Caution
hipDNN is in the early stages of development. There is currently limited functionality available to solve problems. See Operation Support for reference.
hipDNN is a graph-based deep learning library for AMD GPUs that leverages a flexible plugin architecture to provide optimized implementations and utilities for various routines.
The fastest way to get started with hipDNN is to follow the quick start steps in the build guide.
- Building - Prerequisites, build configurations, and platform-specific instructions
- How-To - Using hipDNN components and extending the framework
- Environment Configuration - Runtime configuration and logging setup
- Operation Support - Currently supported operations and their status
- Samples - Frontend usage examples
- Design Overview - Architecture and design descriptions and diagrams
- Extending hipDNN - How to extend hipDNN functionality
- Plugin Development - Creating and using custom plugins for hipDNN
- Roadmap - Feature priorities and development plans
- Testing - Synopsis of testing information
- Testing Strategy - Specific testing approach
- Test Plan - Detailed test planning
- Test Run Template - Guidelines for test execution
hipDNN is organized into several key components. For detailed architecture descriptions, see the Design Overview.
| Component | Description |
|---|---|
| Backend | Core shared library providing C API for operation graphs and managing plugins |
| Frontend | Header-only C++ API wrapper around the backend |
| SDK | Header-only library for plugin development and utilities |
| Plugins | Plugin implementations, including MIOpen Legacy Plugin |
| Samples | Example implementations demonstrating hipDNN usage |
| Tests | Tests for the public API (incl. frontend integration tests) |
See Docker README for containerized development environments.
For information about contributing to the hipDNN project, please see the Contributing Guide.