Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

RETRACTED ARTICLE: AI system outperforms humans in designing floorplans for microchips

A machine-learning system has been trained to place memory blocks in microchip designs. The system beats human experts at the task, and offers the promise of better, more-rapidly produced chip designs than are currently possible.
  1. Andrew B. Kahng

    1. Andrew B. Kahng is in the Department of Computer Science and Engineering, and in the Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, California 92093, USA.

    View author publications

    You can also search for this author in PubMed  Google Scholar

Success or failure in designing microchips depends heavily on steps known as floorplanning and placement. These steps determine where memory and logic elements are located on a chip. The locations, in turn, strongly affect whether the completed chip design can satisfy operational requirements such as processing speed and power efficiency. So far, the floorplanning task, in particular, has defied all attempts at automation. It is therefore performed iteratively and painstakingly, over weeks or months, by expert human engineers. But in a paper in Nature, researchers from Google (Mirhoseini et al.1) report a machine-learning approach that achieves superior chip floorplanning in hours.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 594, 183-185 (2021)

doi: https://doi.org/10.1038/d41586-021-01515-9

Updates & Corrections

  • Retraction 21 September 2023: The author has retracted this article because new information about the methods used in the reported paper (A. Mirhoseini et al. Nature 594, 207–212; 2021) has become available since publication, and that has changed the author’s assessment of, and conclusions about, the paper’s contributions. Nature is also doing an independent investigation of the performance claims in the paper.

References

  1. Mirhoseini, A. et al. Nature 594, 207–212 (2021).

    Article  Google Scholar 

  2. Markov, I. L., Hu, J. & Kim, M.-C. Proc. IEEE 103, 1985–2003 (2015).

    Article  Google Scholar 

  3. Kahng, A. B. Proc. ACM/IEEE Int. Symp. Physical Design 15–22 (2021).

  4. Kirkpatrick, S., Gelatt, C. D. Jr & Vecchi, M. P. Science 220, 671–680 (1983).

    Article  PubMed  Google Scholar 

  5. Mirhoseini, A. et al. Preprint at https://arxiv.org/abs/2004.10746 (2020).

  6. Clarke, A. C. Profiles of the Future: An Inquiry into the Limits of the Possible 41 (Macmillan, 1973).

    Google Scholar 

  7. Sait, S. M. & Youssef, H. VLSI Physical Design Automation: Theory and Practice Ch. 3, 90–95 (McGraw-Hill, 1995).

    Google Scholar 

  8. Zaruba, F. & Benini, L. IEEE Trans. Very Large Scale Integration 27, 2629–2640 (2019).

    Article  Google Scholar 

Download references

Competing Interests

The author declares no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing

Search

Advanced search

Quick links