half-precision topic

Optimised Caffe with OpenCL supporting for less powerful devices such as mobile phones

jizhuoran

Floating-Point Arithmetic Library for Z80

DW0RKiN

Python module which finds the IEEE-754 representation of a floating point number.

canbula

CPP20 implementation of a 16-bit floating-point type mimicking most of the IEEE 754 behavior. Single file and header-only.

fengwang