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

[2504.07835] pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2504.07835 (cs) [Submitted on 10 Apr 2025 ( v1 ), last revised 26 Aug 2026 (this version, v7)] Title: pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks Authors: Erin Carson , Xinye Chen View PDF HTML (experimental) Abstract: 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 \texttt{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. \texttt{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 \texttt{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, \texttt{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. Subjects: Machine Learning (cs.LG) ; Numerical Analysis (math.NA) Cite as: arXiv:2504.07835 [cs.LG] (or arXiv:2504.07835v7 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2504.07835 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xinye Chen [ view email ] [v1] Thu, 10 Apr 2025 15:12:29 UTC (46,157 KB) [v2] Fri, 11 Apr 2025 21:00:08 UTC (45,726 KB) [v3] Sun, 20 Apr 2025 16:18:37 UTC (46,131 KB) [v4] Thu, 1 May 2025 16:35:03 UTC (46,156 KB) [v5] Tue, 24 Feb 2026 15:49:15 UTC (50,496 KB) [v6] Thu, 30 Jul 2026 17:27:18 UTC (13,792 KB) [v7] Wed, 26 Aug 2026 20:15:16 UTC (13,760 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2025-04 Change to browse by: cs cs.NA math math.NA References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• pychop: Emulating Low-Precision Arithmetic in Numerical Methods and Neural Networks#677366
• FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving#998172
• Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver#1050208
• GSC-QEMit: A Telemetry-Driven Hierarchical Forecast-and-Bandit Framework for Adaptive Quantum Error Mitigation#138930
• DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode#10417