Floating-point autotuning with customized precisions
ACM Transactions on Mathematical Software · 12.11.2026
DOI: 10.1145/3862629 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Mathematical Software, online erschienen am 12.11.2026. Verfasst von Xinye Chen und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben.
Abstract (Originalsprache)
Reduced-precision arithmetic offers significant opportunities to improve performance, memory usage, and energy efficiency in numerical applications, provided that numerical accuracy is preserved. This work investigates automated precision tuning through customized floating-point formats with user-defined exponent and significand sizes, enabling the emulation of emerging low-precision formats and the exploration of non-standard precision configurations within a unified mixed-precision framework. The proposed methodology, implemented in the PROMISE precision autotuning tool, combines numerical validation with a systematic search to generate program variants that satisfy user-defined accuracy requirements. To address the computational cost of this exploration, a containerized benchmarking framework supports parallel execution across multiple algorithms and parameter configurations. The approach is evaluated on a suite of numerical programs, including linear solvers and applications from the Rodinia benchmark. Results show that a substantial proportion of variables can be safely reduced to lower precision while preserving accuracy, indicating that standard double precision is often over-provisioned. These findings highlight the potential of automated precision tuning to derive efficient mixed-precision configurations tailored to application-specific accuracy requirements.
Zitieren
APA
Chen, X., Jézéquel, F., & Hilaire, T. (2026). Floating-point autotuning with customized precisions. ACM Transactions on Mathematical Software. https://doi.org/10.1145/3862629
Vancouver
Chen X, Jézéquel F, Hilaire T. Floating-point autotuning with customized precisions. ACM Transactions on Mathematical Software. 2026. doi:10.1145/3862629
BibTeX
@article{Chen2026,
author = {Chen, Xinye and Jézéquel, Fabienne and Hilaire, Thibault},
title = {Floating-point autotuning with customized precisions},
journal = {ACM Transactions on Mathematical Software},
year = {2026},
doi = {10.1145/3862629}
}
EUVIMED