{"id":13418348,"url":"https://github.com/hughperkins/tf-coriander","last_synced_at":"2025-05-16T10:05:57.595Z","repository":{"id":40380446,"uuid":"70801311","full_name":"hughperkins/tf-coriander","owner":"hughperkins","description":"OpenCL 1.2 implementation for Tensorflow","archived":false,"fork":false,"pushed_at":"2022-10-15T18:30:25.000Z","size":96070,"stargazers_count":792,"open_issues_count":43,"forks_count":91,"subscribers_count":68,"default_branch":"master","last_synced_at":"2025-05-16T10:05:10.161Z","etag":null,"topics":["gpu","intel","mac","nvidia","opencl","radeon","tensorflow","ubuntu"],"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}},"created_at":"2016-10-13T11:50:41.000Z","updated_at":"2025-05-03T09:53:38.000Z","dependencies_parsed_at":"2023-01-19T21:15:32.962Z","dependency_job_id":null,"html_url":"https://github.com/hughperkins/tf-coriander","commit_stats":null,"previous_names":[],"tags_count":23,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Ftf-coriander","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Ftf-coriander/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Ftf-coriander/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hughperkins%2Ftf-coriander/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hughperkins","download_url":"https://codeload.github.com/hughperkins/tf-coriander/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254509476,"owners_count":22082891,"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":["gpu","intel","mac","nvidia","opencl","radeon","tensorflow","ubuntu"],"created_at":"2024-07-30T22:01:01.264Z","updated_at":"2025-05-16T10:05:57.556Z","avatar_url":"https://github.com/hughperkins.png","language":"C++","funding_links":[],"categories":["TODO scan for Android support in followings","C++"],"sub_categories":[],"readme":"# Tensorflow-cl\n\nRun [Tensorflow](https://github.com/tensorflow/tensorflow) on OpenCL™ 1.2 devices\n\n- tested on:\n  - Mac Sierra using Radeon Pro 450 GPU (thank you [ASAPP](http://asapp.com) :-) )\n  - Ubuntu 16.04, using NVIDIA K520\n- should work theoretically on any OpenCL 1.2 GPU\n\n## Piccie\n\nOn a Mac:\n\n\u003cimg src=\"doc/img/multilayerperceptron.png\" /\u003e\n\n## Execution speed\n\n- [Execution speed](doc/execution_speed.md)\n\n## What's working\n\n- [What's working](doc/whats_working.md)\n\n## Installation\n\n- [Installation](doc/installation.md)\n\n## Tests\n\n- [Tests](doc/testing.md)\n\n## Design/architecture\n\n- tensorflow code stays 100% [NVIDIA® CUDA™](https://www.nvidia.com/object/cuda_home_new.html)\n- [Coriander](https://github.com/hughperkins/Coriander) compiles the NVIDIA® CUDA™ code into OpenCL\n- Cedric Nugteren's [CLBlast](https://github.com/CNugteren/CLBlast) provides BLAS (matrix multiplications)\n\nPresentation on [Coriander](https://github.com/hughperkins/Coriander) at this year's [IWOCL 2017](http://www.iwocl.org/iwocl-2017/conference-program/)\n\n## Related projects\n\n- [OpenCL Torch](https://github.com/hughperkins/distro-cl)\n- [DeepCL](https://github.com/hughperkins/DeepCL)\n\n## News\n\n- June 11 2017:\n  - set up Jenkins build, which makes build logs and a Ubuntu 16.04 wheel available for certain commits, https://github.com/hughperkins/tf-coriander/commits/example-jenkins-builds (click on one of the green ticks)\n- June 7 2017:\n  - created [v0.18.3](https://github.com/hughperkins/tf-coriander/releases/tag/v0.18.3) release:\n    - `tf.split` enabled\n    - following examples from Aymeric Damien's [Tensorflow-Examples](https://github.com/aymericdamien/TensorFlow-Examples) run now:\n      - [recurrent_network.py](https://github.com/hughperkins/TensorFlow-Examples/blob/enforce-gpu/examples/3_NeuralNetworks/recurrent_network.py)\n      - [bidirectional_rnn.py](https://github.com/hughperkins/TensorFlow-Examples/blob/enforce-gpu/examples/3_NeuralNetworks/bidirectional_rnn.py)\n      - [dynamic_rnn.py](https://github.com/hughperkins/TensorFlow-Examples/blob/enforce-gpu/examples/3_NeuralNetworks/dynamic_rnn.py)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhughperkins%2Ftf-coriander","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhughperkins%2Ftf-coriander","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhughperkins%2Ftf-coriander/lists"}