CN111310400B - BP neural network-based capacitance anti-pad optimization method and system - Google Patents
BP neural network-based capacitance anti-pad optimization method and system Download PDFInfo
- Publication number
- CN111310400B CN111310400B CN202010094701.1A CN202010094701A CN111310400B CN 111310400 B CN111310400 B CN 111310400B CN 202010094701 A CN202010094701 A CN 202010094701A CN 111310400 B CN111310400 B CN 111310400B
- Authority
- CN
- China
- Prior art keywords
- pad
- neural network
- size
- optimization
- simulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 61
- 238000005457 optimization Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004088 simulation Methods 0.000 claims abstract description 31
- 238000003475 lamination Methods 0.000 claims description 25
- 210000002569 neuron Anatomy 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 239000003990 capacitor Substances 0.000 claims description 8
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 6
- 229910052802 copper Inorganic materials 0.000 claims description 6
- 239000010949 copper Substances 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Images
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
- G06N3/04—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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Design And Manufacture Of Integrated Circuits (AREA)
Abstract
The invention provides a method and a system for optimizing a capacitive anti-pad based on a BP (back propagation) neural network, wherein via wizard and HFSS (high frequency synchronous signal) are used for establishing a corresponding simulation model, self-adaptive optimization is realized through the BP neural network, parameters of the size of the anti-pad can be adjusted in a self-adaptive manner as long as target values of impedance and return loss are set, so that the target values are reached, and the influence of traversing each variable on the impedance and the return loss is avoided.
Description
Technical Field
The invention relates to the technical field of PCB design, in particular to a capacitance anti-pad optimization method and system based on a BP neural network.
Background
In PCB high-speed interconnection, a signal transmitting end and a signal receiving end may have different requirements for dc components, and capacitors are often required to be connected in series between the signal transmitting end and the signal receiving end to isolate the dc voltage difference. But the series capacitance causes the link to drop in impedance at the switch point, resulting in an impedance discontinuity. Impedance discontinuities in high speed signals can cause signal reflections that severely affect signal quality, cause signal distortion, and cause signal integrity problems.
Currently, when capacitor anti-pad optimization is performed in the industry, HFSS modeling software is generally adopted, a scanning range is set for each variable by setting the size of an anti-pad as a variable, and an optimal value is found by traversing the influence of each variable on impedance and return loss. When the number of variables is large, the variables are required to be processed step by step according to the variable priorities, which consumes a lot of time, and the obtained optimized values may not meet the requirements of impedance and return loss at the same time.
Disclosure of Invention
The invention aims to provide a method and a system for optimizing a capacitive anti-pad based on a BP (back propagation) neural network, which aim to solve the problems that the size of the anti-pad depends on the experience of a designer and the optimization process is complicated in the prior art, save time and improve optimization precision and efficiency.
In order to achieve the technical purpose, the invention provides a capacitance anti-pad optimization method based on a BP neural network, which comprises the following steps:
s1, rapidly establishing a lamination through via wizard software, and deleting the established via to obtain a capacitance simulation lamination;
s2, establishing corresponding pad, routing, capacitance physical model and anti-pad model for the capacitance simulation lamination by using HFSS;
s3, the size parameters of the anti-bonding pad are adjusted in a self-adaptive mode by the BP neural network, so that the anti-bonding pad meets impedance and return loss indexes, and the optimal size of the anti-bonding pad is obtained.
Preferably, the relevant input variables of the impedance are the dielectric constant DK, the roughness rough of copper, the dimension d1 of pad and the anti-pad d2, and the optimization relation is as follows:
Z＝f(ω1*DK+ω2*rough+ω3*d1+ω4d2)；
the relevant input variables of the return loss are Df, the size of pad and the size of anti-pad, and the optimization relation is as follows:
RL＝f(ω1Df+ω2d1+ω3d2)。
preferably, the specific operation of adaptively adjusting the size parameter of the anti-pad by using the BP neural network is as follows:
determining a neural network according to input and output, wherein the neural network comprises the number of neurons in each layer, a transfer function of the neurons in each layer and the name of a training function;
initializing the weight, and initializing the weight and a threshold;
and (3) network simulation, wherein in the reverse propagation process, the BP neural network reversely transmits the error signal back according to the original forward propagation path, and adjusts the connection weight of each neuron of each hidden layer to realize self-adaptive adjustment and achieve a target output value.
The invention also provides a capacitance anti-pad optimization system based on the BP neural network, which comprises the following components:
the simulation lamination establishing module is used for quickly establishing a lamination through via wizard software and deleting the established via to obtain a capacitance simulation lamination;
the model establishing module is used for establishing a corresponding pad, routing, capacitance physical model and anti-pad model for the capacitance simulation lamination by using HFSS;
and the self-adaptive adjusting module is used for carrying out self-adaptive adjustment on the size parameter of the reverse bonding pad by utilizing the BP neural network, so that the reverse bonding pad meets the impedance and return loss indexes, and the optimal reverse bonding pad size is obtained.
Preferably, the relevant input variables of the impedance are the dielectric constant DK, the roughness rough of copper, the dimension d1 of pad and the anti-pad d2, and the optimization relation is as follows:
Z＝f(ω1*DK+ω2*rough+ω3*d1+ω4d2)；
the relevant input variables of the return loss are Df, the size of pad and the size of anti-pad, and the optimization relation is as follows:
RL＝f(ω1Df+ω2d1+ω3d2)。
preferably, the adaptive adjustment module includes:
the neural network parameter setting unit is used for determining a neural network according to input and output, and comprises the number of neurons in each layer, the transfer function of the neurons in each layer and the name of a training function;
the weight parameter initialization unit is used for initializing the weight and a threshold;
and the simulation unit is used for carrying out network simulation, when the error signals are reversely transmitted, the BP neural network reversely transmits the error signals back according to the original forward transmission path, and adjusts the connection weight of each neuron of each hidden layer, so that the self-adaptive adjustment is realized, and the target output value is reached.
The invention also provides a BP neural network-based capacitance anti-pad optimization device, which comprises:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the capacitance anti-pad optimization method based on the BP neural network.
The invention also provides a readable storage medium for storing a computer program, wherein the computer program is used for realizing the BP neural network-based capacitance anti-pad optimization method when being executed by a processor.
The effect provided in the summary of the invention is only the effect of the embodiment, not all the effects of the invention, and one of the above technical solutions has the following advantages or beneficial effects:
compared with the prior art, the method uses via wizard and HFSS to establish a corresponding simulation model, realizes self-adaptive optimization through a BP neural network, can self-adaptively adjust the parameters of the size of the anti-pad as long as the target values of the impedance and the return loss are set, thereby reaching the target values, avoiding the influence of traversing each variable on the impedance and the return loss one by a designer, on one hand, the requirement on optimizing the experience of the designer is lower, the operation can be carried out without having rich experience, on the other hand, the time can be saved, and the optimization precision and the efficiency can be improved.
Drawings
Fig. 1 is a flowchart of a capacitance anti-pad optimization method based on a BP neural network according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a capacitor simulation stacked structure according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a simulation model of a capacitor anti-pad provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a BP neuron model provided in an embodiment of the present invention;
fig. 5 is a block diagram of a capacitance anti-pad optimization system based on a BP neural network according to an embodiment of the present invention.
Detailed Description
In order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Moreover, the present disclosure may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
The following describes in detail a method and a system for optimizing a capacitive anti-pad based on a BP neural network according to an embodiment of the present invention with reference to the accompanying drawings.
As shown in fig. 1, the invention discloses a capacitance anti-pad optimization method based on a BP neural network, which comprises the following steps:
s1, rapidly establishing a lamination through via wizard software, and deleting the established via to obtain a capacitance simulation lamination;
s2, establishing corresponding pad, routing, capacitance physical model and anti-pad model for the capacitance simulation lamination by using HFSS;
s3, the size parameters of the anti-bonding pad are adjusted in a self-adaptive mode by the BP neural network, so that the anti-bonding pad meets the impedance and return loss indexes, and the optimal anti-bonding pad size is obtained.
According to the embodiment of the invention, a corresponding simulation model is established through via wizard and HFSS, and self-adaptive adjustment is carried out through a BP neural network, so that corresponding impedance and return loss indexes are achieved, and the size of a reverse welding pad is optimized.
And (3) rapidly establishing a lamination through via wizard software, and deleting the established via to obtain the capacitance simulation lamination, as shown in figure 2.
HFSS was used to build the corresponding pad, trace, capacitance physical model, and anti-pad as shown in fig. 3.
The method utilizes a BP neural network to realize the self-adaptive adjustment of the size parameter of the anti-pad, so that the anti-pad meets the impedance and loss indexes, the discontinuous phenomenon of the impedance of an interconnection line is improved, and the optimal physical size of the anti-pad is found, wherein the self-adaptive adjustment process comprises the following steps:
as shown in fig. 4, the BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm.
Determining input and output variables, wherein for the impedance Z of the output variable, the relevant input variables are dielectric constant DK, roughness of copper rough, size d1 of pad and anti-pad d2, and for the return loss RL of the output variable, the relevant input variables comprise Df, size of pad and anti-pad size, and establishing the following relation for optimization:
RL＝f(ω1Df+ω2d1+ω3d2)
Z＝f(ω1*DK+ω2*rough+ω3*d1+ω4d2)
weight ω in the above relation1、ω2、ω3The method is obtained by training a network, generally uses Matlab, and does not need to be set. The following commands are used:
net＝newff(minmax(p),[3,2],{'tansig','logsig'},'trainlm')
and automatically assigning the weight parameters, wherein the range is between [0 and 1 ]. Wherein the weight and the size d2 of the reverse pad are variables, and the rest variables are quantitative.
In practical designs where the stack is fixed and the size of the capacitor pad is fixed, these are all fixed values, and the only variable to be adjusted is the anti-pad size.
Determining a neural network according to the input and the output, namely determining the number of neurons of each layer, the transfer function of the neurons of each layer and the name of a training function;
initializing the weight, wherein the feedforward neural network has to initialize the weight and the threshold before training, and the process can be automatically completed through a newff function;
and (3) network simulation, wherein in the reverse propagation process, the BP neural network reversely transmits the error signal back according to the original forward propagation path, and adjusts the connection weight of each neuron of each hidden layer so as to enable the expected error signal to tend to be minimum, thereby realizing the self-adaptive adjustment and achieving the target output value.
In the embodiment of the invention, via wizard and HFSS are used to establish a corresponding simulation model, self-adaptive optimization is realized through a BP neural network, and as long as target values of impedance and return loss are set, parameters of the size of the anti-pad can be adjusted in a self-adaptive manner, so that the target values are reached, the influence of traversing each variable on the impedance and the return loss one by a designer is avoided, on one hand, the requirement on experience of the optimization designer is low, operation can be carried out without abundant experience, on the other hand, time is saved, and the optimization precision and efficiency are improved.
As shown in fig. 5, an embodiment of the present invention further discloses a BP neural network-based capacitance anti-pad optimization system, where the system includes:
the simulation lamination establishing module is used for quickly establishing a lamination through via wizard software and deleting the established via to obtain a capacitance simulation lamination;
the model establishing module is used for establishing a corresponding pad, routing, capacitance physical model and anti-pad model for the capacitance simulation lamination by using HFSS;
and the self-adaptive adjusting module is used for carrying out self-adaptive adjustment on the size parameter of the reverse bonding pad by utilizing the BP neural network, so that the reverse bonding pad meets the impedance and return loss indexes, and the optimal reverse bonding pad size is obtained.
And (3) rapidly establishing a lamination through via wizard software, and deleting the established via to obtain the capacitance simulation lamination.
HFSS is used to build up the corresponding pad, trace, capacitive physical model, and anti-pad.
The method utilizes a BP neural network to realize the self-adaptive adjustment of the size parameter of the anti-pad, so that the anti-pad meets the impedance and loss indexes, the discontinuous phenomenon of the impedance of an interconnection line is improved, and the optimal physical size of the anti-pad is found, wherein the self-adaptive adjustment process comprises the following steps:
the BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm.
Determining input and output variables, wherein for the impedance Z of the output variable, the relevant input variables are dielectric constant DK, roughness of copper rough, size d1 of pad and anti-pad d2, and for the return loss RL of the output variable, the relevant input variables comprise Df, size of pad and anti-pad size, and establishing the following relation for optimization:
RL＝f(ω1Df+ω2d1+ω3d2)
Z＝f(ω1*DK+ω2*rough+ω3*d1+ω4d2)
the weight ω in the above relation1、ω2、ω3The network is obtained by training the network, and Matlab is generally used without setting. The following commands are used:
net＝newff(minmax(p),[3,2],{'tansig','logsig'},'trainlm')
and automatically assigning the weight parameters, wherein the range is between [0 and 1 ]. Wherein the weight and the pad-opposing size d2 are variables and the remaining variables are quantitative.
In practical designs where the stack is fixed and the size of the capacitor pad is fixed, these are all fixed values, and the only variable to be adjusted is the anti-pad size.
Determining a neural network according to the input and the output, namely determining the number of neurons of each layer, the transfer function of the neurons of each layer and the name of a training function;
initializing the weight, wherein the feedforward neural network has to initialize the weight and the threshold before training, and the process can be automatically completed through a newff function;
and (3) network simulation, wherein in the reverse propagation process, the BP neural network reversely transmits the error signal back according to the original forward propagation path, and adjusts the connection weight of each neuron of each hidden layer so as to enable the expected error signal to tend to be minimum, thereby realizing the self-adaptive adjustment and achieving the target output value.
The embodiment of the invention also discloses a BP neural network-based capacitance anti-pad optimization device, which comprises:
a memory for storing a computer program;
and the processor is used for executing the computer program to realize the capacitance anti-pad optimization method based on the BP neural network.
The embodiment of the invention also discloses a readable storage medium for storing a computer program, wherein the computer program is used for realizing the BP neural network-based capacitance anti-pad optimization method when being executed by a processor.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. A capacitance anti-pad optimization method based on a BP neural network is characterized by comprising the following steps:
s1, rapidly establishing a lamination through via wizard software, and deleting the established via to obtain a capacitance simulation lamination;
s2, establishing corresponding pad, routing, capacitance physical model and anti-pad model for the capacitance simulation lamination by using HFSS;
s3, carrying out self-adaptive adjustment on the size parameter of the anti-bonding pad by using the BP neural network, so that the anti-bonding pad meets impedance and return loss indexes, and the optimal size of the anti-bonding pad is obtained;
the relevant input variables of the impedance are dielectric constant DK, roughness rough of copper, size d1 of pad and anti-bonding pad d2, and the optimization relation is as follows:
the relevant input variables of the return loss are Df, the size of pad and the size of anti-pad, and the optimization relation is as follows:
2. the method for optimizing the capacitive anti-pad based on the BP neural network as claimed in claim 1, wherein the specific operation of adaptively adjusting the size parameter of the anti-pad by using the BP neural network is as follows:
determining a neural network according to input and output, wherein the neural network comprises the number of neurons in each layer, a transfer function of the neurons in each layer and the name of a training function;
initializing the weight, and initializing the weight and a threshold;
and (3) network simulation, wherein in the reverse propagation process, the BP neural network reversely transmits the error signal back according to the original forward propagation path, and adjusts the connection weight of each neuron of each hidden layer to realize self-adaptive adjustment and achieve a target output value.
3. A BP neural network based capacitive anti-pad optimization system, the system comprising:
the simulation lamination establishing module is used for rapidly establishing lamination through via wizard software and deleting the established via to obtain a capacitance simulation lamination;
the model establishing module is used for establishing a corresponding pad model, a routing model, a capacitor physical model and an anti-pad model for the capacitor simulation lamination by using HFSS;
the adaptive adjustment module is used for adaptively adjusting the size parameters of the reverse bonding pad by using a BP (back propagation) neural network so that the reverse bonding pad meets impedance and return loss indexes and the optimal reverse bonding pad size is obtained;
the relevant input variables of the impedance are dielectric constant DK, roughness rough of copper, size d1 of pad and anti-bonding pad d2, and the optimization relation is as follows:
the relevant input variables of the return loss are Df, the size of pad and the size of anti-pad, and the optimization relation is as follows:
4. the BP neural network based capacitive anti-pad optimization system according to claim 3, wherein the adaptive adjustment module comprises:
the neural network parameter setting unit is used for determining a neural network according to input and output, and comprises the number of neurons in each layer, the transfer function of the neurons in each layer and the name of a training function;
the weight parameter initialization unit is used for initializing the weight and a threshold;
and the simulation unit is used for carrying out network simulation, when the error signals are reversely transmitted, the BP neural network reversely transmits the error signals back according to the original forward transmission path, and adjusts the connection weight of each neuron of each hidden layer, so that the self-adaptive adjustment is realized, and the target output value is reached.
5. A BP neural network-based capacitive anti-pad optimization device, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the BP neural network based capacitive anti-pad optimization method of claim 1 or 2.
6. A readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the BP neural network based capacitive antipad optimization method of claim 1 or 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010094701.1A CN111310400B (en) | 2020-02-16 | 2020-02-16 | BP neural network-based capacitance anti-pad optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010094701.1A CN111310400B (en) | 2020-02-16 | 2020-02-16 | BP neural network-based capacitance anti-pad optimization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111310400A CN111310400A (en) | 2020-06-19 |
| CN111310400B true CN111310400B (en) | 2022-06-07 |
Family
ID=71159364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010094701.1A Active CN111310400B (en) | 2020-02-16 | 2020-02-16 | BP neural network-based capacitance anti-pad optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310400B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832247B (en) * | 2020-06-24 | 2022-06-03 | 苏州浪潮智能科技有限公司 | Method and device for determining size of via hole anti-pad based on BP neural network |
| CN112395807B (en) * | 2020-11-12 | 2022-07-12 | 苏州浪潮智能科技有限公司 | Method and system for optimizing coupling of via hole and in-out wire after capacitance |
| CN112747663B (en) * | 2020-12-11 | 2023-06-02 | 浪潮电子信息产业股份有限公司 | Method, device and system for detecting hollowed-out size of differential via anti-bonding pad |
| CN112888155B (en) * | 2021-01-14 | 2022-04-01 | 合肥移瑞通信技术有限公司 | Circuit board, circuit board via hole optimization method, electronic device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787558A (en) * | 2016-04-11 | 2016-07-20 | 江苏科技大学 | Knowledge-based neural network micro-strip filter design method based on ADS |
| CN109726817A (en) * | 2018-12-21 | 2019-05-07 | 河北工业大学 | The WPT system impedance matching methods of genetic algorithm optimization BP neural network |
| CN110765723A (en) * | 2019-11-15 | 2020-02-07 | 苏州浪潮智能科技有限公司 | Routing modeling optimization method and device based on BP neural network |
-
2020
- 2020-02-16 CN CN202010094701.1A patent/CN111310400B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787558A (en) * | 2016-04-11 | 2016-07-20 | 江苏科技大学 | Knowledge-based neural network micro-strip filter design method based on ADS |
| CN109726817A (en) * | 2018-12-21 | 2019-05-07 | 河北工业大学 | The WPT system impedance matching methods of genetic algorithm optimization BP neural network |
| CN110765723A (en) * | 2019-11-15 | 2020-02-07 | 苏州浪潮智能科技有限公司 | Routing modeling optimization method and device based on BP neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111310400A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310400B (en) | BP neural network-based capacitance anti-pad optimization method and system | |
| US8866282B2 (en) | Semiconductor apparatus, signal transmission system and signal transmission method | |
| US20160291894A1 (en) | Dynamic termination scheme for memory communication | |
| CN110765723B (en) | Routing modeling optimization method and device based on BP neural network | |
| CN111832247B (en) | Method and device for determining size of via hole anti-pad based on BP neural network | |
| CN108596331A (en) | A kind of optimization method of cell neural network hardware structure | |
| CN109726353B (en) | Convolution operation device and method | |
| CN111586969B (en) | Circuit wiring method, DDR4 internal memory circuit and electronic equipment | |
| CN111314252B (en) | Self-adaptive equalization method and system for high-speed serial port transceiver | |
| CN112395807B (en) | Method and system for optimizing coupling of via hole and in-out wire after capacitance | |
| CN110059800A (en) | Impulsive neural networks conversion method and related conversion chip | |
| JP2005150644A (en) | High frequency wiring structure, method for forming the same, and method for shaping waveform of high frequency signal | |
| CN110175432B (en) | Negative group delay circuit based on four parallel microstrip lines and design method thereof | |
| CN107748914A (en) | Artificial neural network computing circuit | |
| WO2020087254A1 (en) | Optimization method for convolutional neural network, and related product | |
| WO2022147000A1 (en) | Equalization for pulse-amplitude modulation | |
| TW202030647A (en) | System and method for reducing computational complexity of artificial neural network | |
| US10909417B2 (en) | Proposal processing method and related products | |
| CN110290634A (en) | The generation method and electronic equipment of a kind of printed circuit board, printed circuit board model | |
| CN112766479A (en) | Neural network accelerator supporting channel separation convolution based on FPGA | |
| CN104797078A (en) | Method for reducing impedance mismatching degree under condition of discontinuous returning path | |
| Lin et al. | Influence of Via Stubs on Signal Integrity of Multi-layer PCB Boards | |
| CN102811547A (en) | Impedance control method | |
| WO2022227099A1 (en) | Sending device, receiving device, and signal compensation method | |
| CN109753134B (en) | Global decoupling-based GPU internal energy consumption control system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |