Floating Point Unit with High Precision Efficiency
Year: 2025
Type: article
Abstract: In this paper, we dive into designing a Single Precision Floating Point Unit (FPU), a key player in modern processors. FPUs are essential for handling complex numerical calculations with high precision and a broad range, making them indispensable in scientific research, graphics rendering, and machine learning—our design centers around two main components: the Brent-Kung adder and the radix-4 Booth multiplier. The BrentKung adder is our go-to for fast addition and subtraction. Thanks to its clever parallel-prefix structure, it minimises delays even as the numbers get bigger. For multiplication, we turn to the radix-4 Booth multiplier. This powerhouse streamlines the multiplication process by cutting down the number of partial products and operations needed, efficiently handling both positive and negative numbers. By integrating these components, our FPU can handle floating-point arithmetic with excellent efficiency and reliability. In scientific computing, this means more accurate simulations and data analyses. For graphics processing, it translates to better image rendering and smoother visual effects. And in machine learning, it supports robust training and execution of algorithms on massive datasets, ensuring dependable model performance.
Authors: Dr. Vasudeva G, Dr. Bharathi Gururaj
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410747676