cuda-c-patterns

Community

CUDA-C patterns: vector ops, reductions, matmul.

Authorxchang1121
Version1.0.0
Installs0

System Documentation

What problem does it solve?

CUDA-C patterns provide structured templates for common GPU programming tasks, enabling faster, correct, and performant kernel implementations.

Core Features & Use Cases

  • Vector operation pattern: simple, vectorized element-wise kernels with proper indexing and boundary handling.
  • Reduction pattern: scalable reduction strategies using shared memory and synchronization.
  • Matrix multiplication pattern: tiled, memory-efficient matmul with optional shared memory usage.

Quick Start

Use CUDA-C pattern templates to implement a vector op kernel and validate it on a small test array.

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: cuda-c-patterns
Download link: https://github.com/xchang1121/AutoResearch-CC-hook/archive/main.zip#cuda-c-patterns

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.