Package apple.metalperformanceshaders

Class 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.

    • Constructor Detail

      • MPSRNNMatrixInferenceLayer

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

    • Method Detail

      • accessInstanceVariablesDirectly

        public static boolean accessInstanceVariablesDirectly()

      • allocWithZone

        public static java.lang.Object 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 java.lang.Object 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.

      • hash_static

        public static long hash_static()

      • 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.

      • 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 java.lang.Object 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: