GPU Acceleration Skill

Official

Accelerate imaging with GPU power.

Authordsa110
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides expert guidance on configuring and utilizing GPU acceleration within the DSA-110 imaging pipeline, significantly speeding up processing times.

Core Features & Use Cases

  • GPU Configuration: Details hardware specs, driver versions, and CUDA compatibility for specific machines (e.g., h17).
  • Usage Methods: Demonstrates how to leverage GPUs via Docker, specific device selection, and environment variables.
  • WSClean Optimization: Explains optimal WSClean gridder settings (IDG modes) for different GPU memory constraints.
  • CuPy Integration: Shows how to use CuPy for GPU-accelerated photometry on large datasets.
  • Use Case: Dramatically reduce the time it takes to generate astronomical images by enabling GPU acceleration for WSClean, allowing for faster scientific discovery.

Quick Start

Run the wsclean command with GPU acceleration enabled using the dsa110-contimg:gpu Docker image.

Dependency Matrix

Required Modules

None required

Components

referencesscripts

💻 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: GPU Acceleration Skill
Download link: https://github.com/dsa110/dsa110-contimg/archive/main.zip#gpu-acceleration-skill

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 223,000+ vetted skills library on demand.