{"id":23951422,"url":"https://github.com/psteinb/gpu-lecture-task-parallelism","last_synced_at":"2025-02-24T09:20:35.899Z","repository":{"id":55400267,"uuid":"76549332","full_name":"psteinb/gpu-lecture-task-parallelism","owner":"psteinb","description":"Lecture given at TU Dresden on task parallelism with (Nvidia) GPUs","archived":false,"fork":false,"pushed_at":"2021-01-03T14:25:16.000Z","size":108,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-06T12:59:45.344Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/psteinb.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":"2016-12-15T10:19:19.000Z","updated_at":"2021-01-04T11:54:18.000Z","dependencies_parsed_at":"2022-08-14T23:30:30.507Z","dependency_job_id":null,"html_url":"https://github.com/psteinb/gpu-lecture-task-parallelism","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/psteinb%2Fgpu-lecture-task-parallelism","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psteinb%2Fgpu-lecture-task-parallelism/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psteinb%2Fgpu-lecture-task-parallelism/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/psteinb%2Fgpu-lecture-task-parallelism/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/psteinb","download_url":"https://codeload.github.com/psteinb/gpu-lecture-task-parallelism/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240449893,"owners_count":19803125,"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":[],"created_at":"2025-01-06T12:59:46.107Z","updated_at":"2025-02-24T09:20:35.828Z","avatar_url":"https://github.com/psteinb.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# gpu-lecture-task-parallelism\n\nLecture given at TU Dresden on task parallelism with GPUs (CUDA, OpenACC).\n\n## Working on Taurus (if needed)\n\nFirst, establish an interactive bash session on a gpu host (attention: the reservation flag will only work during class hours, omit them anytime else):\n    \n  + for Dec 16, 2019\n  ```\n  $ srun --reservation p_lv_gpu1920_323 -A p_lv_gpu1920 -t 1:30:00 --mem=4000 --gres=gpu:1 --partition=gpu1-interactive --pty bash -l\n  ``` \n  \n  + for Dec 17, 2019\n  ```\n  $ srun --reservation p_lv_gpu1920_324 -A p_lv_gpu1920 -t 1:30:00 --mem=4000 --gres=gpu:1 --partition=gpu1-interactive --pty bash -l\n  ```\n\nSecond, please setup the correct environment (the defaul CUDA on taurus is version `10.1.243`):\n\n```\n$ module add modenv/scs5\n\nModule GCCcore/6.4.0, zlib/1.2.11-GCCcore-6.4.0, cURL/7.58.0-GCCcore-6.4.0, expat/2.2.5-GCCcore-6.4.0, XZ/5.2.3-GCCcore-6.4.0, libxml2/2.9.4-GCCcore-6.4.0, ncurses/6.0-GCCcore-6.4.0, gettext/0.19.8.1-GCCcore-6.4.0, Perl/5.26.1-GCCcore-6.4.0, git/2.18.0-GCCcore-6.4.0 unloaded.\nModule GCCcore/6.4.0, zlib/1.2.11-GCCcore-6.4.0, cURL/7.58.0-GCCcore-6.4.0, expat/2.2.5-GCCcore-6.4.0, XZ/5.2.3-GCCcore-6.4.0, libxml2/2.9.4-GCCcore-6.4.0, ncurses/6.0-GCCcore-6.4.0, gettext/0.19.8.1-GCCcore-6.4.0, Perl/5.26.1-GCCcore-6.4.0, git/2.18.0-GCCcore-6.4.0 loaded.\n$ module load CUDA\nModule CUDA/10.1.243 loaded.\n```\n\n## Working with the code\n\nNote that the examples use C++11. please make sure that the installed host side compiler supports this standard. If your host uses gcc as the default c/c++ compiler, any version between 4.9 and 7 should be fine with CUDA 10, see [here](https://gist.github.com/ax3l/9489132) for compatibility matrix.\n\nTo prepare for class, change your working directory to where your code lives and checkout this repo :\n\n```\n$ cd /path/to/where/I/want/to/work\n$ git clone https://github.com/psteinb/gpu-lecture-task-parallelism.git\n$ cd gpu-lecture-task-parallelism\n```\n\nLet's start with the acceptance test:\n\n```\n$ cd 0_getting_started/\n$ make\n$ ./test_simple_increment\n```\n\nIf this test passes, you are ready to go, if not, diagnose the problem. Feel free to post an issue to this repo if you are unable to solve the problem.\n\n\n   \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpsteinb%2Fgpu-lecture-task-parallelism","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpsteinb%2Fgpu-lecture-task-parallelism","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpsteinb%2Fgpu-lecture-task-parallelism/lists"}