{"id":28719144,"url":"https://github.com/jiaau/kernels","last_synced_at":"2026-04-21T16:40:28.230Z","repository":{"id":295384569,"uuid":"988496664","full_name":"jiaau/kernels","owner":"jiaau","description":"This repository showcases common optimization techniques for kernels.","archived":false,"fork":false,"pushed_at":"2025-06-09T12:53:37.000Z","size":53,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-15T06:01:51.430Z","etag":null,"topics":["cpp","cuda","cute","cutlass","hpc","kernel"],"latest_commit_sha":null,"homepage":"","language":"Cuda","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jiaau.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":"2025-05-22T16:22:56.000Z","updated_at":"2025-06-09T12:53:40.000Z","dependencies_parsed_at":"2025-06-15T06:00:24.286Z","dependency_job_id":"8cfae239-8b47-4115-93ff-516f5542b14e","html_url":"https://github.com/jiaau/kernels","commit_stats":null,"previous_names":["jiaau/kernels"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jiaau/kernels","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiaau%2Fkernels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiaau%2Fkernels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiaau%2Fkernels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiaau%2Fkernels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jiaau","download_url":"https://codeload.github.com/jiaau/kernels/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiaau%2Fkernels/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32101011,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-21T11:25:29.218Z","status":"ssl_error","status_checked_at":"2026-04-21T11:25:28.499Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["cpp","cuda","cute","cutlass","hpc","kernel"],"created_at":"2025-06-15T06:00:17.087Z","updated_at":"2026-04-21T16:40:28.210Z","avatar_url":"https://github.com/jiaau.png","language":"Cuda","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kernels\n\n## 关注点\n\n- [reduce](./src/reduce)\n    - CUDA Warp-Level Primitives\n    - Parallel reduction\n\n- [transpose](./src/transpose)\n    - Memory Coalescing\n    - Shared Memory\n    - Bank Conflict\n    - Swizzling\n    - CuTe\n\n- [sgemm](./src/sgemm)\n    - Tile Size Tuning\n    - Shared Memory\n    - Bank Conflict\n    - Double Buffer\n    - Warp Divergence\n    - Vectorized memory access\n\n## 编译与运行\n\n### 编译项目\n\n```bash\nmake build\nmake install \u003ckernel_name\u003e\n```\n\n### 运行测试\n\n```bash\nmake run \u003ckernel_name\u003e\n```\n\n### 使用NVIDIA Compute Profiler进行性能分析\n\n```bash\nmake ncu \u003ckernel_name\u003e\n```\n\n### 清理构建文件\n\n```bash\nmake clean\n```\n\n## 命令行选项\n\n运行SGEMM测试时支持以下选项：\n\n- `--bench`: 启用基准测试模式\n- `--times N`: 指定基准测试迭代次数（默认：3）\n- `--help`: 显示帮助信息\n\n例如：\n\n```bash\nmake run \u003ckernel_name\u003e -- --bench --times 10\n```\n\n## Acknowledgments\n\n- 本项目使用了 [Chtholly-Boss/swizzle](https://github.com/Chtholly-Boss/swizzle) 的一些工具函数","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiaau%2Fkernels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjiaau%2Fkernels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiaau%2Fkernels/lists"}