ai.djl

Class Device

java.lang.Object

ai.djl.Device

public class Device
extends java.lang.Object

The Device class provides the specified assignment for CPU/GPU processing on the NDArray.

Users can use this to specify whether to load/compute the NDArray on CPU/GPU with deviceType and deviceId provided.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static interface	Device.Type Contains device type string constants.

Constructor Summary

Constructors

Constructor and Description
Device(java.lang.String deviceType) Creates a Device with basic information.
Device(java.lang.String deviceType, int deviceId) Creates a Device with basic information.

Method Summary

Modifier and Type	Method and Description
static Device	cpu() Returns the default CPU Device.
static Device	defaultDevice() Returns the default context used in Engine.
static Device	defaultIfNull(Device device) Returns the given device or the default if it is null.
static Device	defaultIfNull(Device device, Device def) Returns the given device or the passed in default if it is null.
boolean	equals(java.lang.Object o)
int	getDeviceId() Returns the deviceId of the Device.
static Device[]	getDevices(int maxGpus) Returns an array of devices given the maximum number of GPUs to use.
java.lang.String	getDeviceType() Returns the device type of the Device.
static int	getGpuCount() Returns the number of GPUs available in the system.
static int	getGpuCount(java.lang.String engineName) Returns the number of GPUs available with specified framework.
static Device	gpu() Returns the default GPU Device.
static Device	gpu(int deviceId) Returns a new instance of GPU Device with the specified deviceId.
int	hashCode()
java.lang.String	toString()

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

Device

public Device(java.lang.String deviceType)

Creates a Device with basic information.

Parameters:

deviceType - the device type, typically CPU or GPU choose which GPU to process the NDArray

Device

public Device(java.lang.String deviceType,
              int deviceId)

Creates a Device with basic information.

Parameters:

deviceType - the device type, typically CPU or GPU

deviceId - the deviceId on the hardware. For example, if you have multiple GPUs, you can choose which GPU to process the NDArray

Method Detail

getDeviceType

public java.lang.String getDeviceType()

Returns the device type of the Device.

Returns:

the device type of the Device

getDeviceId

public int getDeviceId()

Returns the deviceId of the Device.

Returns:

the deviceId of the Device

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

equals

public boolean equals(java.lang.Object o)

Overrides:

equals in class java.lang.Object

hashCode

public int hashCode()

Overrides:

hashCode in class java.lang.Object

cpu

public static Device cpu()

Returns the default CPU Device.

Returns:

the default CPU Device

gpu

public static Device gpu()

Returns the default GPU Device.

Returns:

the default GPU Device

gpu

public static Device gpu(int deviceId)

Returns a new instance of GPU Device with the specified deviceId.

Parameters:

deviceId - the GPU device ID

Returns:

a new instance of GPU Device with specified deviceId

getDevices

public static Device[] getDevices(int maxGpus)

Returns an array of devices given the maximum number of GPUs to use.

If GPUs are available, it will return an array of Device of size \(min(numAvailable, maxGpus)\). Else, it will return an array with a single CPU device.

Parameters:

maxGpus - the max number of GPUs to use

Returns:

an array of devices

getGpuCount

public static int getGpuCount()

Returns the number of GPUs available in the system.

Returns:

the number of GPUs available in the system

getGpuCount

public static int getGpuCount(java.lang.String engineName)

Returns the number of GPUs available with specified framework.

Parameters:

engineName - the name of engine to retrieve

Returns:

the number of GPUs available in the system

defaultDevice

public static Device defaultDevice()

Returns the default context used in Engine.

The default type is defined by whether the Deep Learning framework is recognizing GPUs available on your machine. If there is no GPU available, CPU will be used.

Returns:

a Device

defaultIfNull

public static Device defaultIfNull(Device device)

Returns the given device or the default if it is null.

Parameters:

device - the device to try to return

Returns:

the given device or the default if it is null

defaultIfNull

public static Device defaultIfNull(Device device,
                                   Device def)

Returns the given device or the passed in default if it is null.

Parameters:

device - the device to try to return

def - the default device to return if device is null

Returns:

the given device or the passed in default if it is null