cooley's Cobalt scheduler
-using the ``CobaltProvider``. This configuration assumes that the script is being executed on the login nodes of Cooley.
-
-.. literalinclude:: configs/cooley.yaml
-   :language: yaml
-
-
 Polaris (ALCF)
 ^^^^^^^^^^^^^^
 
@@ -199,17 +168,6 @@ running on a login node, uses the ``SlurmProvider`` to interface with the schedu
 .. literalinclude:: configs/bridges-2.yaml
    :language: yaml
 
-Stampede2 (TACC)
-^^^^^^^^^^^^^^^^
-
-.. image:: _static/images/stampede2.jpg
-
-The following snippet shows an example configuration for accessing the Stampede2 system at the Texas Advanced Computing Center (TACC).
-The configuration below assumes that the user is running on a login node, uses the ``SlurmProvider`` to interface with the scheduler,
-and uses the ``SrunLauncher`` to launch workers.
-
-.. literalinclude:: configs/stampede2.yaml
-   :language: yaml
 
 FASTER (TAMU)
 ^^^^^^^^^^^^^