Answers are grounded in this paper and cite their sources.
The IEEE 754 Standard for Floating-Point Arithmetic has long dominated real-number representation in modern computing. Posit arithmetic, a recent alternative, has garnered growing attention for its potential advantages over IEEE 754, inspiring research across academia and industry. This survey provides a detailed examination of the theoretical foundations of posits, their applications in fields such as scientific computing and neural networks, and notable advancements in hardware implementations, including accelerators and RISC-V cores. By synthesizing these developments, this work offers key insights and highlights opportunities for future research, providing a comprehensive resource for understanding and advancing posit arithmetic in diverse computational domains.
No takes yet. Share an insight, caveat, or question.
Mallasén et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: