namespace InferenceEngine::PrecisionUtils

Overview

Namespace for precision utilities. More…

namespace PrecisionUtils {

// namespaces

namespace InferenceEngine::PrecisionUtils::details;

// global functions

ie_fp16 f32tof16(float x);
float f16tof32(ie_fp16 x);

void f16tof32Arrays(
    float \* dst,
    const ie_fp16 \* src,
    size_t nelem,
    float scale = 1.f,
    float bias = 0.f
    );

void f32tof16Arrays(
    ie_fp16 \* dst,
    const float \* src,
    size_t nelem,
    float scale = 1.f,
    float bias = 0.f
    );

template <
    class OutT,
    class InT,
    typename std::enable_if<std::is_integral<OutT>::value&&std::is_integral<InT>::value&&std::is_signed<InT>::value&&!std::is_same<OutT, InT>::value>::type \* = nullptr
    >
OutT saturate_cast(const InT& value);

template <class InT>
InT saturate_cast(const InT& value);

} // namespace PrecisionUtils

Detailed Documentation

Namespace for precision utilities.

Global Functions

ie_fp16 f32tof16(float x)

Converts a single-precision floating point value to a half-precision floating poit value.

Parameters:

x	A single-precision floating point value

Returns:

A half-precision floating point value

float f16tof32(ie_fp16 x)

Convers a half-precision floating point value to a single-precision floating point value.

Parameters:

x	A half-precision floating point value

Returns:

A single-precision floating point value

void f16tof32Arrays(
    float \* dst,
    const ie_fp16 \* src,
    size_t nelem,
    float scale = 1.f,
    float bias = 0.f
    )

Converts a half-precision floating point array to single-precision floating point array and applies scale and bias is needed.

Parameters:

dst	A destination array of single-precision floating point values
src	A source array of half-precision floating point values
nelem	A number of elements in arrays
scale	An optional scale parameter
bias	An optional bias parameter

void f32tof16Arrays(
    ie_fp16 \* dst,
    const float \* src,
    size_t nelem,
    float scale = 1.f,
    float bias = 0.f
    )

Converts a single-precision floating point array to a half-precision floating point array and applies scale and bias if needed.

Parameters:

dst	A destination array of half-precision floating point values
src	A sources array of single-precision floating point values
nelem	A number of elements in arrays
scale	An optional scale parameter
bias	An optional bias parameter

template <
    class OutT,
    class InT,
    typename std::enable_if<std::is_integral<OutT>::value&&std::is_integral<InT>::value&&std::is_signed<InT>::value&&!std::is_same<OutT, InT>::value>::type \* = nullptr
    >
OutT saturate_cast(const InT& value)

Converts one integral type to another saturating the result if the source value doesn’t fit into destination type range.

Parameters:

value

Value to be converted

Returns:

A saturated value

template <class InT>
InT saturate_cast(const InT& value)

Converts one integral type to another saturating the result if the source value doesn’t fit into destination type range.

Parameters:

value

Value to be converted

Returns:

A saturated value