diff --git a/docs/_static/images/31174D02-Cooley800.jpg b/docs/_static/images/31174D02-Cooley800.jpg deleted file mode 100644 index bf84b8604..000000000 Binary files a/docs/_static/images/31174D02-Cooley800.jpg and /dev/null differ diff --git a/docs/_static/images/ALCF-Theta_111016-1000px.jpg b/docs/_static/images/ALCF-Theta_111016-1000px.jpg deleted file mode 100644 index 7832aeac3..000000000 Binary files a/docs/_static/images/ALCF-Theta_111016-1000px.jpg and /dev/null differ diff --git a/docs/_static/images/stampede2.jpg b/docs/_static/images/stampede2.jpg deleted file mode 100644 index d58c19487..000000000 Binary files a/docs/_static/images/stampede2.jpg and /dev/null differ diff --git a/docs/configs/cooley.yaml b/docs/configs/cooley.yaml deleted file mode 100644 index 5dccb75a7..000000000 --- a/docs/configs/cooley.yaml +++ /dev/null @@ -1,34 +0,0 @@ -engine: - type: HighThroughputEngine - max_workers_per_node: 2 - worker_debug: False - - address: - type: address_by_interface - ifname: ib0 - - provider: - type: CobaltProvider - queue: default - account: {{ YOUR_COOLEY_ALLOCATION }} - - launcher: - type: MpiExecLauncher - - # string to prepend to #COBALT blocks in the submit - # script to the scheduler - # eg: "#COBALT -t 50" - scheduler_options: {{ OPTIONS }} - - # Command to be run before starting a worker - # e.g., "module load Anaconda; source activate compute_env" - worker_init: {{ COMMAND }} - - # Scale between 0-1 blocks with 2 nodes per block - nodes_per_block: 2 - init_blocks: 0 - min_blocks: 0 - max_blocks: 1 - - # Hold blocks for 30 minutes - walltime: 00:30:00 diff --git a/docs/configs/expanse.yaml b/docs/configs/expanse.yaml index 486c0be24..5d1e370f2 100644 --- 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 index 90b8d92f6..e39cc4035 100644 --- 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 index 64001dfb3..dcd07dc0d 100644 --- a/docs/configs/midway.yaml +++ b/docs/configs/midway.yaml @@ -1,3 +1,5 @@ +display_name: Midway3@rcc.uchicago.edu + engine: type: HighThroughputEngine max_workers_per_node: 2 diff --git a/docs/configs/perlmutter.yaml b/docs/configs/perlmutter.yaml index ac811b236..41343ecca 100644 --- 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 index 66466726e..558e61472 100644 --- 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 deleted file mode 100644 index 43b8393e5..000000000 --- a/docs/configs/stampede2.yaml +++ /dev/null @@ -1,35 +0,0 @@ -display_name: Stampede2.TACC.batch - -engine: - type: HighThroughputEngine - address: - type: address_by_interface - ifname: em3 - - max_workers_per_node: 2 - - provider: - type: SlurmProvider - partition: development - - launcher: - type: SrunLauncher - - # string to prepend to #SBATCH blocks in the submit - # script to the scheduler - # e.g., "#SBATCH --constraint=knl,quad,cache" - scheduler_options: {{ OPTIONS }} - - # Command to be run before starting a worker - # e.g., module load Anaconda; source activate parsl_env - # e.g., "source ~/anaconda3/bin/activate; conda activate gce_py3.9" - worker_init: {{ COMMAND }} - - # Scale between 0-1 blocks with 2 nodes per block - nodes_per_block: 2 - init_blocks: 1 - max_blocks: 1 - min_blocks: 0 - - # Blocks are provisioned for a maxmimum of 10 minutes - walltime: 00:10:00 diff --git a/docs/configs/theta.yaml b/docs/configs/theta.yaml deleted file mode 100644 index 0441c6faf..000000000 --- a/docs/configs/theta.yaml +++ /dev/null @@ -1,37 +0,0 @@ -engine: - type: HighThroughputEngine - max_workers_per_node: 1 - worker_debug: False - - address: - type: address_by_interface - ifname: vlan2360 - - provider: - type: CobaltProvider - queue: debug-flat-quad - - # Specify the account/allocation to which jobs should be charged - account: {{ YOUR_THETA_ALLOCATION }} - - launcher: - type: AprunLauncher - overrides: -d 64 - - # string to prepend to #COBALT blocks in the submit - # script to the scheduler - # eg: "#COBALT -t 50" - scheduler_options: {{ OPTIONS }} - - # Command to be run before starting a worker - # e.g., "module load Anaconda; source activate compute_env" - worker_init: {{ COMMAND }} - - # Scale between 0-1 blocks with 2 nodes per block - nodes_per_block: 2 - init_blocks: 0 - min_blocks: 0 - max_blocks: 1 - - # Hold blocks for 30 minutes - walltime: 00:30:00 diff --git a/docs/configs/theta_singularity.yaml b/docs/configs/theta_singularity.yaml deleted file mode 100644 index 23ed7972c..000000000 --- a/docs/configs/theta_singularity.yaml +++ /dev/null @@ -1,42 +0,0 @@ -engine: - type: HighThroughputEngine - max_workers_per_node: 1 - worker_debug: False - - address: - type: address_by_interface - ifname: vlan2360 - - scheduler_mode: soft - worker_mode: singularity_reuse - container_type: singularity - container_cmd_options: -H /home/$USER - - provider: - type: CobaltProvider - queue: debug-flat-quad - - # Specify the account/allocation to which jobs should be charged - account: {{ YOUR_THETA_ALLOCATION }} - - launcher: - type: AprunLauncher - overrides: -d 64 - - # string to prepend to #COBALT blocks in the submit - # script to the scheduler - # eg: "#COBALT -t 50" - scheduler_options: {{ OPTIONS }} - - # Command to be run before starting a worker - # e.g., "module load Anaconda; source activate compute_env" - worker_init: {{ COMMAND }} - - # Scale between 0-1 blocks with 2 nodes per block - nodes_per_block: 2 - init_blocks: 0 - min_blocks: 0 - max_blocks: 1 - - # Hold blocks for 30 minutes - walltime: 00:30:00 diff --git a/docs/configuring.rst b/docs/configuring.rst index 9207ed4f4..4d797b74c 100644 --- 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) ^^^^^^^^^^^^^