CN109670255A - A kind of exemplary simulation condition recommended method of time sequence parameter cluster - Google Patents
A kind of exemplary simulation condition recommended method of time sequence parameter cluster Download PDFInfo
- Publication number
- CN109670255A CN109670255A CN201811601063.7A CN201811601063A CN109670255A CN 109670255 A CN109670255 A CN 109670255A CN 201811601063 A CN201811601063 A CN 201811601063A CN 109670255 A CN109670255 A CN 109670255A
- Authority
- CN
- China
- Prior art keywords
- collection
- parameter
- time sequence
- path
- circuit
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/39—Circuit design at the physical level
- G06F30/398—Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
Abstract
A kind of exemplary simulation condition recommended method of time sequence parameter cluster, comprising the following steps: building service condition collection, path parameter collection and cell parameters collection；The path parameter collection and the cell parameters collection are subjected to Z-score normalization, and extraction typical statistic parameter for statistical analysis；It carries out ISODATA clustering and obtains the path parameter collection and the corresponding cluster classification of the cell parameters collection；Supervised classification model is established, determines simulated conditions boundary corresponding to the different operating mode of circuit.The present invention obtains circuit critical path and the relevant time sequence parameter building sample data set of internal element under more simulated conditions, the classification and screening of time sequence parameter are completed by ISODATA clustering algorithm, and it navigates to typical simulation run condition and recommends user, accelerate circuit sequence verifying and analytic process, and then shortens the chip design cycle.
Description
Technical field
The present invention relates to EDA design field, in particular to a kind of exemplary simulation condition recommended method of time sequence parameter cluster.
Background technique
Eda tool completes the physical Design of chip by calling standard cell lib (Standard Cell Library), when
Sequence library (Timing Library) is then at static timing analysis (Static Timing Analysis, STA) with bivariate table
Form recording unit library in cell delay information.Timing verification and analytic process of the eda tool when chip makes physical is implemented
In, circuit basic unit delay parameter is to be directly acquired by the library or interpolation calculation obtains.Meanwhile circuit interconnection line RC joins
It is several that the influence of the timing of entire circuit also can not be ignored.With the continuous improvement of technological level and design requirement, multiterminal angle-is introduced
Multi-mode (Multi-Corner Multi-mode, MCMM) technology is carried out for the different working environment of chip and operating mode
Combination is as SPICE emulation (i.e. Simulation program with integrated circuit emphasis, emulation
Circuit simulator is most common circuit-level simulation program, and it is big that each software vendor provides VSPICE, HSPICE and PSPICE etc.
With the SPICE software version of small difference, be all made of the spice simulation algorithm of Berkeley university exploitation) model parameter, with reality
Circuit sequence analysis and inspection under existing many condition operating condition.During synchronous circuit timing Design, temporal constraint
(Timing Constraints) plays directive function to the physical Design and timing Design of chip, is that checking chip timing is
No convergent benchmark.The timing results obtained by STA can in standard cell lib specific PVT (Process,
Voltage and Temperature) under SPICE emulation timing results complete calibration.It is old that circuit is introduced under the conditions of typical PVT
Change time (Aging Time) and is used as SPICE circuit simulation model parameter, it can be more truly in solving circuit critical path
The time sequence parameter of portion's each unit efficiently solves limitation of STA during chip designs.But SPICE circuit simulation one
As take a long time, and each time the time sequence parameter of simulation and calculation can not reactionary slogan, anti-communist poster to circuit each unit, for subsequent STA circuit analysis
It is recycled, which increases the period of chip design.Meanwhile under a large amount of simulated conditions SPICE emulation when
Its information redundance of order parameter is larger, lacks typicalness, to hinder subsequent conditioning circuit timing verification and analytic process.
Circuit sequence analysis mainly by be calculated on two levels of circuit critical path and inside unit when
Order parameter completes correlation analysis, and it may also include phase without same path that wherein single-pathway, which may include multiple and different units,
Same unit.Either which level, the time sequence parameter obtained under more simulated conditions can construct effective sample data set,
And the classification and screening of emulation time sequence parameter data set are completed by classical machine learning algorithm (such as classify, cluster), and fixed
User is recommended to typical simulation run condition in position, accelerates circuit sequence verifying and analytic process.
Summary of the invention
In order to solve the shortcomings of the prior art, the purpose of the present invention is to provide a kind of typical cases of time sequence parameter cluster
Simulated conditions recommended method, obtains circuit critical path under more simulated conditions and the relevant time sequence parameter of internal element constructs sample
Notebook data collection, the classification and screening of time sequence parameter are completed by ISODATA clustering algorithm, and navigate to typical simulation run item
Part recommends user, accelerates circuit sequence verifying and analytic process, and then shorten the chip design cycle.
To achieve the above object, the exemplary simulation condition recommended method of time sequence parameter cluster provided by the invention, including with
Lower step:
1) service condition collection, path parameter collection and cell parameters collection are constructed；
2) the path parameter collection and the cell parameters collection are subjected to Z-score normalization, and for statistical analysis mentioned
Take typical statistic parameter；
3) it carries out ISODATA clustering and obtains the path parameter collection and the corresponding cluster class of the cell parameters collection
Not；
4) supervised classification model is established, determines simulated conditions boundary corresponding to the different operating mode of circuit.
Further, in the step 1), according to artificial circuit topological structure and artificial tasks hierarchical structure, selection is imitative
True task proper subclass and emulation time sequence parameter proper subclass construct service condition collection and path parameter collection or cell parameters collection respectively；
The building of path parameter collection or cell parameters collection is fit to same artificial tasks hierarchical structure, wherein preceding 3 layers of correspondence
In mulitpath and multiple units, latter 2 layers then correspond to a paths or a unit, specific steps are as follows:
Service condition collection is constructed with the actual SPICE simulation run condition of circuit；
The SPICE emulation that circuit is completed for all SPICE simulated conditions vector resolves the circuit critical path and interior
The time sequence parameter of portion's unit；
Using critical path or essential elements as research object, its time sequence parameter under the conditions of all simulation runs is integrated
Construct set of data samples；The set of data samples, including path parameter collection and cell parameters collection construct a R respectively4And R3's
European sample space, path parameter collection vector sum cell parameters collection vector are respectively the feature vector in the sample space.
Further, the service condition collection, including, Process, Voltage, Temperature and Aging Time.
Further, the path parameter collection, including, launch clock path delay, data path delay,
Capture clock path delay and path slack；The cell parameters collection, including, increment delay,
Transition time and arrival time.
Further, in the step 2), path parameter collection and cell parameters collection are subjected to Z-score normalization, system
Typical statistic parameter is extracted in meter analysis；With reference to timing sequence library and temporal constraint, the primary condition of ISODATA Clustering Model is determined,
The typical statistic parameter includes sum, maximum value, minimum value, mean value, minimal characteristic distance, maximum characteristic distance.
Further, the step 3) further comprises selecting in each classification according to minimal distance principle apart from classification
The nearest time sequence parameter sample in center is represented as such time sequence parameter, and corresponding simulated conditions are as circuit exemplary operation
Service condition under mode.
Further, the step 4) further comprises, using cluster result label as the sample of corresponding service condition collection
This label establishes supervised classification model, for predicting its corresponding circuits time sequence status for new simulated conditions, while determining circuit
Simulated conditions boundary corresponding to different operating modes, for time sequence status prediction and exception of the circuit under new simulated conditions
Situation detection.
It further, can be by new simulated conditions and emulation time sequence parameter difference after completing SPICE emulation to new samples
It is included in service condition collection and path parameter collection, cell parameters collection, updates optimization Clustering Model and disaggregated model, is further obtained more
Has exemplary simulation service condition subset.
To achieve the above object, the present invention also provides a kind of computer readable storage mediums, are stored thereon with computer and refer to
The step of order, the computer instruction executes the exemplary simulation condition recommended method of above-mentioned time sequence parameter cluster when running.
Technical solution of the present invention has the advantages that
1) OCS, PPS and CPS are constructed respectively using the parameter of emulation front and back, and using Z-Score rule to PPS and
CPS carries out standardization processing, balances the influence of each time sequence parameter.And typical operation item is reverse-located by analysis PPS and CPS
Part subsetAndThen will represent a kind of typical circuit operating pattern；
2) realize that the timing redundancy of SPICE emulation time sequence parameter collection PPS and CPS is solidifying using ISODATA clustering algorithm
It is poly-.Temporal constraint rule can be incorporated after clustering and quickly navigates to the exception class of timing violation, and then accelerates timing verification
And analytic process, effectively shorten the chip design cycle；
3) class label that PPS and CPS cluster generates is used for the supervised classification of OCS, quickly distinguishes and predicts to reach
Circuit operating pattern under subsequent simulation service condition.Newly-increased simulated conditions are used to simultaneously to cluster the update with disaggregated model
The precision of Clustering Model and disaggregated model is continuously improved in optimization process.
4) after increasing artificial tasks newly, its simulation run condition and emulation time sequence parameter are used for Clustering Model and disaggregated model
Update optimization finally stablized and accurate exemplary simulation condition recommendation results until model is restrained.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, and with it is of the invention
Embodiment together, is used to explain the present invention, and is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the flow chart of the exemplary simulation condition recommended method of time sequence parameter according to the present invention cluster；
Fig. 2 is the schematic diagram according to the artificial tasks hierarchical structure of embodiments of the present invention；
Fig. 3 is the emulation time sequence parameter clustering block diagram according to embodiments of the present invention；
Fig. 4 is the signal updated according to the emulation time sequence status prediction of embodiments of the present invention and machine learning model
Figure.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Fig. 1 is the flow chart of the exemplary simulation condition recommended method of time sequence parameter according to the present invention cluster, below will ginseng
Fig. 1 is examined, the exemplary simulation condition recommended method of time sequence parameter cluster of the invention is described in detail.
Firstly, constructing service condition collection (Operating Conditions Set, OCS), path parameter in step 101
Collect (Path Parameter Set, PPS) and cell parameters collection (Cell Parameter Set, CPS).
Fig. 2 is the schematic diagram according to the artificial tasks hierarchical structure of embodiments of the present invention.As shown in Fig. 2, illustrating
The hierarchical structure explosion views of artificial tasks (Simulation Task) under normal circumstances, forCorresponding to one
Specific artificial tasks.According to the development of MCMM technology, each artificial tasks may include multiple scenes (Scenarios).
Meanwhile each scene, by constituting comprising one or more group of paths (Path Groups), each group of paths includes one or more
Paths (Paths, data path or clock path), and each path can all pass through one or more units (Cells).It presses
For the hierarchical structure, it can be separately included according to Simulation Task, Scenarios and Path Groups three first layers
Paths and the emulation time sequence parameter of Cells construct PPS and CPS, then by the way that ISODATA clustering circuit is whole or electricity
The time sequence status in road region；And be directed to Paths and Cells level, then when selecting the emulation of same Path or the same Cell
Order parameter constructs PPS and CPS, and passes through the time sequence status of ISODATA clustering circuit part.Pass through building and emulation
PPS corresponding to task hierarchical structure and CPS is, it can be achieved that the timing verification of circuit different levels structure is analyzed.It is each simultaneously
There is the primary and secondary dependence for clearly " including and constituting " between level, it, can be successively secondary in conjunction with existing temporal constraint principle
Apparent more fully analysis, which is controlled, to be realized to the time sequence status of circuit.
In this step, according to artificial circuit topological structure and artificial tasks hierarchical structure, reasonable artificial tasks are selected
Proper subclass and emulation time sequence parameter proper subclass construct OCS and PPS, CPS (wherein PPS and CPS at least constructs one) respectively, to grind
Study carefully the time sequence status feature that circuit is whole or part is under each operating mode.Specific steps are as follows:
1) service condition collection (Operating Conditions is constructed with the actual SPICE simulation run condition of circuit
Set, OCS), OCS includes: process (Process), voltage (Voltage), temperature (Temperature) and ageing time
Multiple parameters such as (Aging Time).
2) SPICE for completing circuit to all SPICE simulated conditions vectors in 1) is emulated, and resolves the circuit critical path
And the time sequence parameter of internal element；
3) using critical path or essential elements as research object, its comprehensive timing under the conditions of all simulation runs is joined
Number building set of data samples, wherein path parameter collection (Path Parameter Set, PPS) includes that the path launch clock prolongs
(launch clock path delay), data path delay (data path delay), capture clock path delay late
(capture clock path delay) and timing path relaxation (timing path slack)；The cell parameters collection, packet
Include delta delay (incremental delay), transit time (transition time) and arrival time (arrival
Time), a R is constructed respectively4And R3European sample space, PPS vector sum CPS vector is respectively in the sample space
Feature vector.
It may be noted that the time sequence parameter collection of building includes circuit hierarchical information.The building of PPS and CPS needs to be fit to same
Artificial tasks hierarchical structure, wherein first 3 layers likely correspond to mulitpath and multiple units, latter 2 layers then correspond to a paths
An or unit (single-pathway may also include multiple units).
In step 102, PPS and CPS is subjected to Z-score normalization, statistical analysis extracts typical statistic parameter.
In this step, PPS and CPS are subjected to Z-score normalization, need for different path or cell respectively into
Row statistical analysis extracts typical statistic parameter, such as sum, maximum value, minimum value, mean value, minimal characteristic distance, maximum feature away from
From determining the primary condition of ISODATA Clustering Model with reference to timing sequence library and temporal constraint.
In this step, in order to balance the contribution of each temporal aspect parameter, using Z-score feature normalization rule pair
Each parameter is standardized, so that the temporal aspect parameter of all path or cell obeys standardized normal distribution N (0,1).
In step 103, ISODATA clustering obtains the corresponding cluster classification of PPS and CPS.
ISODATA is introduced first, ISODATA, i.e. Iterative Self-organizing Data
Analysis Techniques Algorithm, iteration self-organizing data analysis algorithm are the bases in K-means clustering algorithm
On plinth, increase to cluster result " merging " and " division " two operations, and a kind of cluster of set algorithm operational parameter control is calculated
Method.Wherein, the selection of iterative parameter and the number of iterations all has an impact to cluster result.
By the redundancy of a large amount of emulation time sequence parameters of ISODATA cluster removal, so that the stronger timing ginseng of similitude
Number merger is same class, establishes screening rule and is recommended using navigating to suitable time sequence parameter and service condition as Typical Representative
User is used for timing verification and abnormality detection.Specifically, in this step, ISODATA clustering obtains time sequence parameter collection
The corresponding cluster classification of PPS and CPS selects timing nearest apart from class center in each classification to join according to minimal distance principle
Numerical example is represented as such time sequence parameter, and corresponding simulated conditions are as the operation item under circuit typical mode of operation
Part.That is, using simulation run conditional parameter corresponding to the temporal aspect vector nearest apart from each cluster centre as this
Service condition of the circuit under a certain typical mode of operation represents, i.e., all kinds of included artificial circuit timing shapes in cluster result
State belongs to the circuit typical mode of operation under typical service condition.
Fig. 3 is the emulation time sequence parameter clustering block diagram according to embodiments of the present invention.As shown in figure 3, giving
SPICE emulates the process of time sequence parameter collection PPS and CPS clustering, and introducing temporal constraint facilitates ISODATA Clustering Model
Rationally initialization, and cluster result is explained to analyze the typical circuit operating mode of each classification.According to minimum range
Principle pulls out the emulation time sequence parameter nearest apart from such center as representing from each cluster classification, carries out timing and tests
Card and analysis；The representation parameter maps corresponding simulated conditions and constitutes typical service condition subsetPass through
To time sequence parameter collection PPS and CPS using Z-score normalize and ISODATA clustering, it is intended to by with similar characteristic when
Order parameter is integrated into same category, removes bulk redundancy information, screens typical time sequence parameter and represents as timing verification and analysis,
To shorten the chip design cycle.
In this step, cluster is completed to all feature samples using ISODATA clustering algorithm, primary condition can root
It is constrained according to timing sequence library and correlation timing, the statistical result of joint PPS or CPS codetermines.
In step 104, supervised classification model is established, determines simulated conditions side corresponding to the different operating mode of circuit
Boundary.
In this step, it using cluster result label as the sample label of corresponding OCS, establishes pre- for new simulated conditions
The supervised classification model of its corresponding circuits time sequence status is surveyed, while determining simulated conditions corresponding to the different operating mode of circuit
Boundary is conducive to time sequence status prediction and abnormal conditions detection of the circuit under new simulated conditions.
Fig. 4 is the signal updated according to the emulation time sequence status prediction of embodiments of the present invention and machine learning model
Figure.As shown in figure 4, can also establish supervised classification model to subsequent simulation by the ISODATA cluster labels of emulation time sequence parameter
Circuit timing parameters state corresponding to condition is predicted and is distinguished.Existing simulated conditions collection OCS joint cluster labels are built
Vertical supervised learning model, to prejudge to the SPICE emulation time sequence status of circuit under new simulated conditions, verification process can
It is completed by SPICE emulation and temporal constraint.Since the machine learning models such as cluster, classify are larger to the dependence of sample,
Its precision and the independence of sample, typicalness and separability are closely related, therefore after new samples complete SPICE emulation, it can will be new
Simulated conditions and emulation time sequence parameter be included in OCS and PPS, CPS respectively, and then realize the update of Clustering Model and disaggregated model
Optimization further obtains and has more exemplary simulation service condition subset Ω '.
It, can be by the supervised classification model of foundation to the corresponding circuit of the simulated conditions when there is new artificial tasks creation
Time sequence status is prejudged, and is verified by SPICE emulation；If duplicate simulated conditions can be built by data with existing
The mode of vertical look-up table is directly searched to circuit sequence state corresponding to the condition, without carrying out SPICE emulation again.Meanwhile
New simulation run condition and emulation time sequence parameter can be used for updating OCS and PPS, CPS, and repeat 102-104 pairs of step
ISODATA Clustering Model and supervised classification model realization update optimization, obtain more typical simulation run condition subset and more quasi-
True simulated conditions distinguish boundary.That is, the operating mode in order to quickly distinguish and predict the circuit under subsequent simulation service condition,
Can exercise supervision to the simulation run conditional parameter collection constructed in step 101 time sequence parameter cluster result corresponding with its taxology
It practises, while newly-increased simulated conditions can also be used in the update optimization of Clustering Model and disaggregated model, further obtain more typical
Simulation run condition recommends user.
Secondary use ISODATA cluster analysis result establishes classical supervised classification model to simulation run conditional parameter collection
OCS is distinguished, and determines the simulated conditions boundary under different circuit operating patterns, and the timing for accelerating circuit subsequent simulation task is tested
Card and analysis.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer instruction, the computer
The step of exemplary simulation condition recommended method of above-mentioned time sequence parameter cluster is executed when instruction operation, the time sequence parameter cluster
Exemplary simulation condition recommended method referring to the introduction of preceding sections, repeat no more.
Those of ordinary skill in the art will appreciate that: the foregoing is only a preferred embodiment of the present invention, and does not have to
In the limitation present invention, although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art
For, still can to foregoing embodiments record technical solution modify, or to part of technical characteristic into
Row equivalent replacement.All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should all include
Within protection scope of the present invention.
Claims (9)
1. a kind of exemplary simulation condition recommended method of time sequence parameter cluster, which comprises the following steps:
1) service condition collection, path parameter collection and cell parameters collection are constructed；
2) the path parameter collection and the cell parameters collection are subjected to Z-score normalization, and extraction allusion quotation for statistical analysis
Type statistical parameter；
3) it carries out ISODATA clustering and obtains the path parameter collection and the corresponding cluster classification of the cell parameters collection；
4) supervised classification model is established, determines simulated conditions boundary corresponding to the different operating mode of circuit.
2. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that described
In step 1), according to artificial circuit topological structure and artificial tasks hierarchical structure, artificial tasks proper subclass and emulation timing are selected
Parameter proper subclass constructs service condition collection and path parameter collection or cell parameters collection respectively；
The building of path parameter collection or cell parameters collection is fit to same artificial tasks hierarchical structure, wherein first 3 layers correspond to it is more
Paths and multiple units, latter 2 layers then correspond to a paths or a unit, specific steps are as follows:
Service condition collection is constructed with the actual SPICE simulation run condition of circuit；
The SPICE emulation that circuit is completed for all SPICE simulated conditions vectors resolves the circuit critical path and internal list
The time sequence parameter of member；
Using critical path or essential elements as research object, its comprehensive time sequence parameter under the conditions of all simulation runs is constructed
Set of data samples；The set of data samples, including path parameter collection and cell parameters collection construct a R respectively4And R3It is European
Sample space, path parameter collection vector sum cell parameters collection vector are respectively the feature vector in the sample space.
3. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that the fortune
Row condition set, including, process, voltage, temperature and ageing time.
4. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that the road
Diameter parameter set, including, the path launch clock delay, data path delay, capture clock path delay and timing path pine
It relaxes；The cell parameters collection, including, delta delay, transit time and arrival time.
5. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that described
In step 2, path parameter collection and cell parameters collection are subjected to Z-score normalization, statistical analysis extracts typical statistic parameter；
With reference to timing sequence library and temporal constraint, the primary condition of ISODATA Clustering Model is determined, the typical statistic parameter includes total
Number, maximum value, minimum value, mean value, minimal characteristic distance, maximum characteristic distance.
6. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that the step
It is rapid 3), further comprise that time sequence parameter sample nearest apart from class center in each classification is selected according to minimal distance principle
Time sequence parameter as such represents, and corresponding simulated conditions are as the service condition under circuit typical mode of operation.
7. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that the step
It is rapid 4), further comprise, using cluster result label as the sample label of corresponding service condition collection, establishing supervised classification mould
Type for predicting its corresponding circuits time sequence status for new simulated conditions, while determining corresponding to the different operating mode of circuit
Simulated conditions boundary, for circuit under new simulated conditions time sequence status prediction and abnormal conditions detection.
8. the exemplary simulation condition recommended method of time sequence parameter cluster according to claim 1, which is characterized in that new sample
After this completion SPICE emulation, new simulated conditions and emulation time sequence parameter can be included in service condition collection and path parameter respectively
Collection, cell parameters collection update optimization Clustering Model and disaggregated model, further obtain and have more exemplary simulation service condition subset.
9. a kind of computer readable storage medium, is stored thereon with computer instruction, which is characterized in that the computer instruction fortune
Perform claim requires the step of exemplary simulation condition recommended method of 1 to 8 described in any item time sequence parameter clusters when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811601063.7A CN109670255B (en) | 2018-12-26 | 2018-12-26 | Typical simulation condition recommendation method for time sequence parameter clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811601063.7A CN109670255B (en) | 2018-12-26 | 2018-12-26 | Typical simulation condition recommendation method for time sequence parameter clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670255A true CN109670255A (en) | 2019-04-23 |
| CN109670255B CN109670255B (en) | 2020-04-07 |
Family
ID=66146235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811601063.7A Active CN109670255B (en) | 2018-12-26 | 2018-12-26 | Typical simulation condition recommendation method for time sequence parameter clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670255B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898335A (en) * | 2020-06-23 | 2020-11-06 | 北京大学 | Circuit reliability analysis method |
| CN112100158A (en) * | 2020-09-21 | 2020-12-18 | 海光信息技术有限公司 | Standard cell library establishing method and device, electronic equipment and storage medium |
| CN113806151A (en) * | 2021-09-07 | 2021-12-17 | 深圳宝新创科技股份有限公司 | Time sequence parameter determination method, device, electronic equipment and system |
| CN114626324A (en) * | 2022-02-24 | 2022-06-14 | 深圳市紫光同创电子有限公司 | Post-simulation verification method and device for FPGA circuit, electronic equipment and storage medium |
| CN116796209A (en) * | 2023-08-24 | 2023-09-22 | 北京安图生物工程有限公司 | Data processing method for monitoring storage environment temperature of detection kit |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08137974A (en) * | 1994-11-15 | 1996-05-31 | Toshiba Corp | Fund operation supporting device for automatic transaction device |
| CN107238817A (en) * | 2017-07-04 | 2017-10-10 | 中国人民解放军海军航空工程学院 | A kind of parameter adaptive setting and the radar emitter signal method for separating of adjust automatically |
| CN107895222A (en) * | 2017-10-26 | 2018-04-10 | 华北电力大学 | The bad Leakage Reactance discrimination method of transformer based on DBSCAN algorithms |
| CN108446412A (en) * | 2017-02-16 | 2018-08-24 | 龙芯中科技术有限公司 | Memory Compilation Method, device and the memory of generation |
-
2018
- 2018-12-26 CN CN201811601063.7A patent/CN109670255B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08137974A (en) * | 1994-11-15 | 1996-05-31 | Toshiba Corp | Fund operation supporting device for automatic transaction device |
| CN108446412A (en) * | 2017-02-16 | 2018-08-24 | 龙芯中科技术有限公司 | Memory Compilation Method, device and the memory of generation |
| CN107238817A (en) * | 2017-07-04 | 2017-10-10 | 中国人民解放军海军航空工程学院 | A kind of parameter adaptive setting and the radar emitter signal method for separating of adjust automatically |
| CN107895222A (en) * | 2017-10-26 | 2018-04-10 | 华北电力大学 | The bad Leakage Reactance discrimination method of transformer based on DBSCAN algorithms |
Non-Patent Citations (2)
| Title |
|---|
| 李志博: "射频电路多参数健康评估技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 梁涛: "模拟集成电路性能参数建模及其参数成品率估计算法的研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898335A (en) * | 2020-06-23 | 2020-11-06 | 北京大学 | Circuit reliability analysis method |
| CN112100158A (en) * | 2020-09-21 | 2020-12-18 | 海光信息技术有限公司 | Standard cell library establishing method and device, electronic equipment and storage medium |
| CN112100158B (en) * | 2020-09-21 | 2022-11-22 | 海光信息技术股份有限公司 | Standard cell library establishing method and device, electronic equipment and storage medium |
| CN113806151A (en) * | 2021-09-07 | 2021-12-17 | 深圳宝新创科技股份有限公司 | Time sequence parameter determination method, device, electronic equipment and system |
| CN113806151B (en) * | 2021-09-07 | 2024-01-02 | 深圳宝新创信息技术有限公司 | Time sequence parameter determining method, device, electronic equipment and system |
| CN114626324A (en) * | 2022-02-24 | 2022-06-14 | 深圳市紫光同创电子有限公司 | Post-simulation verification method and device for FPGA circuit, electronic equipment and storage medium |
| CN114626324B (en) * | 2022-02-24 | 2023-12-12 | 深圳市紫光同创电子有限公司 | FPGA circuit post-simulation verification method and device, electronic equipment and storage medium |
| CN116796209A (en) * | 2023-08-24 | 2023-09-22 | 北京安图生物工程有限公司 | Data processing method for monitoring storage environment temperature of detection kit |
| CN116796209B (en) * | 2023-08-24 | 2023-10-20 | 北京安图生物工程有限公司 | Data processing method for monitoring storage environment temperature of detection kit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109670255B (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670255A (en) | A kind of exemplary simulation condition recommended method of time sequence parameter cluster | |
| CN112100952B (en) | Post-simulation method and device for integrated circuit, electronic equipment and storage medium | |
| US7092845B2 (en) | Computational design methods | |
| US11836641B2 (en) | Machine learning-based prediction of metrics at early-stage circuit design | |
| CN111274134A (en) | Vulnerability identification and prediction method and system based on graph neural network, computer equipment and storage medium | |
| CN109657805A (en) | Hyper parameter determines method, apparatus, electronic equipment and computer-readable medium | |
| US11726899B2 (en) | Waveform based reconstruction for emulation | |
| US7249331B2 (en) | Architectural level throughput based power modeling methodology and apparatus for pervasively clock-gated processor cores | |
| US20110035203A1 (en) | system level power evaluation method | |
| US10699046B2 (en) | System and method for achieving functional coverage closure for electronic system verification | |
| CN114730352A (en) | Method and apparatus for machine learning based delay calculation and verification of integrated circuit design | |
| CN107909141A (en) | A kind of data analysing method and device based on grey wolf optimization algorithm | |
| KR101966558B1 (en) | System and method for visualizing equipment inventory status and repair parts procurement request | |
| CN115165332A (en) | Integrated design method and system for built-in test and comprehensive test of equipment | |
| US6847927B2 (en) | Efficient array tracing in a logic simulator machine | |
| CN117435505B (en) | Visual generation method of performance test script | |
| US11227090B2 (en) | System and method for achieving functional coverage closure for electronic system verification | |
| CN112783513A (en) | Code risk checking method, device and equipment | |
| CN117272896A (en) | Machine learning techniques for circuit design verification | |
| Bounceur et al. | A classification approach for an accurate analog/RF BIST evaluation based on the process parameters | |
| CN115184055A (en) | Method and system for determining test set with optimized hierarchical testability | |
| US20220390999A1 (en) | System and method for predicting power usage of network components | |
| US20220164511A1 (en) | Method and apparatus for power measurement in electronic circuit design and analysis | |
| US6829572B2 (en) | Method and system for efficiently overriding array net values in a logic simulator machine | |
| US11842130B1 (en) | Model-based simulation result predictor for circuit design |
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 | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100102 Beijing city two Chaoyang District Lize Road No. 2 A block 2 layer Patentee after: Beijing Huada Jiutian Technology Co.,Ltd. Address before: 100102 Beijing city two Chaoyang District Lize Road No. 2 A block 2 layer Patentee before: HUADA EMPYREAN SOFTWARE Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |