hpc-code-reviewer

Community

Streamline parallel code reviews for correctness.

AuthorSamyakJhaveri
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Provides a structured checklist to identify correctness issues in parallel CUDA, OpenMP, and OpenCL code, including data races, memory-model violations, and synchronization bugs, especially when reviewing translated code, auditing benchmark sources, or documenting failure modes.

Core Features & Use Cases

  • Comprehensive review checklist covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls across CUDA, OpenMP, and OpenCL.
  • Practical guidance for auditing benchmark sources, reviewing LLM-generated translations, and preparing academic analyses of failure modes.
  • Triggered by explicit review requests or when evaluating parallel kernels to ensure root-cause analysis and reproducible results.

Quick Start

Run the HPC Code Reviewer on your parallel kernels to systematically identify and root-cause correctness issues.

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: hpc-code-reviewer
Download link: https://github.com/SamyakJhaveri/loam/archive/main.zip#hpc-code-reviewer

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 545,000+ vetted skills library on demand.