{"id":23752480,"url":"https://github.com/livelace/clmixer","last_synced_at":"2026-03-14T18:30:18.106Z","repository":{"id":140868511,"uuid":"412575769","full_name":"livelace/clmixer","owner":"livelace","description":"clmixer (\"opencl\" + \"mixer\") is a tool for quick parallel computation evaluation (CPU and GPU, APU not tested).","archived":false,"fork":false,"pushed_at":"2024-09-28T20:30:06.000Z","size":923,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-12-31T17:51:59.750Z","etag":null,"topics":["gpgpu","opencl","parallel-computing"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/livelace.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}},"created_at":"2021-10-01T18:21:19.000Z","updated_at":"2024-09-28T20:30:09.000Z","dependencies_parsed_at":"2024-01-22T17:04:13.942Z","dependency_job_id":null,"html_url":"https://github.com/livelace/clmixer","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/livelace%2Fclmixer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/livelace%2Fclmixer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/livelace%2Fclmixer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/livelace%2Fclmixer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/livelace","download_url":"https://codeload.github.com/livelace/clmixer/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239921844,"owners_count":19718844,"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":["gpgpu","opencl","parallel-computing"],"created_at":"2024-12-31T17:52:21.432Z","updated_at":"2026-03-14T18:30:18.075Z","avatar_url":"https://github.com/livelace.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# clmixer\n\n\n***clmixer*** (\"opencl\" + \"mixer\") is a tool for quick parallel computation evaluation ([CPU](https://en.wikipedia.org/wiki/Central_processing_unit) and [GPU](https://en.wikipedia.org/wiki/Graphics_processing_unit), [APU](https://en.wikipedia.org/wiki/AMD_Accelerated_Processing_Unit) not tested).\n\n### Use cases:\n\n1. Fast evaluation of a [kernel](https://en.wikipedia.org/wiki/Compute_kernel) code (runtime compilation). \n2. Multiple kernels parallel execution, configurable number of repeats.\n3. Validate computations (hardware failures).\n\n### Current API support:\n\n1. [OpenCL](https://en.wikipedia.org/wiki/OpenCL).\n\n### Current memory model support:\n\n1. OpenCL buffer.\n\n### Build dependencies:\n\n* C++17 compatible compiler.\n* OpenCL ICD Loader ([first](https://github.com/KhronosGroup/OpenCL-ICD-Loader) or [second](https://github.com/OCL-dev/ocl-icd)).\n* [spdlog](https://github.com/gabime/spdlog) library (v7/8 should be fine).\n* [CLI11](https://github.com/CLIUtils/CLI11) library.\n* [gtest](https://github.com/google/googletest) library.\n\n### AppImage dependencies:\n\n* [FUSE](https://github.com/libfuse/libfuse)\n* [Glibc](https://www.gnu.org/software/libc/) \u003e= 2.29 (Ubuntu 20.04)\n\n### Quick start:\n\n```shell script\n# command line.\nuser@localhost ~ $ cd /tmp\nuser@localhost /tmp $ git clone https://github.com/livelace/clmixer.git\nuser@localhost /tmp $ curl -L https://github.com/livelace/clmixer/releases/download/v1.1.0/clmixer-v1.1.0.appimage -o clmixer.appimage \u0026\u0026 chmod +x clmixer.appimage\nuser@localhost /tmp $ ./clmixer.appimage --opencl-kernel-file clmixer/examples/opencl/buffer_copy_long.c\n[2021-10-02 00:23:42.746] [info] clmixer v1.1.0\n[2021-10-02 00:23:42.911] [info] device: #0 (Intel(R) Core(TM) i7-7700T CPU @ 2.90GHz, 2900MHz, 31.1G, 7.8G)\n[2021-10-02 00:23:42.911] [info] task mode: opencl\n[2021-10-02 00:23:42.911] [info] opencl mode: buffer\n[2021-10-02 00:23:42.911] [info] generate increment data: started\n[2021-10-02 00:23:43.388] [info] generate increment data: finished (long, 134217728, 1G)\n[2021-10-02 00:23:43.388] [info] task [1][1]: creation ...\n[2021-10-02 00:23:43.497] [info] task [1][1]: creation: kernel compiled\n[2021-10-02 00:23:43.762] [info] task [1][1]: creation: input buffer written\n[2021-10-02 00:23:43.762] [info] task [1][1]: creation: finished\n[2021-10-02 00:23:43.763] [info] task [1][1]: execution ...\n[2021-10-02 00:23:44.233] [info] task [1][1]: execution: compute fulfilled\n[2021-10-02 00:23:44.503] [info] task [1][1]: execution: output buffer read\n[2021-10-02 00:23:44.503] [info] task [1][1]: execution: finished\n[2021-10-02 00:23:44.503] [info] task [1]: cleanup\n[2021-10-02 00:23:44.793] [info] data: cleanup\n[2021-10-02 00:23:44.793] [info] result show [1]: [0 ... 134217727]\n[2021-10-02 00:23:44.877] [info] exiting\n\n# docker.\nuser@localhost /tmp $ docker run -ti ghcr.io/livelace/clmixer:v1.1.0 clmixer --show-devices\n[2021-10-01 21:26:01.852] [info] available devices:\n\ncpu:\n  device: #0\n    name:                      Intel(R) Core(TM) i7-7700T CPU @ 2.90GHz\n    platform:                  Intel(R) OpenCL\n    clock speed:               2900MHz\n    memory global size:        31.1G\n    memory max allocate:       7.8G\n    svm coarse-grained buffer: false\n    svm fine-grained buffer:   false\n    svm fine-grained system:   false\n    work group dimension:      3\n    work group size:           8192\n\n```\n\n### ToDo:\n\n1. Add zero-copy/SVM buffer support.\n2. Summary execution statistics.\n3. OpenCL images and pipes.\n4. CUDA support.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flivelace%2Fclmixer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flivelace%2Fclmixer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flivelace%2Fclmixer/lists"}