Skills
.Work. You
Rest

parallel-python

Official

Tune Python parallelism for HPC workloads.

Software Engineering#python#hpc#threading#parallelism#multiprocessing#slurm#workload-sizing
Authoryale-som-hpc
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps you optimize Python parallelism in HPC workloads by selecting the right parallelism model and sizing workers to SLURM resources, preventing oversubscription and underutilization.

Core Features & Use Cases

  • Recommend the main parallelism layer (process pool, threads, Slurm arrays) based on workload.
  • Provide guidance on start methods for multiprocessing contexts and safe parallelism practices.
  • Advise on dynamic load balancing, Slurm arrays, and avoiding nested parallelism for stable performance.
  • Real-world scenario: CPU-bound workloads benefit from one main layer with appropriate BLAS threading controls.

Quick Start

Configure your job to run with one main parallelism layer and set SLURM_CPUS_PER_TASK to size workers, then run a small benchmark.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: parallel-python
Download link: https://github.com/yale-som-hpc/claude-code-marketplace/archive/main.zip#parallel-python

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.