{"id":13477511,"url":"https://github.com/maestro-project/maestro","last_synced_at":"2025-03-27T05:31:58.966Z","repository":{"id":37623611,"uuid":"189778669","full_name":"maestro-project/maestro","owner":"maestro-project","description":"An analytical cost model evaluating DNN mappings (dataflows and tiling).","archived":false,"fork":false,"pushed_at":"2024-04-15T11:49:39.000Z","size":761,"stargazers_count":181,"open_issues_count":18,"forks_count":58,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-10-30T10:40:50.542Z","etag":null,"topics":["dataflow","deep-learning","deep-neural-networks"],"latest_commit_sha":null,"homepage":"http://maestro.ece.gatech.edu","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/maestro-project.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":"2019-06-01T21:23:04.000Z","updated_at":"2024-10-24T03:24:18.000Z","dependencies_parsed_at":"2023-01-21T11:46:51.563Z","dependency_job_id":"6d1065f9-e1cf-4bec-8084-f7d699b96ac8","html_url":"https://github.com/maestro-project/maestro","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/maestro-project%2Fmaestro","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maestro-project%2Fmaestro/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maestro-project%2Fmaestro/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maestro-project%2Fmaestro/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maestro-project","download_url":"https://codeload.github.com/maestro-project/maestro/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245791691,"owners_count":20672666,"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":["dataflow","deep-learning","deep-neural-networks"],"created_at":"2024-07-31T16:01:43.850Z","updated_at":"2025-03-27T05:31:58.557Z","avatar_url":"https://github.com/maestro-project.png","language":"MATLAB","funding_links":[],"categories":["MATLAB","Tools","Verification Frameworks"],"sub_categories":["FPGA based accelerator / HLS for CNNs"],"readme":"# MAESTRO: An Open-source Infrastructure for Modeling Dataflows within Deep Learning Accelerators\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)\n\n# What is MAESTRO?\nMAESTRO is an open-source tool for modeling and evaluating the performance and energy-efficiency of different dataflows. MAESTRO is actively developed by the [Synergy Lab](https://synergy.ece.gatech.edu/) at [Georgia Institute of Technology](https://www.gatech.edu/). For more details about MAESTRO, please visit the following links.\n\n- [MAESTRO Website](http://maestro.ece.gatech.edu/)\n- [MAESTRO Docs](http://maestro.ece.gatech.edu/docs/build/html/index.html)\n\n\n# Codebase\n\n## Updates\n### May 26th, 2021\n\nWe updated the hardware description file, added off-chip bandwidth added as constraint.\n\nWe added a validation folder with data for Eyeriss and MAERI from MICRO 2019 paper.\n\n### Oct 13th, 2020\n\nWe added a direct support for GEMM layers. For more information, please take a look at [here](http://maestro.ece.gatech.edu/docs/build/html/layer_supported.html).\n\n### May 13th, 2020\n\nWe updated the naming convention of mappings and the directory structure of data folder.\n\n### Oct 14th, 2019\n\nLatest codebase released along with MAESTRO MICRO 2019 paper.\n\n\n## Maintainers\n- Felix (Sheng-Chun) Kao (felix@gatech.edu)\n- Geonhwa Jeong (geonhwa.jeong@gatech.edu)\n- Tushar Krishna (tushar@ece.gatech.edu)\n\n\n## Technical Contributors\n- Hyoukjun Kwon (Georgia Tech, now at Facebook Reality Labs): Main developer (core framework and functionalities)\n- Prasanth Chatarasi (Georgia Tech, now at IBM Research): APIs + interface to mapping optimizers.\n- Felix (Sheng-Chun) Kao (Georgia Tech): Pytorch frontend + updates to cost-model/interface + GAMMA mapper\n- Geonhwa Jeong (Georgia Tech): Keras frontend + debugging + website maintainer.\n- Saurabh Malik (Georgia Tech, now at Microsoft): Jupyter Notebooks demo + website.\n\n# Citations ###\n```\n@inproceedings{maestro_micro2019,\n  author    = {Hyoukjun Kwon and\n               Prasanth Chatarasi and\n               Michael Pellauer and\n               Angshuman Parashar and\n               Vivek Sarkar and\n               Tushar Krishna},\n  title     = {Understanding Reuse, Performance, and Hardware Cost of {DNN} Dataflow:\n               {A} Data-Centric Approach},\n  booktitle = {Proceedings of the 52nd Annual {IEEE/ACM} International Symposium\n               on Microarchitecture, {MICRO}},\n  pages     = {754--768},\n  publisher = {{ACM}},\n  year      = {2019},\n}\n\n```\n```\n@article{maestro_toppicks2020,\n  author    = {Hyoukjun Kwon and\n               Prasanth Chatarasi and\n               Vivek Sarkar and\n               Tushar Krishna and\n               Michael Pellauer and\n               Angshuman Parashar},\n  title     = {{MAESTRO:} {A} Data-Centric Approach to Understand Reuse, Performance,\n               and Hardware Cost of {DNN} Mappings},\n  journal   = {{IEEE} Micro},\n  volume    = {40},\n  number    = {3},\n  pages     = {20--29},\n  year      = {2020},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaestro-project%2Fmaestro","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaestro-project%2Fmaestro","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaestro-project%2Fmaestro/lists"}