Port CUDA Kernel to HIP

Official

Port CUDA kernels to HIP with ROCm parity.

Authortensormux
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Port CUDA kernels to HIP for ROCm-enabled AMD GPUs while preserving correctness and performance intent during migration.

Core Features & Use Cases

  • HIP porting workflow: From CUDA to HIP using hipify, with careful review of semantic differences.
  • Wavefront and memory model adaptation: Handles AMD's 64-wide wavefronts and memory semantics.
  • Validation & tooling guidance: Guidance on compiling, testing, and verifying numerical equivalence to the CUDA reference.

Quick Start

Port a minimal CUDA kernel to HIP and verify functional parity on an AMD device.

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: Port CUDA Kernel to HIP
Download link: https://github.com/tensormux/kernel-skills/archive/main.zip#port-cuda-kernel-to-hip

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 510,000+ vetted skills library on demand.