Class NativeND4JCUDATensorBackend

java.lang.Object

org.episteme.nativ.mathematics.linearalgebra.tensors.backends.ND4JBaseTensorBackend

org.episteme.nativ.mathematics.linearalgebra.tensors.backends.NativeND4JCUDATensorBackend

All Implemented Interfaces:

TensorBackend, TensorProvider, AlgorithmProvider, Backend, ComputeBackend

@AutoService({TensorBackend.class,AlgorithmProvider.class})
public class NativeND4JCUDATensorBackend
extends ND4JBaseTensorBackend

NativeND4J CUDA (GPU) Tensor backend.

Since:

1.0

Author:

Silvere Martin-Michiellot, Gemini AI (Google DeepMind)

Field Summary

Fields inherited from class ND4JBaseTensorBackend

isAvailable

Constructor Summary

Constructors

Constructor	Description
NativeND4JCUDATensorBackend()

Method Summary

Modifier and Type	Method	Description
protected boolean	checkAvailability()
protected ExecutionContext	doGetContext()
HardwareAccelerator	getAcceleratorType()	Returns the type of hardware accelerator used by this backend.
String	getDescription()	Returns a description of the backend.
String	getId()	Returns the unique identifier for this backend (e.g., "javafx", "jmol", "cuda").
String	getName()	Returns the name of this provider.
int	getPriority()	Returns the priority of this provider (higher = preferred).
boolean	supportsGPU()	Returns true if this provider supports GPU acceleration.

Methods inherited from class ND4JBaseTensorBackend

checkCommonClasses, convertShape, create, createContext, fromINDArray, isAvailable, ones, supportsParallelOps, toINDArray, zeros

Methods inherited from class Object

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

Methods inherited from interface AlgorithmProvider

description, getMetadata, score

Methods inherited from interface Backend

getAlgorithmProviders, getStatusMessage, isExplicitlyDisabled

Methods inherited from interface ComputeBackend

createBackend, getType, supportsComplexNumbers, supportsFloatingPoint

Methods inherited from interface TensorBackend

shutdown

Methods inherited from interface TensorProvider

getAlgorithmType

Constructor Details

NativeND4JCUDATensorBackend

public NativeND4JCUDATensorBackend()

Method Details

doGetContext

protected ExecutionContext doGetContext()

Specified by:

doGetContext in class ND4JBaseTensorBackend

getAcceleratorType

public HardwareAccelerator getAcceleratorType()

Description copied from interface: ComputeBackend

Returns the type of hardware accelerator used by this backend.

Returns:

the accelerator type

checkAvailability

protected boolean checkAvailability()

Specified by:

checkAvailability in class ND4JBaseTensorBackend

getId

public String getId()

Description copied from interface: Backend

Returns the unique identifier for this backend (e.g., "javafx", "jmol", "cuda").

getName

public String getName()

Description copied from interface: TensorBackend

Returns the name of this provider.

Returns:

provider name (e.g., "Native", "ND4J", "DJL")

getDescription

public String getDescription()

Description copied from interface: Backend

Returns a description of the backend.

getPriority

public int getPriority()

Description copied from interface: TensorBackend

Returns the priority of this provider (higher = preferred).

Used for automatic selection when multiple providers are available.

Returns:

priority (0-100, default native = 50)

supportsGPU

public boolean supportsGPU()

Description copied from interface: TensorBackend

Returns true if this provider supports GPU acceleration.

Specified by:

supportsGPU in interface TensorBackend

Specified by:

supportsGPU in class ND4JBaseTensorBackend

Returns:

true if GPU is available