Chinese Academy of Sciences

Cambricon Technologies Corporation Limited

Shijin Zhang

Yunji Chen

Shaoli Liu

Tao Luo

Tianshi Chen

Zhen Li

Cheng Qian

Qi Guo

Jin Wang

Jinhua Tao

Xi Chen

Xiao Lin Zhang

Dong Han

Huiying Lan

Zhibin Guo

Shangying Li

Aspects for modifying data in a multi-layer neural network (MNN) acceleration processor for neural networks are described herein. As an example, the aspects may include receiving a predetermined weight value array and connection data. Further, the aspects may include modifying the weight values included in the predetermined weight value array based on the connection data. Further still, the aspects may include calculating one or more groups of output data based on the modified weight values.

Calculating device and method for a sparsely connected artificial neural network

Aspects for backpropagation in a fully connect layer of a convolutional neural network are described herein. The aspects may include a direct memory access unit configured to receive input data and one or more first data gradients from a storage device. The aspects may further include a master computation module configured to transmit the input data and the one or more first data gradients to one or more slave computation modules. The slave computation modules are respectively configured to multiply one of the one or more first data gradients with the input data to generate a default weight gradient vector.

Apparatus and methods for training in fully connected layers of convolutional networks

The present disclosure relates to a data processing method, a device, an electronic device, and a readable storage medium. When the above are adopted, a target neural network is subject to a subnet classification. The target neural network includes at least one subnet. When the method is adopted, at least during the process of compiling and running the subnets, only one input operation and one output operation are required. Whereas when the network layers of the subnet are compiled and run layer by layer, pluralities of input operations and output operations are required. Therefore, the data processing method is more efficient and is capable of improving the operation rate.

Layer fusion in neural network processing

The invention relates to an operation method and device and a related product, the product comprises a control module, and the control module comprises an instruction caching unit, an instruction processing unit and a storage queue unit; the instruction caching unit is used for storing a calculation instruction associated with the artificial neural network operation; the instruction processing unit is used for analyzing the calculation instruction to obtain a plurality of operation instructions; the storage queue unit is used for storing instruction queues, and the instruction queues comprise a plurality of operation instructions or calculation instructions to be executed according to the sequence of the queues. Through the method, the operation efficiency of related products during operation of the neural network model can be improved.

Operation method, device and related products

The present invention provides a fractal tree structure-based data transmit device and method, a control device, and an intelligent chip. The device comprises: a central node that is as a communication data center of a network-on-chip and used for broadcasting or multicasting communication data to a plurality of leaf nodes; the plurality of leaf nodes that are as communication data nodes of the network-on-chip and for transmitting the communication data to a central leaf node; and forwarder modules for connecting the central node with the plurality of leaf nodes and forwarding the communication data; the central node, the forwarder modules and the plurality of leaf nodes are connected in the fractal tree network structure, and the central node is directly connected to M the forwarder modules and/or leaf nodes, any the forwarder module is directly connected to M the next level forwarder modules and/or leaf nodes.

Fractal tree structure-based data transmit device and method, control device, and intelligent chip

The disclosure relates to a network structure processing method and device and a related product, including: obtaining, by a computer device, an optimization instruction; and executing a corresponding optimization processing operation on the network structure according to the optimization level in the optimization instruction to obtain an optimized network structure. According to the processing method of the network structure, the resource cost can be reduced, and the detection rate of the network structure on images is improved.

Network structure processing method and device and related products

The present disclosure provides an operation apparatus and method for an acceleration chip for accelerating a deep neural network algorithm. The apparatus comprises: a vector addition processor module and a vector function value arithmetic unit and a vector multiplier-adder module wherein the three modules execute a programmable instruction, and interact with each other to calculate values of neurons and a network output result of a neural network, and a variation amount of a synaptic weight representing the interaction strength of the neurons on an input layer to the neurons on an output layer; and the three modules are all provided with an intermediate value storage region and perform read and write operations on a primary memory.

Operation apparatus and method for acceleration chip for accelerating deep neural network algorithm

One example of a device comprises: a central node that is as a communication data center of a network-on-chip; a plurality of leaf nodes that are as communication data nodes of the network-on-chip and for transmitting the communication data to a central leaf node; forwarder modules for connecting the central node with the plurality of leaf nodes and forwarding the communication data, wherein the plurality of leaf nodes are divided into N groups, each group having the same number of leaf nodes, the central node is individually in communication connection with each group of leaf nodes by means of the forwarder module, a communication structure constituted by each group of leaf nodes has self-similarity, and the plurality of leaf nodes are in communication connection with the central node in a complete multi-way tree approach by means of the forwarder modules of multiple levels.

An example device comprises a central node for receiving vector data returned by leaf nodes, a plurality of leaf nodes for calculating and shifting the vector data, and forwarder modules comprising a local cache structure and a data processing component, wherein the plurality of leaf nodes are divided into N groups, each group having the same number of leaf nodes; the central node is individually in communication connection with each group of leaf nodes by means of the forwarder modules; a communication structure constituted by each group of leaf nodes has self-similarity; the plurality of leaf nodes are in communication connection with the central node in a complete M-way tree approach by means of the forwarder modules of multiple levels; each of the leaf nodes comprises a setting bit.

Device for vector data returning processing unit in fractal tree, method, control device, and intelligent chip

A communication structure comprises: a central node that is a communication data center of a network-on-chip and used for broadcasting or multicasting communication data to a plurality of leaf nodes; a plurality of leaf nodes that are communication data nodes of the network-on-chip and used for transmitting the communication data to the central node; and forwarder modules for connecting the central node with the plurality of leaf nodes and forwarding the communication data, wherein the plurality of leaf nodes are divided into N groups, each group having the same number of leaf nodes, the central node is individually in communication connection with each group of leaf nodes by means of the forwarder modules, the communication structure is a fractal-tree structure, the communication structure constituted by each group of leaf nodes has self-similarity, and the forwarder modules comprises a central forwarder module, leaf forwarder modules, and intermediate forwarder modules.

Fractal-tree communication structure and method, control apparatus and intelligent chip

The present disclosure provides a quick operation device for a nonlinear function, and a method therefor. The device comprises: a domain conversion part for converting an input independent variable into a corresponding value in a table lookup range; a table lookup part for looking up a slope and an intercept of the corresponding piecewise linear fitting based on the input independent variable or an independent variable processed by the domain conversion part; and a linear fitting part for obtaining, a final result in a way of linear fitting based on the slope and the intercept obtained, by means of table lookup, by the table lookup part. The present disclosure solves the problems of slow operation speed, large area of the operation device, and high power consumption caused by the traditional method.

Quick operation device for nonlinear function, and method therefor

The present disclosure discloses an adder device, a data accumulation method and a data processing device. The adder device comprises: a first adder module provided with an adder tree unit, composed of a multi-stage adder array, and a first control unit, wherein the adder tree unit accumulates data by means of step-by-step accumulation based on a control signal of the first control unit; a second adder module comprising a two-input addition/subtraction operation unit and a second control unit, and used for performing an addition or subtraction operation on input data; a shift operation module for performing a left shift operation on output data of the first adder module; an AND operation module for performing an AND operation on output data of the shift operation module and output data of the second adder module; and a controller module.

Adder device, data accumulation method and data processing device

The present disclosure provides a data accumulation device and method, and a digital signal processing device. The device comprises: an accumulation tree module for accumulating input data in the form of a binary tree structure and outputting accumulated result data; a register module including a plurality of groups of registers and used for registering intermediate data generated by the accumulation tree module during an accumulation process and the accumulated result data; and a control circuit for generating a data gating signal to control the accumulation tree module to filter the input data not required to be accumulated, and generating a flag signal to perform the following control: selecting a result obtained after adding one or more of intermediate data stored in the register to the accumulated result as output data, or directly selecting the accumulated result as output data. Thus, a plurality of groups of input data can be rapidly accumulated to a group of sums in a clock cycle. At the same time, the accumulation device can flexibly select to simultaneously accumulate some data of the plurality of input data by means of a control signal.

Growing community of inventors

Beijing, China

Shijin Zhang