In-memory multiplication and addition calculation method and device, chip and calculation equipment
A technology of adding calculations and products, applied in calculations, instruments, biological neural network models, etc., can solve the problems of operating performance bandwidth limitations, large resource consumption, etc., and achieve the effect of reducing resource occupation and power consumption
Pending Publication Date: 2021-12-03
NANJING HOUMO TECH CO LTD
View PDF0 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] For traditional neural network accelerators, a large amount of resources are consumed in each architectural link, such as the power consumption and delay of multipliers and adders, and its operating performance is also limited by the bandwidth between storage and processors.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032]Hereinafter, exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited by the exemplary embodiments described here.
[0033] It should be noted that relative arrangements of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
[0034] Those skilled in the art can understand that terms such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc. necessary logical sequence.
[0035] It should also be understood that in the embodiments of the present disclosure, "p...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the invention discloses an in-memory multiplication and addition calculation method and device, a chip and calculation equipment, and the method comprises the steps: obtaining a target number of input weight data pair sets from a preset neural network; generating codes respectively corresponding to the input weight data pairs in the input weight data pair set; storing the target number of input weight data pair sets into a preset first storage area; based on the code corresponding to each piece of product data in the second storage area, determining whether a corresponding target input weight data pair exists in the first storage area, and if yes, determining the product data as to-be-accumulated data corresponding to the target input weight data pair; and performing accumulation operation on the to-be-accumulated data respectively corresponding to the input weight data pairs in each input weight data pair set to obtain an accumulation result. According to the embodiment of the invention, the use of an addition tree is avoided, the resource occupation amount is reduced, the sparsity of data in the neural network can be utilized in the reverse search process, and the power consumption of accumulation operation is reduced.
Description
technical field [0001] The present disclosure relates to the technical field of computers, in particular to an in-memory multiply-add calculation method, device, chip and calculation equipment. Background technique [0002] A neural network, a computing system used to simulate the human brain to analyze and process information. It is the foundation of artificial intelligence, solving problems that would prove impossible or difficult to solve by human or statistical standards. Artificial neural networks are self-learning and can produce better results given more data. Neural network technology is widely used in face recognition, named entity recognition, speech recognition, signature verification, semantic detection and other scenarios. [0003] For traditional neural network accelerators, a large amount of resources are consumed in each architectural link, such as the power consumption and delay of multipliers and adders, and their operating performance is also limited by ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F7/498G06N3/02
CPCG06F7/4983G06N3/02
Inventor 常亮李苇航司鑫沈朝晖陈亮吴强
Owner NANJING HOUMO TECH CO LTD