---
title: "ClikaRT::dtype::float16_t"
sidebar_label: "float16_t"
description: "IEEE 754 binary16: 1 sign + 5 exponent + 10 mantissa, bias 15. Range ±65504, smallest normal 2^-14, eps 2^-10. 16-bit storage."
---

<!-- Generated by tools/doxygen2mdx from Doxygen XML. Do not edit. -->

<span class="api-kind api-kind--struct">struct</span>

**Header:** `ClikaRT/compute/scalar_types.h`

IEEE 754 binary16: 1 sign + 5 exponent + 10 mantissa, bias 15. Range ±65504, smallest normal 2^-14, eps 2^-10. 16-bit storage.

## Static member functions

### from\_bits() {#from_bits}

<div class="api-signature">

`static` `constexpr` [`float16_t`](./float16_t.md) **`from_bits`**(`std::uint16_t` `b`) `noexcept`

</div>

Reinterpret a raw 16-bit encoding without converting.

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 52

</div>

## Member functions

### float16\_t() {#float16_t}

<div class="api-signature">

`constexpr` `constexpr` **`float16_t`**() `noexcept=default`

</div>

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 43

</div>

### float16\_t(float) {#float16_t-2}

<div class="api-signature">

`explicit` **`float16_t`**(`float` `f`) `noexcept`

</div>

Convert from fp32 (round-to-nearest-even).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 46

</div>

### operator float() {#operator-float}

<div class="api-signature">

**`operator float`**() `const noexcept`

</div>

Convert to fp32 (lossless).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 49

</div>

## Data members

### bits {#bits}

<div class="api-signature">

`std::uint16_t` **`bits`** `= 0`

</div>

Raw 16-bit encoding (the storage/ABI form).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 41

</div>

## Friends

### operator== {#operator-eq}

<div class="api-signature">

`friend` `bool` **`operator==`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 54

</div>

### operator\!= {#operator-ne}

<div class="api-signature">

`friend` `bool` **`operator!=`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 55

</div>

### operator\< {#operator-lt}

<div class="api-signature">

`friend` `bool` **`operator<`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 56

</div>

### operator\<= {#operator-le}

<div class="api-signature">

`friend` `bool` **`operator<=`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 57

</div>

### operator\> {#operator-gt}

<div class="api-signature">

`friend` `bool` **`operator>`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 58

</div>

### operator\>= {#operator-ge}

<div class="api-signature">

`friend` `bool` **`operator>=`**([`float16_t`](./float16_t.md) `a`, [`float16_t`](./float16_t.md) `b`) `noexcept`

</div>

Compares `a` and `b` by dequantized value (IEEE rules; a NaN operand compares false).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 59

</div>