{"id":23534992,"url":"https://github.com/kis-balazs/cuda-research","last_synced_at":"2025-05-14T20:35:06.870Z","repository":{"id":269280786,"uuid":"889520616","full_name":"kis-balazs/CUDA-Research","owner":"kis-balazs","description":"CUDA Research \u0026 Code. Course-style structured. Inspiration from @Infatoshi.","archived":false,"fork":false,"pushed_at":"2025-01-28T19:18:43.000Z","size":11108,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-17T06:13:07.861Z","etag":null,"topics":["cuda"],"latest_commit_sha":null,"homepage":"","language":"Cuda","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/kis-balazs.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}},"created_at":"2024-11-16T14:40:33.000Z","updated_at":"2025-01-28T19:18:47.000Z","dependencies_parsed_at":"2025-01-28T14:33:50.406Z","dependency_job_id":null,"html_url":"https://github.com/kis-balazs/CUDA-Research","commit_stats":null,"previous_names":["kis-balazs/cuda-research"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kis-balazs%2FCUDA-Research","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kis-balazs%2FCUDA-Research/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kis-balazs%2FCUDA-Research/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kis-balazs%2FCUDA-Research/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kis-balazs","download_url":"https://codeload.github.com/kis-balazs/CUDA-Research/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239242112,"owners_count":19605954,"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"],"created_at":"2024-12-26T01:14:07.921Z","updated_at":"2025-05-14T20:35:06.864Z","avatar_url":"https://github.com/kis-balazs.png","language":"Cuda","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CUDA-Research\nResearch \u0026amp; Code for CUDA components developed/experimented by me.\n\n## Resources Outline\n- [cuda-course](https://github.com/Infatoshi/cuda-course)\n- [cuda-mnist](https://github.com/Infatoshi/cuda-course)\n- [cuda-opencv-examples](https://github.com/evlasblom/cuda-opencv-examples/tree/master)\n- [Getting Started with Accelerated Computing in CUDA C/C++ -- NVIDIA DLI Course](https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-AC-04+V1)\n- [Holistic Trace Analysis](https://github.com/facebookresearch/HolisticTraceAnalysis/tree/main) - this seems like a very-very good resource for understanding PyTorch GPU traces, for end-to-end ML model evaluation\n  - [Open Torch Perf Traces](https://reimbar.org/dev/torch-profile-trace/)\n\n## Environment\n- [CUDA Installation Guide Ubuntu](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/#ubuntu)\n- [CUDNN Installation - Latest](https://docs.nvidia.com/deeplearning/cudnn/installation/latest/index.html)\n\n## Related\n- [[repo] kis-balazs/CUDA-Containers-Infrastructure-Repository](https://github.com/kis-balazs/cuda-containers-infra)\n- [relevant(+adjacent) CUDADocs.md](99_Docs/CUDADocs.md)\n- [[PDF] Multi-GPU Programming @ Supercomputing 2011](https://www.nvidia.com/docs/IO/116711/sc11-multi-gpu.pdf)\n\n## Particularly Handy Gists\n- [kis-balazs/macro__check_cuda_return.cu](https://gist.github.com/kis-balazs/03f8023320639632db46523aa6e2bc69)\n  - Macro to check CUDA Error from Function Returning exit code\n- [kis-balazs/verif_last_cuda_error.cu](https://gist.github.com/kis-balazs/3a2590d4bf90f33b0f8776d94da25a92)\n  - Verify last CUDA Error code, mainly from kernels, to use for straight-forward debugging\n\n---\n## Important Notice - GPU-specific nvcc params\n\nWhen running `nvcc` commands, the `-arch` command is not always synced to the correct physical GPU. This can be fixed by specifying this.\n\nSteps:\n- find compute version: find the GPU compute version [here](https://developer.nvidia.com/cuda-gpus)\n- specify when compiling: `nvcc -o exec code.cu -arch=compute_XX`\n- optionally, `code` can be specified as well: `-code=sm_XX,compute_XX`\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkis-balazs%2Fcuda-research","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkis-balazs%2Fcuda-research","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkis-balazs%2Fcuda-research/lists"}