Half-Precision Floating Point
6.12 Half-Precision Floating Point
On ARM targets, GCC supports half-precision (16-bit) floating point via the __fp16
type. You must enable this type explicitly with the -mfp16-format
command-line option in order to use it.
ARM supports two incompatible representations for half-precision floating-point values. You must choose one of the representations and use it consistently in your program.
Specifying -mfp16-format=ieee
selects the IEEE 754-2008 format. 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.
Specifying -mfp16-format=alternative
selects the ARM alternative format. This representation is similar to the IEEE format, but does not support infinities or NaNs. Instead, the range of exponents is extended, so that this format can represent normalized valu