io.milvus.common.utils

Class Float16Utils

java.lang.Object

io.milvus.common.utils.Float16Utils

public class Float16Utils
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
Float16Utils()

Method Summary

Modifier and Type	Method and Description
static java.util.List<java.lang.Float>	bf16BufferToVector(java.nio.ByteBuffer buf) Converts a ByteBuffer to bf16 vector upcasts to float32 array.
static float	bf16ToFloat(short input) Upcasts a bf16 value stored in a short into a float32 value.
static java.util.List<java.lang.Short>	bufferToF16Vector(java.nio.ByteBuffer buf) Converts a ByteBuffer to a fp16/bf16 vector stored in short array.
static java.nio.ByteBuffer	f16VectorToBuffer(java.util.List<java.lang.Short> vector) Stores a fp16/bf16 vector into a ByteBuffer.
static java.nio.ByteBuffer	f32VectorToBf16Buffer(java.util.List<java.lang.Float> vector) Rounds a float32 vector to bf16 values, and stores into a ByteBuffer.
static java.nio.ByteBuffer	f32VectorToFp16Buffer(java.util.List<java.lang.Float> vector) Rounds a float32 vector to fp16 values, and stores into a ByteBuffer.
static short	floatToBf16(float input) Converts a float32 into bf16.
static short	floatToFp16(float input) Rounds a float32 value to a fp16 stored in a short.
static java.util.List<java.lang.Float>	fp16BufferToVector(java.nio.ByteBuffer buf) Converts a ByteBuffer to fp16 vector upcasts to float32 array.
static float	fp16ToFloat(short input) Upcasts a fp16 value stored in a short to a float32 value.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Float16Utils

public Float16Utils()

Method Detail

floatToBf16

public static short floatToBf16(float input)

Converts a float32 into bf16. May not produce correct values for subnormal floats. This method is copied from microsoft ONNX Runtime: https://github.com/microsoft/onnxruntime/blob/main/java/src/main/jvm/ai/onnxruntime/platform/Fp16Conversions.java

Parameters:

input - a standard float32 value which will be converted to a bfloat16 value

Returns:

a short value to store the bfloat16 value

bf16ToFloat

public static float bf16ToFloat(short input)

Upcasts a bf16 value stored in a short into a float32 value. This method is copied from microsoft ONNX Runtime: https://github.com/microsoft/onnxruntime/blob/main/java/src/main/jvm/ai/onnxruntime/platform/Fp16Conversions.java

Parameters:

input - a bfloat16 value which will be converted to a float32 value

Returns:

a float32 value converted from a bfloat16

floatToFp16

public static short floatToFp16(float input)

Rounds a float32 value to a fp16 stored in a short. This method is copied from microsoft ONNX Runtime: https://github.com/microsoft/onnxruntime/blob/main/java/src/main/jvm/ai/onnxruntime/platform/Fp16Conversions.java

Parameters:

input - a standard float32 value which will be converted to a float16 value

Returns:

a short value to store the float16 value

fp16ToFloat

public static float fp16ToFloat(short input)

Upcasts a fp16 value stored in a short to a float32 value. This method is copied from microsoft ONNX Runtime: https://github.com/microsoft/onnxruntime/blob/main/java/src/main/jvm/ai/onnxruntime/platform/Fp16Conversions.java

Parameters:

input - a float16 value which will be converted to a float32 value

Returns:

a float32 value converted from a float16 value

f32VectorToBf16Buffer

public static java.nio.ByteBuffer f32VectorToBf16Buffer(java.util.List<java.lang.Float> vector)

Rounds a float32 vector to bf16 values, and stores into a ByteBuffer.

Parameters:

vector - a float32 vector

Returns:

ByteBuffer the vector is converted to bfloat16 values and stored into a ByteBuffer

fp16BufferToVector

public static java.util.List<java.lang.Float> fp16BufferToVector(java.nio.ByteBuffer buf)

Converts a ByteBuffer to fp16 vector upcasts to float32 array.

Parameters:

buf - a buffer to store a float16 vector

Returns:

List of Float a float32 vector

f32VectorToFp16Buffer

public static java.nio.ByteBuffer f32VectorToFp16Buffer(java.util.List<java.lang.Float> vector)

Rounds a float32 vector to fp16 values, and stores into a ByteBuffer.

Parameters:

vector - a float32 vector

Returns:

ByteBuffer the vector is converted to float16 values and stored in a ByteBuffer

bf16BufferToVector

public static java.util.List<java.lang.Float> bf16BufferToVector(java.nio.ByteBuffer buf)

Converts a ByteBuffer to bf16 vector upcasts to float32 array.

Parameters:

buf - a buffer to store a bfloat16 vector

Returns:

List of Float the vector is converted to float32 values

f16VectorToBuffer

public static java.nio.ByteBuffer f16VectorToBuffer(java.util.List<java.lang.Short> vector)

Stores a fp16/bf16 vector into a ByteBuffer.

Parameters:

vector - a float16 vector stored in a list of Short

Returns:

ByteBuffer a buffer to store the float16 vector

bufferToF16Vector

public static java.util.List<java.lang.Short> bufferToF16Vector(java.nio.ByteBuffer buf)

Converts a ByteBuffer to a fp16/bf16 vector stored in short array.

Parameters:

buf - a buffer to store a float16 vector

Returns:

List of Short the vector is converted to a list of Short, each Short value is a float16 value