toWord

Return an unsigned 16-bit integer corresponding to the IEEE 754 binary representation of a half-precision floating-point number.

Installation

npm install @stdlib/number-float16-base-to-word

Usage

var toWord = require( '@stdlib/number-float16-base-to-word' );

toWord( x )

Returns an unsigned 16-bit integer corresponding to the IEEE 754 binary representation of a half-precision floating-point number.

var float64ToFloat16 = require( '@stdlib/number-float64-base-to-float16' );

var f16 = float64ToFloat16( 1.05 );
// returns 1.0498046875

var w = toWord( f16 ); // => 0 01111 0000110011
// returns 15411

Examples

var float64ToFloat16 = require( '@stdlib/number-float64-base-to-float16' );
var uniform = require( '@stdlib/random-array-uniform' );
var map = require( '@stdlib/array-base-map' );
var naryFunction = require( '@stdlib/utils-nary-function' );
var pickArguments = require( '@stdlib/utils-pick-arguments' );
var logEachMap = require( '@stdlib/console-log-each-map' );
var toWord = require( '@stdlib/number-float16-base-to-word' );

// Generate an array of random double-precision floating-point numbers:
var f64 = uniform( 1000, -50.0, 50.0 );

// Convert each value to a half-precision floating-point number:
var f16 = map( f64, naryFunction( float64ToFloat16, 1 ) );

// Convert half-precision floating-point numbers to integers representing the binary literal:
logEachMap( 'float64: %f => float16: %f => word: %d', f64, f16, pickArguments( toWord, [ 1 ] ) );

C APIs

Usage

#include "stdlib/number/float16/base/to_word.h"

stdlib_base_float16_to_word( x, *word )

Converts a half-precision floating-point number to an unsigned 16-bit integer corresponding to the number's IEEE 754 binary representation.

#include "stdlib/number/float16/ctor.h"
#include <stdint.h>

uint16_t word;

stdlib_float16_t x = stdlib_float16_from_bits( 51648 ); // => -11.5
stdlib_base_float16_to_word( x, &word );

The function accepts the following arguments:

• x: [in] stdlib_float16_t input value.
• word: [out] uint16_t* destination.

void stdlib_base_float16_to_word( const stdlib_float16_t x, uint16_t *word );

stdlib_base_float16_word_t

An opaque type definition for a union for converting between a half-precision floating-point number and an unsigned 16-bit integer.

#include "stdlib/number/float16/ctor.h"
#include <stdint.h>

stdlib_base_float16_word_t w;

// Assign a half-precision floating-point number:
w.value = stdlib_float16_from_bits( 51648 ); // => -11.5

// Retrieve the word:
uint16_t word = w.word;

The union has the following members:

• value: stdlib_float16_t half-precision floating-point number.
• word: uint16_t word.

Examples

#include "stdlib/number/float64/base/to_float16.h"
#include "stdlib/number/float16/base/to_word.h"
#include <stdint.h>
#include <stdio.h>

int main( void ) {
    const double x[] = { 3.14, -3.14, 0.0, 0.0/0.0 };

    stdlib_float16_t v;
    uint16_t word;
    int i;
    for ( i = 0; i < 4; i++ ) {
        v = stdlib_base_float64_to_float16( x[ i ] );
        stdlib_base_float16_to_word( v, &word );
        printf( "%lf => word: %u\n", x[ i ], word );
    }
}

Notice

This package is part of stdlib, a standard library for JavaScript and Node.js, with an emphasis on numerical and scientific computing. The library provides a collection of robust, high performance libraries for mathematics, statistics, streams, utilities, and more.

For more information on the project, filing bug reports and feature requests, and guidance on how to develop stdlib, see the main project repository.

Community

License

See LICENSE.

Copyright

Copyright © 2016-2026. The Stdlib Authors.