Improve AMD HIP support with hipify-perl

[amd-arozanov]

Description

(AI Assist)

This PR improves AMD GPU support by migrating to automated CUDA-to-HIP conversion using hipify-perl.

Key Changes:

1. Automated CUDA-to-HIP conversion with hipify-perl
   • Introduced hipify_files() CMake function that converts CUDA source files to HIP-compatible code at build time
   • Eliminates need to manually maintain separate CUDA/HIP macro definitions
   • Uses official ROCm tool for proper API mapping and compatibility with ROCm updates
   • Limitation: Header files are not automatically converted
2. HIP support for NVLink transport
3. HIP support for nvlink-allocator
4. Compatibility fixes
   • Fixed compilation errors in examples when both USE_MNNVL and USE_HIP are enabled
5. Documentation updates
   • Added USE_HIP flag to build documentation

Type of Change

• [ ] Bug fix
• [x] New feature
  • [x] Transfer Engine
  • [ ] Mooncake Store
  • [ ] Mooncake EP
  • [ ] Integration
  • [ ] P2P Store
  • [ ] Python Wheel
• [ ] Breaking change
• [ ] CI/CD
• [x] Documentation update
• [ ] Other

How Has This Been Tested?

1. Checked build: cmake .. -DUSE_HIP=ON -DUSE_MNNVL=ON -DUSE_ETCD=ON -DSTORE_USE_ETCD=ON -DUSE_CXL=ON -DUSE_TCP=ON && make -j$(nproc) && make install

Checklist

• [x] I have performed a self-review of my own code.
• [x] I have updated the documentation.
• [x] I have added tests to prove my changes are effective.

[gemini-code-assist[bot]]

Summary of Changes

Hello @amd-arozanov, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly improves AMD GPU support by integrating automated CUDA-to-HIP conversion into the build process. It enables HIP compatibility for key components like NVLink transport and its allocator, streamlines the build system for AMD GPUs, and introduces a more abstract approach to GPU-specific headers. These changes aim to provide robust and maintainable support for AMD hardware within the project.

Highlights

• Automated CUDA-to-HIP Conversion: Introduced a hipify_files() CMake function that automatically converts CUDA source files to HIP-compatible code at build time using hipify-perl, eliminating the need for manual macro definitions and ensuring compatibility with ROCm updates.
• Enhanced HIP Support: Extended HIP support to include NVLink transport and the nvlink-allocator, integrating AMD GPU capabilities more deeply into the system.
• Build System Refinements: Updated CMake configurations to properly detect and link HIP libraries, and modified build scripts for the nvlink-allocator to support compilation with hipcc after hipify-perl processing.
• Compatibility and Code Abstraction: Implemented compatibility fixes for examples when both USE_MNNVL and USE_HIP are enabled, and refactored CUDA-specific headers to use a common cuda_alike.h abstraction for better multi-GPU platform support.
• Documentation Updates: Added the -DUSE_HIP=[ON|OFF] flag to the build documentation, making it clear how to enable AMD GPU support.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.