# Cluster profile for Snakemake used in the HPC Workflows lessons
#
# This is a YAML file (<https://yaml.org>, a hierarchical plain-text
# data storage format for lists, key-value pairs, and nested instances
# of either or both. Indentation and punctuation matter!
#
# Use a YAML linter to check for syntax errors after editing:
# yamllint config.yaml
---
# --------------------------------------
# Scheduler settings (cluster-dependent)
# --------------------------------------
# A full listing is in the Snakemake distribution's top-level `__init__.py`
# file. You can view the latest version on the official repository:
# <https://github.com/snakemake/snakemake/blob/main/snakemake/__init__.py>
cluster:
 sbatch
 --job-name={rule}-np{resources.tasks}
 --partition={resources.partition}
 --nodes={resources.nodes}
 --ntasks={resources.tasks}
 --time={resources.time}
 --output=slurm_{rule}_np{resources.tasks}.log
default-resources:
 - partition=rack6 # name of partition (or queue) on which jobs will run
 - nodes=1 # number of cluster nodes to reserve
 - tasks=1 # number of cluster cores to reserve (total)
 - time=5 # maximum expected runtime of each job, in minutes
# ------------------------------------------
# Global job settings (platform independent)
# ------------------------------------------
# directory where Conda or Mamba is installed
# default: none
conda-base-path: "~/mambaforge"
# use a Conda environment
# default: false
use-conda: true
# run at most N CPU cluster jobs in parallel
# default: number of cores on host machine
jobs: 500
# max frequency of job status checks
# default: 10
max-status-checks-per-second: 1
# use at most N cores of the host machine in parallel
# (the cores are used to execute local rules)
# default: number of cores on host machine
local-cores: 1
# how many seconds to wait for an output file
# to appear after the execution of a rule
# (cluster filesystem latency hurts!)
# default: 3
latency-wait: 60
# keep going with independent jobs if a job fails?
# default: false
keep-going: false
# print the shell command of each job
# default: false
printshellcmds: true

# Snakefile to run Amdahl's Law for HPC Workflows
TASKS = [5, 6, 7, 8]
rule plot:
 input:
 expand("amdahl_np{task}.json", task=TASKS)
 output:
 "plot.log"
 log:
 "smk_plot.log"
 resources:
 tasks=1
 conda:
 "amdahl"
 shell:
 "echo {input} > {output}"
rule amdahl:
 input:
 output:
 "amdahl_np{sample}.json"
 log:
 "smk_np{sample}.log"
 resources:
 tasks=lambda wildcards: int(wildcards.sample)
 shell:
 "mpirun amdahl --terse > {output}"
rule clean:
 input:
 output:
 resources:
 tasks=1
 conda:
 "amdahl"
 shell:
 "rm *.log *.json"

snakemake --profile cluster/