跳到主要內容

黃金級贊助商 - Skymizer 帶來 ONNC 通用的開放神經網路編譯器

「AI 創新需要開源生態系,而 ONNX 確保了 frameworks 之間的互通性,ONNC 的目標是將所有的 DLA ASIC 快速、簡單地與 ONNX 連結起來,確保所有的 DLA ASIC 都可以在 ONNX 上執行。」

由於 AI 的應用層面越來越廣,數百種新 AI 晶片將在不久的未來大量出現,目前市場上卻沒有一個能完整支援各家 DLA 的開源編譯器。根據統計,在 2018 年會有超過 34 家 IC 與 IP 廠商提供各式各樣的 AI 晶片與 deep learning accelerator (DLA) ASICs,因此急需一個開源的編譯器來支援各種不同的 AI 晶片。

成立於 2013 年的 Skymizer 一直都專注在 compiler 和 machine learning 領域,看到這個趨勢之後,建立了基於 ONNX 的編譯器 Open Nerual Network Compiler – ONNC,將所有的 AI 晶片與 ONNX 連結起來。

ONNX 是開放類神經網路交換格式,目前常見的 AI framework 如Caffe2、PyTorch…等等各有各的支持者,格式間互通性差,因此訓練出來的深度學習模型無法套用到別的 framework 上,但有了 ONNX,開發者可在不同格式之間輕鬆轉換。而透過 ONNX 支援多平台的特性,ONNC 可以支援各種不同的 AI frameworks,如 Caffe、Caffe2 與 PyTorch,幫助 DLA ASIC 廠商在短時間內就可以支援各種 AI frameworks,提升性能並縮短開發時間。  






想要更了解 ONNC,歡迎到 https://onnc.ai 追蹤最新的動態,
目前 ONNC 已在 GitHub https://repo.onnc.ai 釋出,而所有開發的相關討論,
將會在 mailing list 進行。


ONNC features:
Easy Backend Integration
ONNC is integrated with the LLVM bitcode runtime and compiler. If a DLA already supports the LLVM compiler, it can be connected to ONNC seamlessly. This helps most CPUs, GPUs, and DSPs ported to ONNC in a very short time. On the other hand, if a DLA has unique computation features and is not compatible to LLVM, ONNC also provides a modular framework to speed up the compiler development. DLA vendors can quickly customize an ONNC backend from a so called “vanilla” backend, which already provides some necessary optimization algorithms.


Reusable Compiler Optimizations
Two of ONNC’s contributions are dividing the AI compilation into several clear phases and giving the corresponding APIs for algorithm development.
There are five phases carefully defined, each of which is focused on a particular compiler problem: IR building, partitioning, scheduling, allocation, and code emitting.
ONNC also provides a series of optimization algorithms ready for use. They are general and reusable, including tensor selection, tensor liveness analysis, linear scan local memory allocation, etc. ONNC’s pass manager is flexible and similar to LLVM’s. AI researchers and engineers who are familiar with LLVM can intuitively contribute their general or target-specific optimization algorithms to ONNC.


Status and Future Work
Project ONNC is not mature yet.
Still, we have a lot to do and need the community together to make it better. In this preview release, we carefully designed the software architecture so as to simplify the future development and
maintenance.
The items we have done include:



  • Clear compilation phases and the corresponding APIs.
  • Well-defined and extensible intermediate representation (IR) of target-specific instructions.
  • A pass manager that supports automatic scheduling according to the dependency claimed by each pass.
  • A Sophon backend that supports BITMAIN AI ASIC.
  • Shim library such as ADT, Diagnostics, JSON, etc.

Project ONNC follows the “release early, release often” principle,
so the next release should come soon by the end of August.
We plan to finish the following items.

  • An x86 backend that enables the execution of AI models on an x86 machine. That backend should support both JIT and interpreter way of execution.
  • Improvements of memory allocation based on liveness analysis.

JOIN US
To keep up with the latest development or make suggestions, please join the ONNC mailing list. Also, please head over to the official website https://onnc.ai/ and GitHub https://repo.onnc.ai for more information.








留言

這個網誌中的熱門文章

COSCUP 2024 Call for Participation 議程軌與攤位即日起開放申請

COSCUP 2024 Call for Participation, 議程軌與攤位即日起開放申請 COSCUP 2024 的社群議程/攤位即日起開始接受申請,社群議程於 3 月 17 日截止申請,社群攤位於 6 月 3 號截止。請有興趣在今年與我們共襄盛舉的社群把握機會! 點此快速報名 / Quick Apply 點此跳到社群攤位 Jump to Community Track English Ver. Jump to Community Booth English Ver. 社群議程 Community Room COSCUP 2024 社群議程提供場地與行政協助,您可以在此舉辦一整天關於特定開源議題的討論、座談、工作坊等。 特色包括: 自訂議程時長:各社群可以自己決定每段議程的時間,無論 15 分鐘、30 分鐘、45 分鐘,甚至直接開設數個小時的工作坊都可以。 自訂休息時間:各社群可以決定是否有休息時間,或是連番上陣。 What's new in COSCUP 2024 今年 COSCUP 有一些新的合作注意事項,歡迎欲報名的社群夥伴們確認,報名即視為貴社群同意今年度的合作注意事項 COSCUP 歡迎社群夥伴宣傳、分享社群在 COSCUP 的活動相關資訊,包含且不限於規劃獨立報名系統、架設宣傳活動網頁,或是使用票卷系統等,惟須請在相關管道中註明合作夥伴為 COSCUP 團隊。且秉持 COSCUP 精神,所有以 COSCUP 名義相關的活動,請避免限定會眾參與身分,若因特殊原因需限定參與身分,請與議程組聯絡與討論。 申請加入 COSUCP 的夥伴將視為同意大會 CoC準則,敬請夥伴們一同宣導大會 CoC ,為會眾創造尊重與友善的活動 更多社群合作準則,請參考 本文件,報名即視為同意本文件所提到的各項注意事項 Changes in COSCUP 2024 今年 COSCUP 將基於 20

COSCUP 2024 Early Bird Call for Proposals

COSCUP 2024 Early Bird Call for Proposals Welcome to the Early Bird Call for Proposals of COSCUP 2024! COSCUP Now offer early submission to better prepare our potential speakers to attend the 2024 COSCUP in person 😀 About COSCUP COSCUP is an annual conference organized by the Taiwanese Open source community since 2006. COSCUP aims to provide a platform to connect Open Source coders, users and promoters, while promoting FLOSS within the annual conference. The conference is free to attend and all the staff are volunteers. We had more than 2800 attendees last year, and we believe this year there will be more. It is the biggest open source gathering in Taiwan, and the attendees are mostly developers, along with some power users and FLOSS promoters and lovers. Here is an album of our previous events: https://www.flickr.com/photos/coscup/albums Where is Taiwan? Find it on  Google maps

COSCUP 2023 財務報告

COSCUP 2023 年度財務收支摘要 COSCUP 2023 Annual Income and Expenditure Summary For the period 2023/01/01~2023/12/31 收入 Revenues 金額 總計 企業贊助收入 NT$2,366,132 個人贊助收入 219,054 義賣收入 122,463 利息收入 4,574 周邊活動收入 24,440 總收入 Total Revenues NT$2,736,663 支出 Expenses 金額 總計 場地費 NT$616,498 議程交流費用 446,810 行銷費 444,015 義務工作人員費用 432,000 餐飲費用 220,555 設備與器材費 144,587 周邊活動費用 88,300 擺攤出訪費用 74,203 倉儲及物流費用 43,657 線上系統費用 37,906 保險費 11,957 雜支 6,837 捐贈開源社群 130,983 金流手續費 7,826 稅費與金流服務費 228,769 總支出 Total Expenses NT$2,934,903 期間淨收支 Net Income 2023/01/01~2023/12/31 -NT$198,240 支出科目 歷年結餘 歷年結餘 2006/2008~2018 結餘 NT$5,146,663 2019 結餘 NT$1,128,514 2020 結餘 NT$86,842 2021 結餘 NT$744,271 2022 結餘 NT$1,015,462 2023 結餘 -NT$198,240 結餘款總計 NT$7,923,512