Simulation model of a mathematical processor (Floating point unit, FPU)
-
Updated
Nov 30, 2022 - Python
Simulation model of a mathematical processor (Floating point unit, FPU)
IEEE 754 half-precision (FP16) FPU in Verilog — implements Add, Sub, Mul, Div with a Python/NumPy verification pipeline. Achieves 99.7% accuracy across 10,000 randomised test cases including subnormals, overflow, and NaN edge cases.
Add a description, image, and links to the fpu topic page so that developers can more easily learn about it.
To associate your repository with the fpu topic, visit your repo's landing page and select "manage topics."