{"id":17690438,"url":"https://github.com/hughperkins/coriander-dnn","last_synced_at":"2026-03-07T15:34:57.621Z","repository":{"id":136207651,"uuid":"94709602","full_name":"hughperkins/coriander-dnn","owner":"hughperkins","description":"Partial implementation of NVIDIA® cuDNN API for Coriander, OpenCL 1.2","archived":false,"fork":false,"pushed_at":"2025-04-21T12:17:46.000Z","size":260,"stargazers_count":22,"open_issues_count":0,"forks_count":2,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-05-13T02:14:25.452Z","etag":null,"topics":["coriander","dnn-api","gpu","machine-learning","opencl"],"latest_commit_sha":null,"homepage":"","language":"C++","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/hughperkins.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2017-06-18T19:51:50.000Z","updated_at":"2025-04-21T12:17:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"eb93b1b2-f535-4cbf-a2c1-3376de9f4f21","html_url":"https://github.com/hughperkins/coriander-dnn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hughperkins/coriander-dnn","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Fcoriander-dnn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Fcoriander-dnn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Fcoriander-dnn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Fcoriander-dnn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hughperkins","download_url":"https://codeload.github.com/hughperkins/coriander-dnn/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Fcoriander-dnn/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30219550,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-07T14:02:48.375Z","status":"ssl_error","status_checked_at":"2026-03-07T14:02:43.192Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["coriander","dnn-api","gpu","machine-learning","opencl"],"created_at":"2024-10-24T11:50:52.887Z","updated_at":"2026-03-07T15:34:57.602Z","avatar_url":"https://github.com/hughperkins.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# coriander-dnn\n\nCoriander-dnn provides a partial implementation of the NVIDIA® CUDA™ cuDNN API, for Coriander, OpenCL 1.2\n\n## Installation\n\n- first, install [coriander](https://github.com/hughperkins/coriander)\n- then run `cocl_plugins install --repo-url https://github.com/hughperkins/coriander-dnn`\n\n## Testing\n\n### Smoke test\n\nThis is mostly just to check plugins are working ok. Plugins are new :-)\n\nDownload https://github.com/hughperkins/coriander-dnn/raw/master/test/endtoend/basic1.cu to an empty folder somewhere, then,\nfrom that folder, do:\n```\ncocl_py --clang-home /usr/local/opt/llvm-4.0 basic1.cu\n# hopefully compiles ok\n# then run it\n./basic.cu\n# hopefully will print the model of your gpu at least\n```\n\n### Unit tests\n\nThere are unit tests in [test/gtest](test/gtest).  You can build them:\n```\nmake -j 8 tests\n```\nAnd run them:\n```\nmake run-tests\n```\n\n### cudnn test\n\nThis test uses the cudnn code at https://github.com/tbennun/cudnn-training to test that we can run convolutions and so on.  I modified\nit slightly, to add a `USE_OPENCL` option, https://github.com/hughperkins/cudnn-training\n\nTo build `cudnn-training` using Coriander-dnn, you can do the following\n- first install Coriander, and the Coriander-dnn plugin\n- then build cudnn-training:\n```\ngit clone https://github.com/hughperkins/cudnn-training\ncd cudnn-training\nmkdir build\ncd build\nccmake ..\n# press 'c' configure\n# ignore the error about NVIDIA® CUDA™ toolkit not found, we dont need it\n# change `USE_CUDA` to off\n# change `USE_OPENCL` to on\n# press 'c' configure, then 'g' generate\nmake\n```\n- download the mnist data:\n```\nwget http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\nwget http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz\nwget http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz\nwget http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz\ngunzip train-images-idx3-ubyte.gz\ngunzip train-labels-idx1-ubyte.gz\ngunzip t10k-images-idx3-ubyte.gz\ngunzip t10k-labels-idx1-ubyte.gz\n```\n- run:\n```\n./lenet\n```\nYou should see iterations start running.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhughperkins%2Fcoriander-dnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhughperkins%2Fcoriander-dnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhughperkins%2Fcoriander-dnn/lists"}