{"id":18057091,"url":"https://github.com/denyskryvytskyi/capgemini-cuda","last_synced_at":"2026-05-14T23:41:49.783Z","repository":{"id":259001094,"uuid":"866038513","full_name":"denyskryvytskyi/capgemini-cuda","owner":"denyskryvytskyi","description":"CUDA implementation of vector additon, matrix multiplication, reduction and sorting","archived":false,"fork":false,"pushed_at":"2024-10-28T14:04:28.000Z","size":39,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-05T10:24:04.328Z","etag":null,"topics":["bitonic-sort","cpp","cuda","cuda-kernels","gpgpu","matrix","matrix-multiplication","matrix-multiplication-parallel","matrix-transpose","nvidia","nvidia-cuda","nvidia-gpu","reduction-dimension","sort","sorting-algorithms-implemented","vector","vector-addition","vectorization"],"latest_commit_sha":null,"homepage":"","language":"Cuda","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/denyskryvytskyi.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-10-01T14:42:01.000Z","updated_at":"2024-12-25T10:10:53.000Z","dependencies_parsed_at":"2024-10-21T16:33:19.410Z","dependency_job_id":null,"html_url":"https://github.com/denyskryvytskyi/capgemini-cuda","commit_stats":null,"previous_names":["denyskryvytskyi/capgemini-cuda"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/denyskryvytskyi/capgemini-cuda","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/denyskryvytskyi%2Fcapgemini-cuda","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/denyskryvytskyi%2Fcapgemini-cuda/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/denyskryvytskyi%2Fcapgemini-cuda/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/denyskryvytskyi%2Fcapgemini-cuda/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/denyskryvytskyi","download_url":"https://codeload.github.com/denyskryvytskyi/capgemini-cuda/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/denyskryvytskyi%2Fcapgemini-cuda/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267569505,"owners_count":24109091,"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","status":"online","status_checked_at":"2025-07-28T02:00:09.689Z","response_time":68,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["bitonic-sort","cpp","cuda","cuda-kernels","gpgpu","matrix","matrix-multiplication","matrix-multiplication-parallel","matrix-transpose","nvidia","nvidia-cuda","nvidia-gpu","reduction-dimension","sort","sorting-algorithms-implemented","vector","vector-addition","vectorization"],"created_at":"2024-10-31T02:06:32.479Z","updated_at":"2026-05-14T23:41:44.754Z","avatar_url":"https://github.com/denyskryvytskyi.png","language":"Cuda","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Capgemini CUDA tasks\nTasks were implemented and tested in Windows 10 with the Visual Studio CUDA Integration tool and NVCC compiler.\n\nTasks list:\n- vectors addition;\n- matrix multiplication using tiles, GPU shared memory, and matrix transposition;\n- reduction (sum) with a custom kernel and Nvidia Thrust library for performance comparison;\n- sorting using the Nvidia Thrust library.\n\n## Getting Started\n- Install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit).\n- [Windows] Install Visual Studio 2022 (we need MSVC compiler to compile host code and link with device code for the final executable).\n- [Linux] Install gcc compiler.\n\nCompile code using **nvcc** compiler:\n\n`nvcc \u003cprogram_name\u003e.cu -o \u003cprogram_name\u003e -O3`\n\nRun:\n`./\u003cprogram_name\u003e`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdenyskryvytskyi%2Fcapgemini-cuda","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdenyskryvytskyi%2Fcapgemini-cuda","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdenyskryvytskyi%2Fcapgemini-cuda/lists"}