---
title: "ClikaRT::dtype::tfloat32_t"
sidebar_label: "tfloat32_t"
description: "TensorFloat-32: 1 sign + 8 exponent + 10 effective mantissa, bias 127, stored in a 32-bit container with the low 13 mantissa bits zeroed. Range = fp32, precision ≈ fp16."
---

<!-- 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`

TensorFloat-32: 1 sign + 8 exponent + 10 effective mantissa, bias 127, stored in a 32-bit container with the low 13 mantissa bits zeroed. Range = fp32, precision ≈ fp16. Conversion from fp32 round-to-nearest-even-narrows the low 13 bits; conversion to fp32 is identity. [`from_truncated`](./tfloat32_t.md#from_truncated) drops the bits without rounding.

## Static member functions

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

<div class="api-signature">

`static` `constexpr` [`tfloat32_t`](./tfloat32_t.md) **`from_bits`**(`std::uint32_t` `b`) `noexcept`

</div>

Reinterpret a raw 32-bit encoding without converting.

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 108

</div>

### from\_truncated() {#from_truncated}

<div class="api-signature">

`static` [`tfloat32_t`](./tfloat32_t.md) **`from_truncated`**(`float` `f`) `noexcept`

</div>

Convert from fp32 by truncation (drop the low 13 bits, no rounding).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 111

</div>

## Member functions

### tfloat32\_t() {#tfloat32_t}

<div class="api-signature">

`constexpr` `constexpr` **`tfloat32_t`**() `noexcept=default`

</div>

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 99

</div>

### tfloat32\_t(float) {#tfloat32_t-2}

<div class="api-signature">

`explicit` **`tfloat32_t`**(`float` `f`) `noexcept`

</div>

Convert from fp32 (round-to-nearest-even-narrow the low 13 bits).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 102

</div>

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

<div class="api-signature">

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

</div>

Convert to fp32 (identity).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 105

</div>

## Data members

### bits {#bits}

<div class="api-signature">

`std::uint32_t` **`bits`** `= 0`

</div>

Raw 32-bit encoding (the storage/ABI form).

<div class="api-declared">

Declared in `ClikaRT/compute/scalar_types.h`, line 97

</div>

## Friends

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

<div class="api-signature">

`friend` `bool` **`operator==`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 113

</div>

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

<div class="api-signature">

`friend` `bool` **`operator!=`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 114

</div>

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

<div class="api-signature">

`friend` `bool` **`operator<`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 115

</div>

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

<div class="api-signature">

`friend` `bool` **`operator<=`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 116

</div>

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

<div class="api-signature">

`friend` `bool` **`operator>`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 117

</div>

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

<div class="api-signature">

`friend` `bool` **`operator>=`**([`tfloat32_t`](./tfloat32_t.md) `a`, [`tfloat32_t`](./tfloat32_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 118

</div>