apple.metalperformanceshaders

Class MPSRNNMatrixInferenceLayer

java.lang.Object

org.moe.natj.general.NativeObject

org.moe.natj.objc.ObjCObject

apple.NSObject

apple.metalperformanceshaders.MPSKernel

apple.metalperformanceshaders.MPSRNNMatrixInferenceLayer

All Implemented Interfaces:

NSCoding, NSCopying, NSSecureCoding, NSObject

public class MPSRNNMatrixInferenceLayer
extends MPSKernel

MPSRNNMatrixInferenceLayer [@dependency] This depends on Metal.framework

The MPSRNNMatrixInferenceLayer specifies a recurrent neural network layer for inference on MPSMatrices. Currently two types of recurrent layers are supported: ones that operate with convolutions on images: @ref MPSRNNImageInferenceLayer and one that operates on matrices: @ref MPSRNNMatrixInferenceLayer. The former can be often used to implement the latter by using 1x1-matrices, but due to image size restrictions and performance, it is advisable to use @ref MPSRNNMatrixInferenceLayer for linear recurrent layers. A MPSRNNMatrixInferenceLayer is initialized using a @ref MPSRNNLayerDescriptor, which further specifies the recurrent network layer, or an array of @ref MPSRNNLayerDescriptors, which specifies a stack of recurrent layers, that can operate in parallel a subset of the inputs in a sequence of inputs and recurrent outputs. Note that currently stacks with bidirectionally traversing encode functions do not support starting from a previous set of recurrent states, but this can be achieved quite easily by defining two separate unidirectional stacks of layers, and running the same input sequence on them separately (one forwards and one backwards) and ultimately combining the two result sequences as desired with auxiliary functions. The input and output vectors in encode calls are stored as rows of the input and output matrices and MPSRNNMatrixInferenceLayer supports matrices with decreasing number of rows: The row-indices identify the different sequences that may be of different lengths - for example if we have three sequences: ( x1, x2, x3 ), ( y1, y2, y3, y4 ) and ( z1, z2 ) of vectors xi, yi and zi, then these can be inserted together as a batch to the sequence encoding kernel by using the matrices: [@code] ( y1 ) ( y2 ) ( y3 ) ( y4 ) m1 = ( x1 ), m2 = ( x2 ), m3 = ( x3 ), m4 = ( z1 ) ( z2 ) [@endcode] If a recurrent output state is requested then it will contain the state corresponding to last inputs to each sequence and if all the intermediate states are requested (see storeAllIntermediateStates), then the shorter sequences will be propagated by copying the state of the previous output if the input vector is not present in the sequence - in the example above the output states would be: [@code] ( s_y1 ) ( s_y2 ) ( s_y3 ) ( s_y4 ) s1 = ( s_x1 ), s2 = ( s_x2 ), s3 = ( s_x3 ), s4 = ( s_x3 ) ( s_z1 ) ( s_z2 ) ( s_z2 ) ( s_z2 ) [@endcode] The mathematical operation described in the linear transformations of @ref MPSRNNSingleGateDescriptor [@ref] MPSLSTMDescriptor and @ref MPSGRUDescriptor are y^T = W x^T <=> y = x W^T, where x is the matrix containing the input vectors as rows, y is the matrix containing the output vectors as rows and W is the weight matrix.

Nested Class Summary

Nested classes/interfaces inherited from class apple.NSObject

NSObject.Function_instanceMethodForSelector_ret, NSObject.Function_methodForSelector_ret

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	MPSRNNMatrixInferenceLayer(org.moe.natj.general.Pointer peer)

Method Summary

Modifier and Type	Method and Description
boolean	_supportsSecureCoding() This property must return YES on all classes that allow secure coding.
static boolean	accessInstanceVariablesDirectly()
static MPSRNNMatrixInferenceLayer	alloc()
static MPSRNNMatrixInferenceLayer	allocWithZone(org.moe.natj.general.ptr.VoidPtr zone)
static boolean	automaticallyNotifiesObserversForKey(java.lang.String key)
long	bidirectionalCombineMode() [@property] bidirectionalCombineMode
static void	cancelPreviousPerformRequestsWithTarget(java.lang.Object aTarget)
static void	cancelPreviousPerformRequestsWithTargetSelectorObject(java.lang.Object aTarget, org.moe.natj.objc.SEL aSelector, java.lang.Object anArgument)
static NSArray<java.lang.String>	classFallbacksForKeyedArchiver()
static org.moe.natj.objc.Class	classForKeyedUnarchiver()
MPSRNNMatrixInferenceLayer	copyWithZoneDevice(org.moe.natj.general.ptr.VoidPtr zone, MTLDevice device) Make a copy of this kernel for a new device - @see MPSKernel
static java.lang.String	debugDescription_static()
static java.lang.String	description_static()
void	encodeBidirectionalSequenceToCommandBufferSourceSequenceDestinationForwardMatricesDestinationBackwardMatrices(MTLCommandBuffer commandBuffer, NSArray<? extends MPSMatrix> sourceSequence, NSArray<? extends MPSMatrix> destinationForwardMatrices, NSArray<? extends MPSMatrix> destinationBackwardMatrices) Encode an MPSRNNMatrixInferenceLayer kernel stack for an input matrix sequences into a command buffer bidirectionally.
void	encodeSequenceToCommandBufferSourceMatricesDestinationMatricesRecurrentInputStateRecurrentOutputStates(MTLCommandBuffer commandBuffer, NSArray<? extends MPSMatrix> sourceMatrices, NSArray<? extends MPSMatrix> destinationMatrices, MPSRNNRecurrentMatrixState recurrentInputState, NSMutableArray<MPSRNNRecurrentMatrixState> recurrentOutputStates)
void	encodeSequenceToCommandBufferSourceMatricesSourceOffsetsDestinationMatricesDestinationOffsetsRecurrentInputStateRecurrentOutputStates(MTLCommandBuffer commandBuffer, NSArray<? extends MPSMatrix> sourceMatrices, org.moe.natj.general.ptr.NUIntPtr sourceOffsets, NSArray<? extends MPSMatrix> destinationMatrices, org.moe.natj.general.ptr.NUIntPtr destinationOffsets, MPSRNNRecurrentMatrixState recurrentInputState, NSMutableArray<MPSRNNRecurrentMatrixState> recurrentOutputStates) Encode an MPSRNNMatrixInferenceLayer kernel (stack) for a sequence of inputs into a command buffer.
static long	hash_static()
MPSRNNMatrixInferenceLayer	init()
MPSRNNMatrixInferenceLayer	initWithCoder(NSCoder aDecoder) NS_DESIGNATED_INITIALIZER
MPSRNNMatrixInferenceLayer	initWithCoderDevice(NSCoder aDecoder, java.lang.Object device) NSSecureCoding compatability
MPSRNNMatrixInferenceLayer	initWithDevice(java.lang.Object device) Standard init with default properties per filter type
MPSRNNMatrixInferenceLayer	initWithDeviceRnnDescriptor(MTLDevice device, MPSRNNDescriptor rnnDescriptor) Initializes a linear (fully connected) RNN kernel
MPSRNNMatrixInferenceLayer	initWithDeviceRnnDescriptors(MTLDevice device, NSArray<? extends MPSRNNDescriptor> rnnDescriptors) Initializes a kernel that implements a stack of linear (fully connected) RNN layers
long	inputFeatureChannels() [@property] inputFeatureChannels
static NSObject.Function_instanceMethodForSelector_ret	instanceMethodForSelector(org.moe.natj.objc.SEL aSelector)
static NSMethodSignature	instanceMethodSignatureForSelector(org.moe.natj.objc.SEL aSelector)
static boolean	instancesRespondToSelector(org.moe.natj.objc.SEL aSelector)
static boolean	isSubclassOfClass(org.moe.natj.objc.Class aClass)
static NSSet<java.lang.String>	keyPathsForValuesAffectingValueForKey(java.lang.String key)
static MPSRNNMatrixInferenceLayer	new_objc()
long	numberOfLayers() [@property] numberOfLayers
long	outputFeatureChannels() [@property] outputFeatureChannels
boolean	recurrentOutputIsTemporary() [@property] recurrentOutputIsTemporary
static boolean	resolveClassMethod(org.moe.natj.objc.SEL sel)
static boolean	resolveInstanceMethod(org.moe.natj.objc.SEL sel)
void	setBidirectionalCombineMode(long value) [@property] bidirectionalCombineMode
void	setRecurrentOutputIsTemporary(boolean value) [@property] recurrentOutputIsTemporary
void	setStoreAllIntermediateStates(boolean value) [@property] storeAllIntermediateStates
static void	setVersion_static(long aVersion)
boolean	storeAllIntermediateStates() [@property] storeAllIntermediateStates
static org.moe.natj.objc.Class	superclass_static()
static boolean	supportsSecureCoding()
static long	version_static()

Methods inherited from class apple.metalperformanceshaders.MPSKernel

copyWithZone, device, encodeWithCoder, label, options, setLabel, setOptions

Methods inherited from class apple.NSObject

accessibilityActivate, accessibilityActivationPoint, accessibilityAssistiveTechnologyFocusedIdentifiers, accessibilityAttributedHint, accessibilityAttributedLabel, accessibilityAttributedUserInputLabels, accessibilityAttributedValue, accessibilityContainerType, accessibilityCustomActions, accessibilityCustomRotors, accessibilityDecrement, accessibilityDragSourceDescriptors, accessibilityDropPointDescriptors, accessibilityElementAtIndex, accessibilityElementCount, accessibilityElementDidBecomeFocused, accessibilityElementDidLoseFocus, accessibilityElementIsFocused, accessibilityElements, accessibilityElementsHidden, accessibilityFrame, accessibilityHint, accessibilityIncrement, accessibilityLabel, accessibilityLanguage, accessibilityNavigationStyle, accessibilityPath, accessibilityPerformEscape, accessibilityPerformMagicTap, accessibilityRespondsToUserInteraction, accessibilityScroll, accessibilityTextualContext, accessibilityTraits, accessibilityUserInputLabels, accessibilityValue, accessibilityViewIsModal, addObserverForKeyPathOptionsContext, attemptRecoveryFromErrorOptionIndex, attemptRecoveryFromErrorOptionIndexDelegateDidRecoverSelectorContextInfo, autoContentAccessingProxy, awakeAfterUsingCoder, awakeFromNib, class_objc, classForCoder, classForKeyedArchiver, copy, dealloc, debugDescription, description, dictionaryWithValuesForKeys, didChangeValueForKey, didChangeValueForKeyWithSetMutationUsingObjects, didChangeValuesAtIndexesForKey, doesNotRecognizeSelector, fileManagerShouldProceedAfterError, fileManagerWillProcessPath, finalize_objc, forwardingTargetForSelector, forwardInvocation, hash, indexOfAccessibilityElement, isAccessibilityElement, isEqual, isKindOfClass, isMemberOfClass, isProxy, methodForSelector, methodSignatureForSelector, mutableArrayValueForKey, mutableArrayValueForKeyPath, mutableCopy, mutableOrderedSetValueForKey, mutableOrderedSetValueForKeyPath, mutableSetValueForKey, mutableSetValueForKeyPath, observationInfo, observeValueForKeyPathOfObjectChangeContext, performSelector, performSelectorInBackgroundWithObject, performSelectorOnMainThreadWithObjectWaitUntilDone, performSelectorOnMainThreadWithObjectWaitUntilDoneModes, performSelectorOnThreadWithObjectWaitUntilDone, performSelectorOnThreadWithObjectWaitUntilDoneModes, performSelectorWithObject, performSelectorWithObjectAfterDelay, performSelectorWithObjectAfterDelayInModes, performSelectorWithObjectWithObject, prepareForInterfaceBuilder, provideImageDataBytesPerRowOrigin_Size_UserInfo, removeObserverForKeyPath, removeObserverForKeyPathContext, replacementObjectForCoder, replacementObjectForKeyedArchiver, respondsToSelector, self, setAccessibilityActivationPoint, setAccessibilityAttributedHint, setAccessibilityAttributedLabel, setAccessibilityAttributedUserInputLabels, setAccessibilityAttributedValue, setAccessibilityContainerType, setAccessibilityCustomActions, setAccessibilityCustomRotors, setAccessibilityDragSourceDescriptors, setAccessibilityDropPointDescriptors, setAccessibilityElements, setAccessibilityElementsHidden, setAccessibilityFrame, setAccessibilityHint, setAccessibilityLabel, setAccessibilityLanguage, setAccessibilityNavigationStyle, setAccessibilityPath, setAccessibilityRespondsToUserInteraction, setAccessibilityTextualContext, setAccessibilityTraits, setAccessibilityUserInputLabels, setAccessibilityValue, setAccessibilityViewIsModal, setIsAccessibilityElement, setNilValueForKey, setObservationInfo, setShouldGroupAccessibilityChildren, setValueForKey, setValueForKeyPath, setValueForUndefinedKey, setValuesForKeysWithDictionary, shouldGroupAccessibilityChildren, superclass, validateValueForKeyError, validateValueForKeyPathError, valueForKey, valueForKeyPath, valueForUndefinedKey, willChangeValueForKey, willChangeValueForKeyWithSetMutationUsingObjects, willChangeValuesAtIndexesForKey

Methods inherited from class org.moe.natj.objc.ObjCObject

equals, toString

Methods inherited from class org.moe.natj.general.NativeObject

finalize, getPeer, getPeerPointer

Methods inherited from class java.lang.Object

clone, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

MPSRNNMatrixInferenceLayer

protected MPSRNNMatrixInferenceLayer(org.moe.natj.general.Pointer peer)

Method Detail

accessInstanceVariablesDirectly

public static boolean accessInstanceVariablesDirectly()

alloc

public static MPSRNNMatrixInferenceLayer alloc()

allocWithZone

public static MPSRNNMatrixInferenceLayer allocWithZone(org.moe.natj.general.ptr.VoidPtr zone)

automaticallyNotifiesObserversForKey

public static boolean automaticallyNotifiesObserversForKey(java.lang.String key)

bidirectionalCombineMode

public long bidirectionalCombineMode()

[@property] bidirectionalCombineMode

Defines how to combine the output-results, when encoding bidirectional layers using [@ref] encodeBidirectionalSequenceToCommandBuffer. Defaults to @ref MPSRNNBidirectionalCombineModeNone.

cancelPreviousPerformRequestsWithTarget

public static void cancelPreviousPerformRequestsWithTarget(java.lang.Object aTarget)

cancelPreviousPerformRequestsWithTargetSelectorObject

public static void cancelPreviousPerformRequestsWithTargetSelectorObject(java.lang.Object aTarget,
                                                                         org.moe.natj.objc.SEL aSelector,
                                                                         java.lang.Object anArgument)

classFallbacksForKeyedArchiver

public static NSArray<java.lang.String> classFallbacksForKeyedArchiver()

classForKeyedUnarchiver

public static org.moe.natj.objc.Class classForKeyedUnarchiver()

copyWithZoneDevice

public MPSRNNMatrixInferenceLayer copyWithZoneDevice(org.moe.natj.general.ptr.VoidPtr zone,
                                                     MTLDevice device)

Make a copy of this kernel for a new device - @see MPSKernel

Overrides:

copyWithZoneDevice in class MPSKernel

Parameters:

zone - The NSZone in which to allocate the object

device - The device for the new MPSKernel. If nil, then use self.device.

Returns:

a pointer to a copy of this MPSKernel. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later.

debugDescription_static

public static java.lang.String debugDescription_static()

description_static

public static java.lang.String description_static()

encodeBidirectionalSequenceToCommandBufferSourceSequenceDestinationForwardMatricesDestinationBackwardMatrices

public void encodeBidirectionalSequenceToCommandBufferSourceSequenceDestinationForwardMatricesDestinationBackwardMatrices(MTLCommandBuffer commandBuffer,
                                                                                                                          NSArray<? extends MPSMatrix> sourceSequence,
                                                                                                                          NSArray<? extends MPSMatrix> destinationForwardMatrices,
                                                                                                                          NSArray<? extends MPSMatrix> destinationBackwardMatrices)

Encode an MPSRNNMatrixInferenceLayer kernel stack for an input matrix sequences into a command buffer bidirectionally. The operation proceeds as follows: The first source matrix x0 is passed through all forward traversing layers in the stack, ie. those that were initialized with MPSRNNSequenceDirectionForward, recurrent input is assumed zero. This produces forward output yf0 and recurrent states hf00, hf01, hf02, ... hf0n, one for each forward layer in the stack. Then x1 is passed to forward layers together with recurrent state hf00, hf01, ..., hf0n, which produces yf1, and hf10,... This procedure is iterated until the last matrix in the input sequence x_(N-1), which produces forward output yf(N-1). The backwards layers iterate the same sequence backwards, starting from input x_(N-1) (recurrent state zero), that produces yb(N-1) and recurrent output hb(N-1)0, hf(N-1)1, ... hb(N-1)m, one for each backwards traversing layer. Then the backwards layers handle input x_(N-2) using recurrent state hb(N-1)0, ..., et cetera, until the first matrix of the sequence is computed, producing output yb0. The result of the operation is either pair of sequences ({yf0, yf1, ... , yf(N-1)}, {yb0, yb1, ... , yb(N-1)}) or a combined sequence, {(yf0 + yb0), ... , (yf(N-1) + yb(N-1)) }, where '+' stands either for sum, or concatenation along feature channels, as specified by @ref bidirectionalCombineMode.

Parameters:

commandBuffer - A valid MTLCommandBuffer to receive the encoded filter

sourceSequence - An array of valid MPSMatrix objects containing the source matrix sequence (x0, x1, ... x_n-1).

destinationForwardMatrices - An array of valid MPSMatrices to be overwritten by result from forward input matrices. If bidirectionalCombineMode is either MPSRNNBidirectionalCombineModeAdd or MPSRNNBidirectionalCombineModeConcatenate, then will contain the combined results. destinationForwardMatrix may not alias with any of the source matrices.

destinationBackwardMatrices - If bidirectionalCombineMode is MPSRNNBidirectionalCombineModeNone, then must be an array of valid MPSMatrices that will be overwritten by result from backward input matrices. Otherwise this parameter is ignored and can be nil. destinationBackwardMatrices may not alias to any of the source matrices.

encodeSequenceToCommandBufferSourceMatricesDestinationMatricesRecurrentInputStateRecurrentOutputStates

public void encodeSequenceToCommandBufferSourceMatricesDestinationMatricesRecurrentInputStateRecurrentOutputStates(MTLCommandBuffer commandBuffer,
                                                                                                                   NSArray<? extends MPSMatrix> sourceMatrices,
                                                                                                                   NSArray<? extends MPSMatrix> destinationMatrices,
                                                                                                                   MPSRNNRecurrentMatrixState recurrentInputState,
                                                                                                                   NSMutableArray<MPSRNNRecurrentMatrixState> recurrentOutputStates)

hash_static

public static long hash_static()

init

public MPSRNNMatrixInferenceLayer init()

Overrides:

init in class MPSKernel

initWithCoder

public MPSRNNMatrixInferenceLayer initWithCoder(NSCoder aDecoder)

Description copied from interface: NSCoding

NS_DESIGNATED_INITIALIZER

Specified by:

initWithCoder in interface NSCoding

Overrides:

initWithCoder in class MPSKernel

initWithCoderDevice

public MPSRNNMatrixInferenceLayer initWithCoderDevice(NSCoder aDecoder,
                                                      java.lang.Object device)

NSSecureCoding compatability

See @ref MPSKernel#initWithCoder.

Overrides:

initWithCoderDevice in class MPSKernel

Parameters:

aDecoder - The NSCoder subclass with your serialized MPSRNNMatrixInferenceLayer

device - The MTLDevice on which to make the MPSRNNMatrixInferenceLayer

Returns:

A new MPSRNNMatrixInferenceLayer object, or nil if failure.

initWithDevice

public MPSRNNMatrixInferenceLayer initWithDevice(java.lang.Object device)

Description copied from class: MPSKernel

Standard init with default properties per filter type

Overrides:

initWithDevice in class MPSKernel

Parameters:

device - The device that the filter will be used on. May not be NULL.

Returns:

a pointer to the newly initialized object. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later.

initWithDeviceRnnDescriptor

public MPSRNNMatrixInferenceLayer initWithDeviceRnnDescriptor(MTLDevice device,
                                                              MPSRNNDescriptor rnnDescriptor)

Initializes a linear (fully connected) RNN kernel

Parameters:

device - The MTLDevice on which this MPSRNNMatrixLayer filter will be used

rnnDescriptor - The descriptor that defines the RNN layer

Returns:

A valid MPSRNNMatrixInferenceLayer object or nil, if failure.

initWithDeviceRnnDescriptors

public MPSRNNMatrixInferenceLayer initWithDeviceRnnDescriptors(MTLDevice device,
                                                               NSArray<? extends MPSRNNDescriptor> rnnDescriptors)

Initializes a kernel that implements a stack of linear (fully connected) RNN layers

Parameters:

device - The MTLDevice on which this MPSRNNMatrixLayer filter will be used

rnnDescriptors - An array of RNN descriptors that defines a stack of RNN layers, starting at index zero. The number of layers in stack is the number of entries in the array. All entries in the array must be valid MPSRNNDescriptors.

Returns:

A valid MPSRNNMatrixInferenceLayer object or nil, if failure.

inputFeatureChannels

public long inputFeatureChannels()

[@property] inputFeatureChannels

The number of feature channels input vector/matrix.

instanceMethodForSelector

public static NSObject.Function_instanceMethodForSelector_ret instanceMethodForSelector(org.moe.natj.objc.SEL aSelector)

instanceMethodSignatureForSelector

public static NSMethodSignature instanceMethodSignatureForSelector(org.moe.natj.objc.SEL aSelector)

instancesRespondToSelector

public static boolean instancesRespondToSelector(org.moe.natj.objc.SEL aSelector)

isSubclassOfClass

public static boolean isSubclassOfClass(org.moe.natj.objc.Class aClass)

keyPathsForValuesAffectingValueForKey

public static NSSet<java.lang.String> keyPathsForValuesAffectingValueForKey(java.lang.String key)

new_objc

public static MPSRNNMatrixInferenceLayer new_objc()

numberOfLayers

public long numberOfLayers()

[@property] numberOfLayers

Number of layers in the filter-stack. This will be one when using initWithDevice:rnnDescriptor to initialize this filter and the number of entries in the array 'rnnDescriptors' when initializing this filter with initWithDevice:rnnDescriptors.

outputFeatureChannels

public long outputFeatureChannels()

[@property] outputFeatureChannels

The number of feature channels in the output vector/matrix.

recurrentOutputIsTemporary

public boolean recurrentOutputIsTemporary()

[@property] recurrentOutputIsTemporary

How output states from @ref encodeSequenceToCommandBuffer are constructed. Defaults to NO. For reference @see MPSState.

resolveClassMethod

public static boolean resolveClassMethod(org.moe.natj.objc.SEL sel)

resolveInstanceMethod

public static boolean resolveInstanceMethod(org.moe.natj.objc.SEL sel)

setBidirectionalCombineMode

public void setBidirectionalCombineMode(long value)

[@property] bidirectionalCombineMode

Defines how to combine the output-results, when encoding bidirectional layers using [@ref] encodeBidirectionalSequenceToCommandBuffer. Defaults to @ref MPSRNNBidirectionalCombineModeNone.

setRecurrentOutputIsTemporary

public void setRecurrentOutputIsTemporary(boolean value)

[@property] recurrentOutputIsTemporary

How output states from @ref encodeSequenceToCommandBuffer are constructed. Defaults to NO. For reference @see MPSState.

setStoreAllIntermediateStates

public void setStoreAllIntermediateStates(boolean value)

[@property] storeAllIntermediateStates

If YES then calls to @ref encodeSequenceToCommandBuffer return every recurrent state in the array: recurrentOutputStates. Defaults to NO.

setVersion_static

public static void setVersion_static(long aVersion)

storeAllIntermediateStates

public boolean storeAllIntermediateStates()

[@property] storeAllIntermediateStates

If YES then calls to @ref encodeSequenceToCommandBuffer return every recurrent state in the array: recurrentOutputStates. Defaults to NO.

superclass_static

public static org.moe.natj.objc.Class superclass_static()

supportsSecureCoding

public static boolean supportsSecureCoding()

_supportsSecureCoding

public boolean _supportsSecureCoding()

Description copied from interface: NSSecureCoding

This property must return YES on all classes that allow secure coding. Subclasses of classes that adopt NSSecureCoding and override initWithCoder: must also override this method and return YES. The Secure Coding Guide should be consulted when writing methods that decode data.

Specified by:

_supportsSecureCoding in interface NSSecureCoding

Overrides:

_supportsSecureCoding in class MPSKernel

version_static

public static long version_static()

encodeSequenceToCommandBufferSourceMatricesSourceOffsetsDestinationMatricesDestinationOffsetsRecurrentInputStateRecurrentOutputStates

public void encodeSequenceToCommandBufferSourceMatricesSourceOffsetsDestinationMatricesDestinationOffsetsRecurrentInputStateRecurrentOutputStates(MTLCommandBuffer commandBuffer,
                                                                                                                                                  NSArray<? extends MPSMatrix> sourceMatrices,
                                                                                                                                                  org.moe.natj.general.ptr.NUIntPtr sourceOffsets,
                                                                                                                                                  NSArray<? extends MPSMatrix> destinationMatrices,
                                                                                                                                                  org.moe.natj.general.ptr.NUIntPtr destinationOffsets,
                                                                                                                                                  MPSRNNRecurrentMatrixState recurrentInputState,
                                                                                                                                                  NSMutableArray<MPSRNNRecurrentMatrixState> recurrentOutputStates)

Encode an MPSRNNMatrixInferenceLayer kernel (stack) for a sequence of inputs into a command buffer. Note that when encoding using this function the @see layerSequenceDirection is ignored and the layer stack operates as if all layers were forward feeding layers. In order to run bidirectional sequences use @ref encodeBidirectionalSequenceToCommandBuffer:sourceSequence: or alternatively run two layer stacks and combine results at the end using utility functions. [@code] MPSRNNRecurrentMatrixState* recurrent0 = nil; [filter encodeToCommandBuffer: cmdBuf sourceMatrix: source0 destinationMatrix: destination0 recurrentInputState: nil recurrentOutputState: &recurrent0]; [@endcode] Then use it for the next input in sequence: [@code] [filter encodeToCommandBuffer: cmdBuf sourceMatrix: source1 destinationMatrix: destination1 recurrentInputState: recurrent0 recurrentOutputState: &recurrent0]; [@endcode] And discard recurrent output of the third input: [@code] [filter encodeToCommandBuffer: cmdBuf sourceMatrix: source2 destinationMatrix: destination2 recurrentInputState: recurrent0 recurrentOutputState: nil]; [@endcode]

Parameters:

commandBuffer - A valid MTLCommandBuffer to receive the encoded filter

sourceMatrices - An array of valid MPSMatrix objects containing the sequence of source matrices.

sourceOffsets - An array of byte-offsets into the sourceMatrices, if nil zeros are assumed and if not nil must contain offset for every matrix in sourceMatrices.

destinationMatrices - An array valid MPSMatrices to be overwritten by result matrix sequence. destinationMatrices may not alias sourceMatrices.

destinationOffsets - An array of byte-offsets into the destinationMatrices, if nil zeros are assumed and if not nil must contain offset for every matrix in destinationMatrices.

recurrentInputState - An optional state containing the output matrices and memory cells (for LSTMs) of the layer obtained from the previous input matrices in a sequence of inputs. Has to be the output of a previous call to this function or nil (assumed zero). Note: can be one of the states returned in @ref intermediateRecurrentStates.

recurrentOutputStates - An optional array that will contain the recurrent output states. If nil then the recurrent output state is discarded. If @ref storeAllIntermediateStates is YES, then all intermediate states of the sequence are returned in the array, the first one corresponding to the first input in the sequence, otherwise only the last recurrent output state is returned. If recurrentOutputIsTemporary is YES and then all returned recurrent states will be temporary. @see MPSState:isTemporary. Example: In order to get a new state one can do the following: