IDEAS home Printed from https://ideas.repec.org/a/nat/nature/v620y2023i7975d10.1038_s41586-023-06337-5.html
   My bibliography  Save this article

An analog-AI chip for energy-efficient speech recognition and transcription

Author

Listed:
  • S. Ambrogio

    (IBM Research – Almaden)

  • P. Narayanan

    (IBM Research – Almaden)

  • A. Okazaki

    (IBM Research – Tokyo)

  • A. Fasoli

    (IBM Research – Almaden)

  • C. Mackin

    (IBM Research – Almaden)

  • K. Hosokawa

    (IBM Research – Tokyo)

  • A. Nomura

    (IBM Research – Tokyo)

  • T. Yasuda

    (IBM Research – Tokyo)

  • A. Chen

    (IBM Research – Almaden)

  • A. Friz

    (IBM Research – Almaden)

  • M. Ishii

    (IBM Research – Tokyo)

  • J. Luquin

    (IBM Research – Almaden)

  • Y. Kohda

    (IBM Research – Tokyo)

  • N. Saulnier

    (IBM Research – Albany NanoTech Center)

  • K. Brew

    (IBM Research – Albany NanoTech Center)

  • S. Choi

    (IBM Research – Albany NanoTech Center)

  • I. Ok

    (IBM Research – Albany NanoTech Center)

  • T. Philip

    (IBM Research – Albany NanoTech Center)

  • V. Chan

    (IBM Research – Albany NanoTech Center)

  • C. Silvestre

    (IBM Research – Albany NanoTech Center)

  • I. Ahsan

    (IBM Research – Albany NanoTech Center)

  • V. Narayanan

    (IBM Thomas J. Watson Research Center)

  • H. Tsai

    (IBM Research – Almaden)

  • G. W. Burr

    (IBM Research – Almaden)

Abstract

Models of artificial intelligence (AI) that have billions of parameters can achieve high accuracy across a range of tasks1,2, but they exacerbate the poor energy efficiency of conventional general-purpose processors, such as graphics processing units or central processing units. Analog in-memory computing (analog-AI)3–7 can provide better energy efficiency by performing matrix–vector multiplications in parallel on ‘memory tiles’. However, analog-AI has yet to demonstrate software-equivalent (SWeq) accuracy on models that require many such tiles and efficient communication of neural-network activations between the tiles. Here we present an analog-AI chip that combines 35 million phase-change memory devices across 34 tiles, massively parallel inter-tile communication and analog, low-power peripheral circuitry that can achieve up to 12.4 tera-operations per second per watt (TOPS/W) chip-sustained performance. We demonstrate fully end-to-end SWeq accuracy for a small keyword-spotting network and near-SWeq accuracy on the much larger MLPerf8 recurrent neural-network transducer (RNNT), with more than 45 million weights mapped onto more than 140 million phase-change memory devices across five chips.

Suggested Citation

  • S. Ambrogio & P. Narayanan & A. Okazaki & A. Fasoli & C. Mackin & K. Hosokawa & A. Nomura & T. Yasuda & A. Chen & A. Friz & M. Ishii & J. Luquin & Y. Kohda & N. Saulnier & K. Brew & S. Choi & I. Ok & , 2023. "An analog-AI chip for energy-efficient speech recognition and transcription," Nature, Nature, vol. 620(7975), pages 768-775, August.
  • Handle: RePEc:nat:nature:v:620:y:2023:i:7975:d:10.1038_s41586-023-06337-5
    DOI: 10.1038/s41586-023-06337-5
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41586-023-06337-5
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1038/s41586-023-06337-5?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Yuyan Zhu & Yang Wang & Xingchen Pang & Yongbo Jiang & Xiaoxian Liu & Qing Li & Zhen Wang & Chunsen Liu & Weida Hu & Peng Zhou, 2024. "Non-volatile 2D MoS2/black phosphorus heterojunction photodiodes in the near- to mid-infrared region," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    2. Thomas Dalgaty & Filippo Moro & Yiğit Demirağ & Alessio Pra & Giacomo Indiveri & Elisa Vianello & Melika Payvand, 2024. "Mosaic: in-memory computing and routing for small-world spike-based neuromorphic systems," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    3. Malte J. Rasch & Fabio Carta & Omobayode Fagbohungbe & Tayfun Gokmen, 2024. "Fast and robust analog in-memory deep neural network training," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    4. Simone D’Agostino & Filippo Moro & Tristan Torchet & Yiğit Demirağ & Laurent Grenouillet & Niccolò Castellani & Giacomo Indiveri & Elisa Vianello & Melika Payvand, 2024. "DenRAM: neuromorphic dendritic architecture with RRAM for efficient temporal processing with delays," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    5. Yongxiang Li & Shiqing Wang & Ke Yang & Yuchao Yang & Zhong Sun, 2024. "An emergent attractor network in a passive resistive switching circuit," Nature Communications, Nature, vol. 15(1), pages 1-9, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:nature:v:620:y:2023:i:7975:d:10.1038_s41586-023-06337-5. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.