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.

  • Correspondence
  • Published:

Reducing the ecological impact of computing through education and Python compilers

Nature Astronomy volume 5, pages 334–335 (2021)Cite this article

Subjects

The Original Article was published on 10 September 2020

To the Editor — We read with interest the Comment by Portegies Zwart on the ecological impact of high-performance computing in astrophysics1. We fully agree with its take-home message: scientists should be mindful of their carbon footprint. One of the proposed solutions, however, is to avoid the Python programming language. We contend that this would be counterproductive and that scientific programs written in Python can be efficient and energy-friendly. We argue that human factors, such as education, and the advancement of compiler technology are much more important than choice of language.

To support his point, Portegies Zwart presents a benchmark of the N-body problem with an inefficient implementation in Python that runs 50 times slower than a C++ implementation. As Python users concerned about our ecological impact, we worked on similar benchmarks on the same problem. In contrast to Portegies Zwart, we (1) consider efficient implementations in Python and Julia and (2) measure the energy consumption with dedicated hardware equipped with wattmeters.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

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

Fig. 1: Efficiency in terms of CO2 production and elapsed time for implementations in Python, Julia, C++ and Fortran.

References

  1. Portegies Zwart, S. Nat. Astron. 4, 819–822 (2020).

    Article  ADS  Google Scholar 

  2. Aycock, J. ACM Comput. Surv. 35, 97–113 (2003).

    Article  Google Scholar 

  3. Harris, C. R. et al. Nature 585, 357–362 (2020).

    Article  ADS  Google Scholar 

  4. Knuth, D. E. ACM Comput. Surv. 6, 261–301 (1974).

    Article  Google Scholar 

  5. Guelton, S. et al. Comput. Sci. Discov. 8, 014001 (2015).

    Article  Google Scholar 

  6. Lam, S. K., Pitrou, A. & Seibert, S. In Proc. Second Workshop on the LLVM Compiler Infrastructure in HPC 7 (ACM, 2015).

  7. Bolz, C. F., Cuni, A., Fijalkowski, M. & Rigo, A. In Proc. 4th Workshop on the Implementation, Compilation, Optimization of Object-Oriented Languages and Programming Systems 18–25 (ACM, 2009).

  8. Augier, P., Mohanan, A. V. & Bonamy, C. J. Open Res. Softw. 7, 9 (2019).

    Article  Google Scholar 

  9. Cheng, L., Ilbeyi, B., Bolz-Tereick, C. F. & Batten, C. In Proc. 18th ACM/IEEE International Symposium on Code Generation and Optimization 16–29 (ACM, 2020).

Download references

Acknowledgements

We thank D. Barreto, L. Martínez and A. Oskin for working on the optimized Julia implementations. We also thank Camille Noûs (Cogitamus Laboratory) and the open-source communities who contributed to the tools used for this study. Part of this work was performed using resources provided by Grid’5000 (supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several universities) and CINES under GENCI allocation number A0080107567.

Author information

Authors and Affiliations

  1. University of Grenoble Alpes, CNRS, Grenoble INP, LEGI, Grenoble, France

    Pierre Augier

  2. Heinrich-Heine-Universität, Düsseldorf, Germany

    Carl Friedrich Bolz-Tereick

  3. Namek, Paris, France

    Serge Guelton

  4. Department of Meteorology, Stockholm University, Stockholm, Sweden

    Ashwin Vishnu Mohanan

Authors
  1. Pierre Augier
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Carl Friedrich Bolz-Tereick
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Serge Guelton
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ashwin Vishnu Mohanan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pierre Augier.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Augier, P., Bolz-Tereick, C.F., Guelton, S. et al. Reducing the ecological impact of computing through education and Python compilers. Nat Astron 5, 334–335 (2021). https://doi.org/10.1038/s41550-021-01342-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41550-021-01342-y

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

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