https://github.com/kaocc/orochi-recipe

Orochi-recipe
https://github.com/kaocc/orochi-recipe

amd conan conan-recipe gpgpu-computing gpu

Last synced: about 1 month ago
JSON representation

Orochi-recipe

• Host: GitHub
• URL: https://github.com/kaocc/orochi-recipe
• Owner: KaoCC
• Created: 2022-07-12T14:22:37.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-09-20T19:07:06.000Z (over 2 years ago)
• Last Synced: 2024-10-31T20:07:23.329Z (3 months ago)
• Topics: amd, conan, conan-recipe, gpgpu-computing, gpu
• Language: C++
• Homepage:
• Size: 5.86 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Orochi-recipe

Orochi is a library which can load HIP and CUDA APIs dynamically.

With its support, one does not need to compile two separate implementations for each API and could maintain a single binary to run on both AMD and NVIDIA GPUs. 

## Installation

- Go to the folder where the `conanfile.py` is located

- `conan create .`

- This will clone the source from the repository of Orochi, build it as a static lib and run a test to ensure the package is installed correctly.

## Using the Orochi library

- Once installed, add `orochi/latest` in the `[requires]` section in the `conanfile.txt` in your project

## Note

- One can use `pip install conan` to install conan.