{"id":16863675,"url":"https://github.com/harrism/cuda_event_benchmark","last_synced_at":"2025-03-22T06:32:11.291Z","repository":{"id":51074039,"uuid":"273373315","full_name":"harrism/cuda_event_benchmark","owner":"harrism","description":"Unit benchmarks of CUDA event APIs.","archived":false,"fork":false,"pushed_at":"2024-04-23T04:47:11.000Z","size":24,"stargazers_count":17,"open_issues_count":1,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-01T13:42:06.535Z","etag":null,"topics":["benchmarks","cuda"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/harrism.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":"2020-06-19T01:07:31.000Z","updated_at":"2024-06-27T09:06:33.000Z","dependencies_parsed_at":"2024-03-11T09:31:20.063Z","dependency_job_id":"b73859a5-b740-427d-9c53-4a2b96f34a33","html_url":"https://github.com/harrism/cuda_event_benchmark","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrism%2Fcuda_event_benchmark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrism%2Fcuda_event_benchmark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrism%2Fcuda_event_benchmark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harrism%2Fcuda_event_benchmark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harrism","download_url":"https://codeload.github.com/harrism/cuda_event_benchmark/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244189791,"owners_count":20412991,"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":["benchmarks","cuda"],"created_at":"2024-10-13T14:39:18.461Z","updated_at":"2025-03-22T06:32:06.283Z","avatar_url":"https://github.com/harrism.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CUDA Event Benchmarks\n\nSimple benchmarks of `cudaEvent_t` APIs:\n\n - `cudaEventCreate`\n - `cudaEventRecord`\n - `cudaEventQuery`\n - `cudaStreamWaitEvent`\n - `cudaEventDestroy`\n - A simulated event pool that maintains a list of free events (more of a benchmark of `std::list`\n   push/pop for cost comparison to `cudaEventCreate`).\n\nEach test is performed once using default-created events (support timing) and once with events that\ndo not support timing.\n\nHere are the results from running with a single GPU (`CUDA_VISIBLE_DEVICES` is set to only that GPU)\nof an NVIDIA DGX1 (with Tesla V100 GPUs with 32GB each).\n - OS: `Ubuntu 18.04`.\n - CUDA: `10.2`.\n - NVIDIA Driver: `440.64.00`.\n\n```\n(cudf_dev_10.2) mharris@dgx02:~/github/cuda_event_benchmark/build$ CUDA_VISIBLE_DEVICES=3 ./cuda_event_bench\n2020-06-18T18:57:26-07:00\nRunning ./cuda_event_bench\nRun on (80 X 3600 MHz CPU s)\nCPU Caches:\n  L1 Data 32 KiB (x40)\n  L1 Instruction 32 KiB (x40)\n  L2 Unified 256 KiB (x40)\n  L3 Unified 51200 KiB (x2)\nLoad Average: 1.85, 1.80, 1.17\n------------------------------------------------------------------------------------\nBenchmark                          Time             CPU   Iterations UserCounters...\n------------------------------------------------------------------------------------\nBM_EventCreate\u003ctrue\u003e             782 us          782 us          923 items_per_second=1.27941M/s\nBM_EventCreate\u003cfalse\u003e            422 us          422 us         1558 items_per_second=2.36813M/s\nBM_EventPool\u003ctrue\u003e              14.6 us         14.6 us        48904 items_per_second=68.6765M/s\nBM_EventPool\u003cfalse\u003e             13.0 us         13.0 us        53373 items_per_second=76.659M/s\nBM_EventRecord\u003ctrue\u003e            2499 us         2499 us          278 items_per_second=400.15k/s\nBM_EventRecord\u003cfalse\u003e            244 us          244 us         2762 items_per_second=4.09725M/s\nBM_EventQuery\u003ctrue\u003e             1046 us         1046 us          707 items_per_second=956.295k/s\nBM_EventQuery\u003cfalse\u003e            1016 us         1016 us          665 items_per_second=984.674k/s\nBM_StreamWaitEvent\u003ctrue\u003e         258 us          258 us         2706 items_per_second=3.88102M/s\nBM_StreamWaitEvent\u003cfalse\u003e        254 us          254 us         2752 items_per_second=3.93252M/s\nBM_EventDestroy\u003ctrue\u003e            121 us          121 us         5894 items_per_second=8.28793M/s\nBM_EventDestroy\u003cfalse\u003e           119 us          119 us         5959 items_per_second=8.4334M/s\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharrism%2Fcuda_event_benchmark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharrism%2Fcuda_event_benchmark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharrism%2Fcuda_event_benchmark/lists"}