float>bfloat-bits ( x -- bits )

Vocabulary

math.floats.small

Inputs

x

a real

Outputs

bits	an integer

Word description

Encodes BF16 directly from binary64 with round-to-nearest, ties-to-even, independent of the host rounding mode. NaNs become 0x7fc0.

Definition

USING: math.floats.small.private ;

IN: math.floats.small

: float>bfloat-bits ( x -- bits ) 7 8 float>small-bits ;