{"id":13517807,"url":"https://github.com/vosen/ZLUDA","last_synced_at":"2025-03-31T09:30:47.762Z","repository":{"id":45712860,"uuid":"231958668","full_name":"vosen/ZLUDA","owner":"vosen","description":"CUDA on non-NVIDIA GPUs","archived":false,"fork":false,"pushed_at":"2024-10-16T01:15:49.000Z","size":3817,"stargazers_count":9578,"open_issues_count":96,"forks_count":625,"subscribers_count":132,"default_branch":"master","last_synced_at":"2024-10-29T15:36:06.956Z","etag":null,"topics":["cuda","rust"],"latest_commit_sha":null,"homepage":"https://vosen.github.io/ZLUDA/","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vosen.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE-APACHE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-01-05T18:26:03.000Z","updated_at":"2024-10-29T15:29:53.000Z","dependencies_parsed_at":"2024-04-17T23:32:49.321Z","dependency_job_id":"0e68de1d-868a-4d68-9ed8-b41d46969b04","html_url":"https://github.com/vosen/ZLUDA","commit_stats":{"total_commits":325,"total_committers":5,"mean_commits":65.0,"dds":"0.012307692307692353","last_synced_commit":"3870a96592c6a93d3a68391f6cbaecd9c7a2bc97"},"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vosen%2FZLUDA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vosen%2FZLUDA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vosen%2FZLUDA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vosen%2FZLUDA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vosen","download_url":"https://codeload.github.com/vosen/ZLUDA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246446772,"owners_count":20778871,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cuda","rust"],"created_at":"2024-08-01T05:01:37.598Z","updated_at":"2025-03-31T09:30:47.750Z","avatar_url":"https://github.com/vosen.png","language":"Rust","funding_links":[],"categories":[":steam_locomotive: Runtime Environment","Software","Rust","其他_机器学习与深度学习","rust","Other","Frameworks","GPU Programming","Repos","Miscellaneous","Hardware"],"sub_categories":["Web Development","Trends","Other","Miscellaneous"],"readme":"[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=for-the-badge\u0026logo=discord\u0026logoColor=white)](https://discord.gg/sg6BNzXuc7)\n\n# ZLUDA\n\nZLUDA is a drop-in replacement for CUDA on non-NVIDIA GPU. ZLUDA allows to run unmodified CUDA applications using non-NVIDIA GPUs with near-native performance.\n\nZLUDA supports AMD Radeon RX 5000 series and newer GPUs (both desktop and integrated).\n\n![GeekBench 5.5.1 chart](geekbench.svg)\n\nZLUDA is work in progress. Follow development here and say hi on [Discord](https://discord.gg/sg6BNzXuc7). For more details see the announcement: https://vosen.github.io/ZLUDA/blog/zludas-third-life/\n\n## Usage\n**Warning**: This version ZLUDA is under heavy development (more [here](https://vosen.github.io/ZLUDA/blog/zludas-third-life/)) and right now only supports Geekbench. ZLUDA probably will not work with your application just yet.\n\n### Windows\nYou should have recent AMD GPU driver (\"AMD Software: Adrenalin Edition\") installed.\\\nTo run your application you should etiher:\n* (Recommended approach) Copy ZLUDA-provided `nvcuda.dll` and `nvml.dll` from `target\\release` (if built from sources) or `zluda` (if downloaded a zip package) into a path which your application uses to load CUDA. Paths vary application to application, but usually it's the directory where the .exe file is located\n* Use ZLUDA launcher like below. ZLUDA launcher is known to be buggy and incomplete:\n    ```\n    \u003cZLUDA_DIRECTORY\u003e\\zluda_with.exe -- \u003cAPPLICATION\u003e \u003cAPPLICATIONS_ARGUMENTS\u003e\n    ```\n\n### Linux\n\nRun your application like this:\n```\nLD_LIBRARY_PATH=\u003cZLUDA_DIRECTORY\u003e \u003cAPPLICATION\u003e \u003cAPPLICATIONS_ARGUMENTS\u003e\n```\n\nwhere `\u003cZLUDA_DIRECTORY\u003e` is the directory which contains ZLUDA-provided `libcuda.so`: `target/release` if you built from sources or `zluda` if you downloaded prebuilt package.\n\n### MacOS\n\nNot supported\n\n## Building\n\n### Dependencies\n\n* Git\n* CMake\n* Python 3\n* Rust compiler (recent version)\n* C++ compiler\n* (Optional, but recommended) [Ninja build system](https://ninja-build.org/)\n\n### Build steps\n\n* Git clone the repo (make sure to use `--recursive` option to fetch submodules):  \n`git clone --recursive https://github.com/vosen/ZLUDA.git`  \n* Enter freshly cloned `ZLUDA` directory and build with cargo (this takes a while):  \n`cargo xtask --release`\n\n## Contributing\n\nZLUDA project has a commercial backing and _does not_ accept donations.\nZLUDA project accepts pull requests and other non-monetary contributions.\n\nIf you want to contribute a code fix or documentation update feel free to open a Pull Request.\n\n### Getting started\n\nThere's no architecture document (yet). Two most important crates in ZLUDA are `ptx` (PTX compiler) and `zluda` (AMD GPU runtime). A good starting point to tinkering the project is to run one of the `ptx` unit tests under a debugger and understand what it is doing. `cargo test -p ptx -- ::add_hip` is a simple test that adds two numbers.\n\nGithub issues tagged with [\"help wanted\"](https://github.com/vosen/ZLUDA/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22) are tasks that are self-containted. Their level of difficulty varies, they are not always good beginner tasks, but they defined unambiguously.\n\nIf you have questions feel free to ask on [#devtalk channel on Discord](https://discord.com/channels/1273316903783497778/1303329281409159270).\n\n\n## License\n\nThis software is dual-licensed under either the Apache 2.0 license or the MIT license. See [LICENSE-APACHE](LICENSE-APACHE) or [LICENSE-MIT](LICENSE-MIT) for details\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvosen%2FZLUDA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvosen%2FZLUDA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvosen%2FZLUDA/lists"}