The latest development version of this page may be more current than this released 2.7.5 version.

CONFIG_FP16_ALT

FP16 ARM alternative format

Type: bool

Help

This option selects the ARM alternative format for FP16.  This
representation is similar to the IEEE 754-2008 format, but does not
support infinites or NaNs. Instead, the range of exponents is extended,
so that this format can represent normalized values in the range of
2^(-14) to 131008.

Direct dependencies

<choice: FP16 format>

(Includes any dependencies from ifs and menus.)

Kconfig definition

At arch/arm/core/aarch32/Kconfig:283

Included via Kconfig:8 → Kconfig.zephyr:39 → arch/Kconfig:12 → arch/arm/Kconfig:57

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

config FP16_ALT
    bool "FP16 ARM alternative format"
    depends on <choice>
    help
      This option selects the ARM alternative format for FP16.  This
      representation is similar to the IEEE 754-2008 format, but does not
      support infinites or NaNs. Instead, the range of exponents is extended,
      so that this format can represent normalized values in the range of
      2^(-14) to 131008.

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