CONFIG_FP16_IEEE

FP16 IEEE format

Type: bool

Help

This option selects the IEEE 754-2008 format for FP16.  This format can
represent normalized values in the range of 2^(-14) to 65504.  There are
11 bits of significand precision, approximately 3 decimal digits.

Direct dependencies

<choice: FP16 format>

(Includes any dependencies from ifs and menus.)

Kconfig definition

At <Zephyr>/arch/arm/core/aarch32/Kconfig:287

Included via <Zephyr>/Kconfig:8 → <Zephyr>/Kconfig.zephyr:39 → <Zephyr>/arch/Kconfig:12 → <Zephyr>/arch/arm/Kconfig:65

Menu path: (Top) → ARM Options → Half-precision floating point support → FP16 format

config FP16_IEEE
    bool "FP16 IEEE format"
    depends on <choice>
    help
      This option selects the IEEE 754-2008 format for FP16.  This format can
      represent normalized values in the range of 2^(-14) to 65504.  There are
      11 bits of significand precision, approximately 3 decimal digits.

(The ‘depends on’ condition includes propagated dependencies from ifs and menus.)