EUVIMEDEUVIMED entdecken
Crossref

pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks

Erin Carson, Xinye Chen

ACM Transactions on Mathematical Software · 31.08.2026

DOI: 10.1145/3840284 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Mathematical Software, online erschienen am 31.08.2026. Verfasst von Erin Carson und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivated by the growing demand for reduced-precision arithmetic in computational science, we exploit lower-precision emulation in Python–widely regarded as the dominant programming language for numerical analysis and machine learning. Low-precision paradigms have revolutionized deep learning by enabling more efficient computation and reduced memory footprint while maintaining model fidelity. To better enable numerical experimentation with and exploration of reduced-precision computation, we developed pychop , which supports customizable floating-point formats and a comprehensive set of rounding modes in Python, allowing users to benefit from fast, reduced-precision emulation in numerous applications. pychop also provides flexible interfaces for array and tensor backends, enabling efficient reduced-precision emulation on both CPUs and GPUs for neural network deployment. In this paper, we offer a comprehensive exposition of the design and applications of pychop . Furthermore, we present empirical results on reduced-precision emulation for image classification and object detection using published datasets, illustrating the sensitivity to low precision and delivering valuable insights into its quantization-aware training and post-quantization impacts. Establishing itself as a foundational tool for advancing mixed-precision algorithms, pychop enables in-depth investigations into the effects of numerical precision in scientific computing and deep learning deployment, facilitating the development of novel hardware accelerators.

Zitieren

APA

Carson, E., & Chen, X. (2026). pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks. ACM Transactions on Mathematical Software. https://doi.org/10.1145/3840284

Vancouver

Carson E, Chen X. pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks. ACM Transactions on Mathematical Software. 2026. doi:10.1145/3840284

BibTeX
@article{Carson2026,
  author = {Carson, Erin and Chen, Xinye},
  title = {pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks},
  journal = {ACM Transactions on Mathematical Software},
  year = {2026},
  doi = {10.1145/3840284}
}
Kostenlos starten →