{"id":13578652,"url":"https://github.com/zeux/microprofile","last_synced_at":"2025-04-05T19:33:24.737Z","repository":{"id":30748301,"uuid":"34304771","full_name":"zeux/microprofile","owner":"zeux","description":"microprofile - embeddable CPU/GPU profiler","archived":true,"fork":false,"pushed_at":"2023-05-21T16:01:46.000Z","size":31784,"stargazers_count":492,"open_issues_count":5,"forks_count":46,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-11-05T16:47:27.729Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers","license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zeux.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":"2015-04-21T04:46:23.000Z","updated_at":"2024-11-04T04:35:27.000Z","dependencies_parsed_at":"2024-08-01T15:29:44.141Z","dependency_job_id":"fcdf028f-c79c-48f4-814d-34e11bcfa5e2","html_url":"https://github.com/zeux/microprofile","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/zeux%2Fmicroprofile","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeux%2Fmicroprofile/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeux%2Fmicroprofile/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zeux%2Fmicroprofile/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zeux","download_url":"https://codeload.github.com/zeux/microprofile/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247393095,"owners_count":20931804,"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":"2024-08-01T15:01:32.591Z","updated_at":"2025-04-05T19:33:23.364Z","avatar_url":"https://github.com/zeux.png","language":"C++","readme":"# microprofile [![Build Status](https://travis-ci.org/zeux/microprofile.svg?branch=master)](https://travis-ci.org/zeux/microprofile)\nThis is a fork of [microprofile by Jonas Meyer](https://github.com/jonasmr/microprofile). This library has diverged from upstream.\n\n## Using the upstream version is recommended as this fork will no longer be maintained.\n\nmicroprofile is an embeddable CPU/GPU profiler with an in-app and HTML visualizers.\n\n![Screenshot](https://pbs.twimg.com/media/BnvzublCEAA0Mqf.png:large)\n\n## Features\n\n* Hierarchical regions for timing sections of the code\n* Labels for adding extra information in the form of strings to regions\n* GPU regions (D3D11/D3D12/GL/VK) with GPU timestamp synchronization\n* Counters for measuring various global values that change over time\n* Graphing any region or counter in real-time to observe differences over time\n* Visualization using in-game UI, a web browser (buit-in server) or an HTML file\n* Low overhead\n\n## Platform support\n\nmicroprofile is known to work on Windows XP and above, Linux, OSX, iOS, Android and Xbox One.\n\nIt should be easy to adapt to support any other platforms; pull requests are welcome!\n\n## Difference from upstream\n\nThis library has been forked from upstream in 2015 - back when upstream was using Bitbucket/Mercurial - and has diverged over time from upstream; the difference in priorities for features led to the divergence not really converging, so treat this as a permanent fork.\n\nThe list of features that have not been backported from upstream (as of October 2018):\n\n* WebSocket-based live connection that displays graphs and allows to start the frame capture\n* Timelines that can be useful for profiling long running code such as level loading\n* Support for more than 48 categories\n\nThe list of features that this fork has but upstream doesn't (as of October 2018):\n\n* On-screen UI support that can use OpenGL or any other rendering backend for rendering (upstream removed this in 2017)\n* On-screen UI support for \"Frame\" display mode that only shows the frame bar, to allow for easier detection of spikes without obstructing gameplay\n* Unified nomenclature between on-screen UI and web UI - the same information is consistently displayed in both, with the same names\n* Support for dynamic strings (labels) that are displayed inside of scopes and can use printf-style format strings\n* Automatic color selection based on scope name hash (you can use -1 instead of color value everywhere)\n* Unified CPU/GPU scopes - MicroProfileEnter/MicroProfileLeave/etc. automatically determine whether the group is CPU or GPU\n* Reworked dtrace based context switch visualization on OSX (higher performance, better time synchronization)\n* Completely reworked GPU timing implementation, with support for GL on OSX as well as Vulkan, D3D12, D3D11 on other platforms (upstream now also supports Vulkan via a separate implementation)\n* GPU backends can be chosen dynamically - you can compile support for D3D11, D3D12, OpenGL and Vulkan in (or any selection thereof) and dynamically initialize just one at some point later.\n* Substantially improved web server performance (web server runs in a dedicated thread, creating the HTML dump is several times faster)\n* A lot of robustness fixes for edge cases, overflow conditions, GPU timing issues etc. - this fork should be safe to enable in production builds.\n* Reduce profiler memory overhead when no groups are captured by lazily allocating most large buffers\n* iOS and Android support\n\nThis library ships in Roblox client and editor for all platforms, compiled in (with profiler not capturing data by default but working in on-screen or web-server mode depending on the platform) for all users.\n","funding_links":[],"categories":["C++","\u003ca name=\"cpp\"\u003e\u003c/a\u003eC++"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzeux%2Fmicroprofile","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzeux%2Fmicroprofile","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzeux%2Fmicroprofile/lists"}