Classifications

• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/08—Learning methods
  • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
  • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/044—Recurrent networks, e.g. Hopfield networks
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/045—Combinations of networks
• • G—PHYSICS
  • G06—COMPUTING; CALCULATING OR COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N3/00—Computing arrangements based on biological models
  • G06N3/02—Neural networks
  • G06N3/04—Architecture, e.g. interconnection topology
  • G06N3/048—Activation functions

Definitions

• the present disclosure relates generally to data processing and, more particularly, to system and method for realigning streams of neuron outputs in artificial neural network computations.
• ANNs Artificial Neural Networks
• the human brain contains 10-20 billion neurons connected through synapses. Electrical and chemical messages are passed from neurons to neurons based on input information and their resistance to passing information.
• a neuron can be represented by a node performing a simple operation of addition coupled with a saturation function.
• a synapse can be represented by a connection between two nodes. Each of the connections can be associated with an operation of multiplication by a constant.
• the ANNs are particularly useful for solving problems that cannot be easily solved by classical computer programs.
• forms of the ANNs may vary, they all have the same basic elements similar to the human brain.
• a typical ANN can be organized into layers, each of the layers may include many neurons sharing similar functionality.
• the inputs of a layer may come from a previous layer, multiple previous layers, any other layers or even the layer itself.
• Major architectures of ANNs include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Term Short Memory (LTSM) network, but other architectures of ANN can be developed for specific applications. While some operations have a natural sequence, for example a layer depending on previous layers, most of the operations can be carried out in parallel within the same layer. The ANNs can then be computed in parallel on many different computing elements similar to neurons of the brain.
• a single ANN may have hundreds of layers. Each of the layers can involve millions of connections. Thus, a single ANN may potentially require billions of simple operations like multiplications and additions.
• ANNs can result in a very heavy load for processing units (e.g., CPU), even ones running at high rates.
• processing units e.g., CPU
• GPUs graphics processing units
• GPUs can be used to process large ANNs because GPUs have a much higher throughput capacity of operations in comparison to CPUs. Because this approach solves, at least partially, the throughput limitation problem, GPUs appear to be more efficient in the computations of ANNs than the CPUs.
• GPUs are not well suited to the computations of ANNs because the GPUs have been specifically designed to compute graphical images.
• the GPUs may provide a certain level of parallelism in computations.
• the GPUs are constraining the computations in long pipes implying latency and lack of reactivity.
• very large GPUs can be used which may involving excessive power consumption, a typical issue of GPUs. Since the GPUs may require more power consumptions for the computations of ANNs, the deployment of GPUs can be difficult.
• CPUs provide a very generic engine that can execute very few sequences of instructions with a minimum effort in terms of programming, but lack the power of computing for ANN.
• GPUs are slightly more parallel and require a larger effort of programming than CPUs, which can be hidden behind libraries with some performance costs, but are not very well suitable for ANNs.
• FPGAs Field Programmable Gate Arrays
• the FPGAs can be configured to perform computations in parallel. Therefore, FPGAs can be well suited to compute ANNs.
• One of the challenges of FPGAs is the programming, which requires a much larger effort than programming CPUs and GPUs. Adaption of FPGAs to perform ANN computations can be more challenging than for CPUs and GPUs.
• a system for realigning streams of neuron outputs can include a processing unit, at least one further processing unit, and a synchronization module communicatively coupled to the processing unit and the further processing unit.
• the processing unit can be configured to generate neuron outputs including at least a first neuron output and a second neuron output.
• the further processing unit can be configured to generate further neuron outputs including at least a further first neuron output and a further second neuron output.
• the synchronization module can be configured to receive the neuron outputs from the processing unit and to receive the further neuron outputs from the further processing unit, wherein the neuron outputs and the further neuron outputs are received in an arbitrary order.
• the synchronization module can order the first neuron output, the further first neuron output, the second neuron output, and the further second neuron output. The ordering can be different from the order of receiving the neuron outputs and the further neuron outputs.
• the first neuron output and the further first neuron output can be ordered prior to the second neuron output and the further second neuron output.
• the synchronization module can be further configured to write an ordered sequence to a memory storage, wherein the ordered sequence includes the first neuron output, the further first neuron output, the second neuron output, and the further second neuron output ordered according to the further order.
• the ordered sequence can be used as further input values for further neurons.
• a count of the neuron outputs can differ from a count of the further neuron outputs.
• the processing unit can be configured to provide, to the synchronization module, an indication of the last neuron output of the neuron outputs.
• the further processing unit can be configured to provide, to the synchronization module, a further indication of the last further neuron output of the further neuron outputs.
• the synchronization module can be configured, upon receiving the indication and the further indication, to stand by ready for receiving next set of neuron outputs from the processing unit and further next set of further neuron outputs from the further processing unit.
• a time of the indication can differ from a time of the further indication.
• the processing unit can be configured to receive input values and offsets.
• the processing unit can select, based on the received offsets, weight values from a set of weights.
• the processing unit can also perform arithmetic operations on the received input values and the selected weight values to generate at least one neuron output of the neuron outputs.
• a count of the input values used in the arithmetic operations for generating the neuron outputs can be different from a count of the weight values selected for performing the arithmetic operations.
• the further processing unit can be configured to receive further input values and further offsets.
• the further processing unit can select, based on received further offsets, further weights values from a further set of weights.
• the further processing unit can perform further arithmetic operations on the further input values and the selected further weight values to generate at least one further neuron of the further neurons.
• the further offsets can differ from the offsets.
• the processing unit, the further processing unit, and the synchronization module can be carried out on an electronic circuit.
• a method for realigning streams of neuron outputs may include generating, by a processing unit, neuron outputs including at least a first neuron output and a second neuron output.
• the method may include generating, by at least one further processing unit, further neuron outputs including at least a further first neuron output and a further second neuron output.
• the method may include, receiving, by a synchronization module communicatively coupled to the processing unit and the further processing unit, the neuron outputs from the processing unit and the further neuron outputs from the further processing unit. Reception of the neuron outputs and reception of the further neuron outputs can be carried out in an arbitrary order.
• the method may include ordering, by the synchronization module, the first neuron output, the further first neuron output, the second neuron output and the further second neuron output according to a further order, the further order being different from the order of the receiving the neuron outputs and the further neuron outputs.
• FIG. 1 is a block diagram showing an example system wherein a method for realigning streams of neuron outputs in ANN computations can be implemented, according to some example embodiments.
• FIG. 2 shows an ANN, neuron, and transfer function, according to an example embodiment.
• FIG. 3 is a flow chart showing training and inference of ANN, according to some example embodiments.
• FIG. 4 is a block diagram showing a system for acceleration of ANN computations, according to some example embodiments.
• FIG. 5 is a block diagram showing a system for selecting input values for processing by ANN computations, according to an example embodiment.
• FIG. 6 is a block diagram showing a system for selecting input data for processing by ANN computations, according to another example embodiment.
• FIG. 7 is a block diagram showing a system for realigning of outputs of neurons in ANN computations, according to another example embodiment.
• FIG. 8 is a flow chart showing steps of a method for acceleration of ANN computations, according to some example embodiments.
• FIG. 9 shows a computing system that can be used to implement
• FIG. 10 is a flow chart showing steps of a method for realigning streams of neuron outputs in ANN computations, according to some example embodiments.
• Embodiments of this disclosure are concerned with methods and systems for realigning streams of neuron outputs in ANN computations.
• Embodiments of present disclosure may facilitate selection of input values for processing by neurons of an ANN in order to avoid unnecessary mathematical operations in computation of outputs of neurons and, thereby, accelerating of computations of the ANN.
• the input values equal to zero are not processed by arithmetic units configured to compute the neurons of ANN.
• the selection of input values can be also based on another criterion.
• the sequence of operations performed by the arithmetic units may depend dynamically on the stream of input values and the criterion used for selection.
• a select-all (no selection) criterion would result in an identical sequence of operations for all inputs, wherein essentially all operations of the neurons (and ANN) are performed.
• the computation of ANN will be similar to ANN computations in existing solutions which do not expose a dynamic behavior.
• Embodiments of the present disclosure may further allow realigning streams of neuron outputs generated by different arithmetic units if neuron outputs are unaligned.
• the streams can be unaligned due to differences in selection of input values to be processed by the arithmetic units for computing neuron outputs.
• module shall be construed to mean a hardware device, software, or a combination of both.
• a hardware-based module can use one or more microprocessors, FPGAs, application-specific integrated circuits (ASICs), programmable logic devices, transistor-based circuits, or various combinations thereof.
• Software-based modules can constitute computer programs, computer program procedures, computer program functions, and the like.
• a module of a system can be implemented by a computer or server, or by multiple computers or servers interconnected into a network.
• module may also refer to a subpart of a computer system, a hardware device, an integrated circuit, or a computer program.
• Technical effects of certain embodiments of the present disclosure can include configuring integrated circuits, FPGAs, or computer systems to perform ANN computations without execution of redundant and unnecessary mathematical operations, thereby accelerating the ANN computations. Further technical effects of some embodiments of the present disclosure can facilitate configuration of integrated circuits, FPGAs, or computer systems to dynamically qualify data on which
• FIG. 1 is a block diagram showing an example system 100, wherein a method for realigning streams of neuron outputs in ANN computations can be implemented, according to some example embodiments.
• the system 100 can be part of a computing system, such as a personal computer, a server, a cloud-based computing recourse, and the like.
• the system 100 may include one or more FPGA boards 105 and a chipset 135 including a least one CPU.
• the chipset 135 can be communicatively connected to the FPGA boards 105 via a communication interface.
• the communication interface may include a Peripheral Component Interconnect Express (PCIE) standard 130.
• the communication interface may also include an Ethernet connection 131.
• PCIE Peripheral Component Interconnect Express
• the FPGA board 105 may include an FPGA 115, a volatile memory 110, and a non-volatile memory 120.
• the volatile memory 110 may include a double data rate synchronous dynamic random-access memory (DDR SDRAM), High Bandwidth Memory (HBM), or any other type of memory.
• the volatile memory 110 may include the host memory.
• the non-volatile memory 120 may include Electrically Erasable Programmable Read-Only Memory (EEROM), a solid-state drive (SSD), a flash memory, and so forth.
• EEROM Electrically Erasable Programmable Read-Only Memory
• SSD solid-state drive
• flash memory and so forth.
• the FPGA 115 can include blocks.
• the blocks may include a set of elementary nodes (also referred to as gates) performing basic hardware operations, such as Boolean operations.
• the blocks may further include registers retaining bit information, one or more memory storage of different sizes, and one or more digital signal processors (DSPs) to perform arithmetic computations, for example, additions and multiplications.
• DSPs digital signal processors
• Programming of FPGA 115 may include configuring each of the blocks to have an expected behavior and connecting the blocks by routing information between the blocks.
• FPGA 115 Programming of FPGA 115 can be carried out using a result from a compiler taking as input schematic description, gate-level description, hardware languages like Verilog, System Verilog, or Very High Speed Integrated Circuit Hardware Description Fanguage (VHDF), or any combination of thereof.
• VHDF Very High Speed Integrated Circuit Hardware Description Fanguage
• the non-volatile memory 120 may be configured to store instructions in a form of bit file 125 to be executed by the FPGA 115.
• the FPGA 115 can be configured by the instructions to perform one or more floating point operations including
• the volatile memory 110 may be configured to store weights W[i] for neurons of one or more ANNs, input values V[i] to be processed for the ANNs, and results of ANNs computation including any intermediate results of computations of layers of the ANNs.
• FIG. 2 shows ANN 210, neuron 220, and transfer function 230, according to some example embodiments.
• the ANN 210 may include one or more input layers 240, one or more hidden layers 250, and one or more output layers 260.
• Each of the input layers, hidden layers, and output layers may include one or more (artificial) neurons 220. The number of neurons can be different for different layers.
• Each of neurons 220 may represent a calculation of a mathematical function
• V[i] are neuron input values
• W[i] are weights assigned to input values at neuron
• F(X) is a transfer function.
• the transfer function 230 F(X) is selected to be zero for X ⁇ 0 and have a limit of zero as X approaches zero.
• the transfer function F(X) can be in the form of a sigmoid. The result of calculation of a neuron propagates as an input value of further neurons in the ANN.
• the further neurons can belong to either a next layer, a previous layer or the same layer.
• ANN 210 illustrated in FIG. 2 can be referred to as a feedforward neural network
• embodiments of the present disclosure can be also used in computations of convolution neural networks, recurrent neural networks, long short-term memory networks, and other types of ANNs.
• FIG. 3 is a flow chart showing training 310 and inference 325 of an ANN, according to some example embodiments.
• the training 310 (also known as learning) is a process of teaching ANN 305 to output a proper result based on a given set of training data 315.
• the process of training may include determining weights 320 of neurons of the ANN 305 based on training data 315.
• the training data 315 may include samples. Each of the samples may be represented as a pair of input values and an expected output.
• the training data 315 may include hundreds to millions of samples. While the training 310 is required to be performed only once, it may require a significant amount of computations and take a considerable time.
• the ANNs can be configured to solve different tasks including, for example, image recognition, speech recognition, handwriting recognition, machine translation, social network filtering, video games, medical diagnosis, and so forth.
• the inference 325 is a process of computation of an ANN.
• the inference 325 uses the trained ANN weights 320 and new data 330 including new sets of input values. For each new set of input values, the computation of the ANN provides a new output which answer the problem that the ANN is supposed to solve.
• an ANN can be trained to recognize various animals in images.
• the ANN can be trained on millions of images of animals. Submitting a new image to the ANN would provide the information for animals in the new image (this process being known as image tagging). While the inference for each image takes less computations than training, number of inferences can be large because new images can be received from billions of sources.
• the inference 325 includes multiple computations of sum of products:
• V[i] are new input values and W[i] are weights associated with neurons of ANN.
• Some previous approaches for performing inference include inspection of the weights W[i] and replacing some of the weights W[i] with zero values if a value of the weight is relatively small when compared to other weights of the ANN. In FIG. 3, this process is shown as pruning 335.
• the pruning 335 generates new weights 340 that then can be used in inference 325 instead of the weights 320.
• Advantage of these approaches is that replacing the weights with zero values may allow decreasing the number of computations of the ANN, since multiplications by zero can be avoided in computations.
• the disadvantage of these approaches is that the ANN can become less accurate in producing a correct output due to lack of correspondence between the new weights 340 and training data 315 used in training of ANN.
• Another disadvantage of these approaches is that the pruning of weights is not based on new input values and allow only to avoid operations with weights equal to zero.
• the weights 310 may remain unchanged in inference 325, while
• Multiplications V[i ⁇ x W[i] are not carried out if a determined criterion is satisfied with respect to input value V[i]. For example, multiplication V[i ⁇ x W[i] can be skipped if the input value V[i] is substantially zero.
• the criterion used to select the operations to be done may be different from a comparison to zero and, thereby, allowing to avoid other operations dynamically based on the input values V[i] and other values, for example, static values including weights.
• embodiments of present disclosure allow dynamic selection of operations to be performed.
• FIG. 4 is a block diagram showing a system 400 for accelerating ANN computation, according to some example embodiments.
• the system 400 may include one or more processing unit(s) 450.
• Each of the processing unit(s) 450 may include an arithmetic unit 425, a controller 415, and a selector 420.
• the processing unit(s) 450 may receive a set of X input values ⁇ T[i 0 ], Tfi , , TfG ⁇ of data 405.
• the processing unit(s) 450 may receive a set of weights 410 ( ⁇ tr[i 0 ], I/Ffi ,
• the processing unit(s) 450 may receive further input values 406 which are different from the input values 405.
• the further input values 406 can be related to the neuron, the layer, the ANN, the weights, or the operation to be carried.
• the controller 415 may receive a set ⁇ T[i 0 ], Tfi , T ⁇ N-i ] ⁇ of X input values of data 405.
• the controller 415 may optionally receive further input values 406.
• the controller 415 may provide, based on the input values 405 and the further values 406, an indication to the selector 420 as to which of the X input values are to be selected in the stream.
• the controller 415 may also provide, to the arithmetic unit 425, an offset or an index or bit enables of one or multiple selected value(s) in the set
• the controller 415 may receive a signal 730 indicating the last input value in the set ⁇ T[i 0 Tfh], ... , V[i x® ] ⁇ .
• FIG. 5 is a block diagram showing a controller 415, according to some example embodiments.
• the controller 415 can compare the input values to reference value(s) (ref).
• the reference value(s) can be included in the further values 406. In some embodiments, the controller 415 may not use the further values 406. In some embodiments, the reference value(s) can be equal to zero.
• the controller 415 may provide the selector 420 with one or more index(es) of the input value to be selected. In other embodiments, the controller 415 can perform a selection of an input value based on different criteria. In some embodiments, one or multiple input values 405 and multiple further values 406 can be used for the selection. In certain
• other selection operations could be done involving one or multiple X input values 405 or one or multiple further values 406.
• the input value may be selected if the input value is less than a threshold.
• the selector 420 may receive the set of input values ⁇ T[i 0 ], V[h]’ y[i x-i ] ⁇ and the indication from the controller 415 as to which of the input values to select.
• the selector 420 may select a value V[i] and provide the selected input value V[i] to the arithmetic unit 425.
• the information of the selected input value may be represented in any form.
• the controller 415 and the selector 420 may be carried out as a single unit configured to perform functionalities of both controller 415 and selector 420.
• the selector 420 can be also configured to select weights 410 based on indications from the controller 415.
• the arithmetic unit 425 can be configured to compute sums, multiplications, accumulations, or other operations.
• the arithmetic unit 425 may receive the selected value V[i] from the selector 420 and the offset of index of selected value V[i] from the controller 415.
• the arithmetic unit 425 may be further configured to select, based on the offset, a weight W[i] corresponding to value V[i].
• the arithmetic unit 425 may further determine product V[i] x W[i] and add the product to corresponding sum. Because the multiplication is performed only for selected values of data and selected weights, the computation of sum, and hence computation of the ANN, can be accelerated.
• the arithmetic unit 425 can determine products V[j]xW[k], wherein j and k are determined based on the input values 405, further input values 406, and the weights 410 specified by the controller 415. In some embodiments, the arithmetic unit 425 can perform further mathematical operations different from products and sums, independently, prior to, or after performing the products or sums.
• FIG. 6 is a block diagram showing a system 600 for selecting input values to be processed in an ANN computation, according to another example embodiment.
• the system may include a controller 415, an arithmetic unit 425, and a memory 610.
• the memory 610 can be configured to store a set of X input values ⁇ T[i 0 ], hfi , ... k[i x-1 ] ⁇ .
• the controller 415 can be configured to determine an address of an input value to be selected for multiplication in arithmetic unit 425.
• the arithmetic unit 425 may read the selected input value based on the address received from the controller 415.
• FIG. 7 is a block diagram showing a system 700 for realigning of results of parallel calculations of neurons in the ANN, according to an example embodiment.
• the input values 405-i may be different from each other.
• the weights 410-i may be related to each other and can be associated with the same set of input values.
• input values 405-0 and input values 420-1 may include equal numbers of input values.
• the number and indexes of input values selected from input values 410-0 to compute i-th neuron output by processing unit 710-0 can be different from the number and indexes of input values selected from input values 710-1 to compute i-th neuron output by the processing unit 710-1. Due to the differences in the numbers of selected input values and the indexes of the selected input values, either 1) i-th neuron output of the processing unit 710-0 can be generated substantially prior to i-th neuron output of the processing unit 710-1; or 2) the i-th neuron output of the processing unit 710-0 can be generated substantially after the i-th neuron output of the processing unit 720-1.
• a first stream of neuron outputs generated by the processing unit 710-0 can be substantially unaligned with a second stream of neuron outputs generated by the processing unit 710-1 even when the first processing unit 710-0 and the second arithmetic unit 710-1 are configured to process the input values 405-0 and the input values 405-1 in parallel.
• the first stream of neuron outputs and the second stream of neuron outputs can also be unaligned due to the difference in the number of neuron outputs from the processing unit 710-0 and the processing unit 710-1 because the processing unit 710-0 and the processing unit 710-1 can be configured to generate different numbers of neuron outputs based on the same number of input values.
• the synchronization module 715 may receive partial results of neurons or multiple results of different neurons.
• the neuron outputs may be received by the synchronization module 715 in an unordered time sequence O[0,0], O[0,l], O[l,0], 0[ 0,2], 0[1,1], ... .
• the synchronization module 715 can write the neuron outputs in a correct order: O[0,0], O[l,0], ..., O[N,0], O[0,l], 0[1,1], ..., 0[N,1], 0[ 0,2], 0[1,2], ... .
• the neuron outputs can be read in a correct order as input values for neurons at further layer(s) of the ANN.
• the synchronization module 715 an indication 735 that the last part of the input data is being processed.
• the synchronization module 715 may finish writing neuron output to memory storage 720 and stand by ready for the next series of neuron outputs.
• FIG. 8 is a flow chart illustrating a method 800 for accelerating of ANN computations, in accordance with some example embodiments.
• the operations may be combined, performed in parallel, or performed in a different order.
• the method 800 may also include additional or fewer operations than those illustrated.
• the method 800 may be performed by system 100 described above with reference to in FIG. 1.
• the method 800 may select, by a controller communicatively coupled to a selector and an arithmetic unit and based on a criterion, an input value from a stream of input values of a neuron.
• the controller can be configured to select input values by comparison of the input values to a reference value.
• the reference value can be equal to zero.
• the method 800 may configure, by the controller, the selector to provide the selected input value to the arithmetic unit.
• the method 800 may provide, by the controller, to the arithmetic unit, information for the selected input value.
• the information may include an offset of the selected input values in the stream.
• the method 800 may acquire, by the arithmetic unit and based on the information, a weight from a set of weights.
• the method 800 may perform, by the arithmetic unit, a mathematical operation on the selected input value and the weight to obtain a result, wherein the result is to be used in computing an output of the neuron.
• the arithmetic unit may determine a multiplication product of the selected input values and weight, and summate the multiplication product into a sum.
• a count of the input values in the stream may be greater than a count of mathematical operations performed by the arithmetic units, wherein the operations are performed on the input values selected from the stream.
• FIG. 9 illustrates an example computing system 900 that may be used to implement embodiments described herein.
• the example computing system 900 of FIG. 9 may include one or more processors 910 and memory 920.
• Memory 920 may store, in part, instructions and data for execution by the one or more processors 910.
• Memory 920 can store the executable code when the exemplary computing system 900 is in operation.
• the processor 910 may include internal accelerators like a graphical processing unit, a Field Programmable Gate Array, or similar accelerators that may be suitable for use with embodiments described herein.
• the memory 920 may include internal accelerators like a graphical processing unit, a Field Programmable Gate Array, or similar accelerators that may be suitable for use with embodiments described herein.
• the example computing system 900 of FIG. 9 may further include a mass storage 930, portable storage 940, one or more output devices 950, one or more input devices 960, a network interface 970, and one or more peripheral devices 980.
• the components shown in FIG. 9 are depicted as being connected via a single bus 990.
• the components may be connected through one or more data transport means.
• the one or more processors 910 and memory 920 may be connected via a local microprocessor bus, and the mass storage 930, one or more peripheral devices 980, portable storage 940, and network interface 970 may be connected via one or more input/output buses.
• Mass storage 930 which may be implemented with a magnetic disk drive, an optical disk drive or a solid state drive, is a non-volatile storage device for storing data and instructions for use by a magnetic disk, an optical disk drive or SSD, which in turn may be used by one or more processors 910. Mass storage 930 can store the system software for implementing embodiments described herein for purposes of loading that software into memory 920.
• the mass storage 930 may also include internal accelerators like a graphical processing unit, a Field Programmable Gate Array, or similar
• Portable storage 940 may operate in conjunction with a portable non-volatile storage medium, such as a compact disk (CD) or digital video disc (DVD), to input and output data and code to and from the computing system 900 of FIG. 9.
• a portable non-volatile storage medium such as a compact disk (CD) or digital video disc (DVD)
• CD compact disk
• DVD digital video disc
• the system software for implementing embodiments described herein may be stored on such a portable medium and input to the computing system 900 via the portable storage 940.
• One or more input devices 960 provide a portion of a user interface.
• the one or more input devices 960 may include an alphanumeric keypad, such as a keyboard, for inputting alphanumeric and other information, or a pointing device, such as a mouse, a trackball, a stylus, or cursor direction keys.
• the computing system 900 as shown in FIG. 9 includes one or more output devices 950. Suitable one or more output devices 950 include speakers, printers, network interfaces, and monitors.
• Network interface 970 can be utilized to communicate with external devices, external computing devices, servers, and networked systems via one or more
• Network interface 970 may be a network interface card, such as an Ethernet card, optical transceiver, radio frequency transceiver, or any other type of device that can send and receive information.
• Other examples of such network interfaces may include Bluetooth®, 3G, 4G, and WiFi® radios in mobile computing devices as well as a USB.
• One or more peripheral devices 980 may include any type of computer support device to add additional functionality to the computing system.
• the one or more peripheral devices 980 may include a modem or a router.
• the example computing system 900 of FIG. 9 may also include one or more accelerator devices 985.
• the accelerator devices 985 may include PCIe-form-factor boards or storage-form-factor boards, or any electronic board equipped with a specific electronic component like a Graphical Processing Unit, a Neural Processing Unit, a Multi-CPU component, a Field Programmable Gate Array component, or similar accelerators electronic or photonic components, that may be suitable for use with embodiments described herein.
• the components contained in the exemplary computing system 900 of FIG. 9 are those typically found in computing systems that may be suitable for use with embodiments described herein and are intended to represent a broad category of such computer components that are well known in the art.
• the exemplary computing system 900 of FIG. 9 can be a personal computer, hand held computing device, telephone, mobile computing device, workstation, server, minicomputer, mainframe computer, or any other computing device.
• the computer can also include different bus configurations, networked platforms, multi-processor platforms, and so forth.
• Various operating systems (OS) can be used including UNIX, Linux, Windows, Macintosh OS, Palm OS, and other suitable operating systems.
• Some of the above-described functions may be composed of instructions that are stored on storage media (e.g., computer-readable medium).
• the instructions may be retrieved and executed by the processor.
• storage media are memory devices, tapes, disks, and the like.
• the instructions are operational when executed by the processor to direct the processor to operate in accord with the example
• Non-volatile media include, for example, optical or magnetic disks, such as a fixed disk.
• Volatile media include dynamic memory, such as RAM.
• Transmission media include coaxial cables, copper wire, and fiber optics, among others, including the wires that include one embodiment of a bus. Transmission media can also take the form of acoustic or light waves, such as those generated during radio frequency and infrared data communications.
• Computer-readable media include, for example, a floppy disk, a flexible disk, a hard disk, magnetic tape, any other magnetic medium, SSD, a CD-read-only memory (ROM) disk, DVD, any other optical medium, any other physical medium with patterns of marks or holes, a RAM, a PROM, an EPROM, an EEPROM, a FLASHEPROM, any other memory chip or cartridge, a carrier wave, or any other medium from which a computer can read.
• Various forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to a CPU for execution.
• a bus carries the data to system RAM, from which a CPU retrieves and executes the instructions.
• the instructions received by system RAM can optionally be stored on a fixed disk either before or after execution by a CPU.
• the instructions or data may not be used by the CPU but be accessed in writing or reading from the other devices without having the CPU directing them.
• FIG. 10 is a flow chart showing steps of a method 1000 for realigning streams of neuron outputs in ANN computations, according to some example embodiments.
• the operations may be combined, performed in parallel, or performed in a different order.
• the method 1000 may also include additional or fewer operations than those illustrated.
• the method 1000 may be performed by system 100 described above with reference to FIG. 1.
• the method 1000 can be also performed by system 700 described above with reference to FIG. 7.
• method 1000 may proceed with generating, by a processing unit, neuron outputs including at least a first neuron output and a second neuron output.
• the method 1000 may proceed with generating, by at least one further processing unit, further neuron outputs including at least a further first neuron output and a further second neuron output.
• the method 1000 may proceed with receiving, by a
• the neuron outputs and the further neuron outputs can be received in arbitrary order.
• the method may include ordering, by the synchronization module, the first neuron output, the further first neuron output, the second neuron output and the further second neuron output according to a further order.
• the ordering can be different from the order of the receiving the neuron outputs and the further neuron outputs.
• the method may proceed with writing, by the synchronization module, an ordered sequence to a memory storage, wherein the ordered sequence includes the first neuron output, the further first neuron output, the second neuron output and the further second neuron output ordered according to the further order.
• the ordered sequence can be used as further input values for further neurons.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Theoretical Computer Science (AREA)
• Health & Medical Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Biomedical Technology (AREA)
• Biophysics (AREA)
• Evolutionary Computation (AREA)
• Computational Linguistics (AREA)
• Data Mining & Analysis (AREA)
• Artificial Intelligence (AREA)
• General Health & Medical Sciences (AREA)
• Molecular Biology (AREA)
• Computing Systems (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Mathematical Physics (AREA)
• Software Systems (AREA)
• Neurology (AREA)
• Complex Calculations (AREA)

Applications Claiming Priority (3)

Publications (1)

Family

ID=69158146

Family Applications (2)

Family Applications Before (1)

Country Status (2)

Family Cites Families (3)

• 2019
  • 2019-12-10 EP EP19835489.6A patent/EP3895073A1/de active Pending
  • 2019-12-10 WO PCT/IB2019/060630 patent/WO2020121202A1/en unknown
  • 2019-12-10 EP EP19835488.8A patent/EP3895072A1/de active Pending
  • 2019-12-10 WO PCT/IB2019/060631 patent/WO2020121203A1/en unknown

Also Published As

Similar Documents

Legal Events