CN115348181B - Data transmission modeling method, system, equipment and storage medium - Google Patents
Data transmission modeling method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN115348181B CN115348181B CN202211271372.9A CN202211271372A CN115348181B CN 115348181 B CN115348181 B CN 115348181B CN 202211271372 A CN202211271372 A CN 202211271372A CN 115348181 B CN115348181 B CN 115348181B
- Authority
- CN
- China
- Prior art keywords
- transmission request
- transmission
- control parameters
- simulation
- request
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 290
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000000977 initiatory effect Effects 0.000 claims abstract description 69
- 238000004088 simulation Methods 0.000 claims abstract description 59
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000005094 computer simulation Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000013500 data storage Methods 0.000 claims description 38
- 239000003999 initiator Substances 0.000 claims description 35
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004806 packaging method and process Methods 0.000 claims 2
- 238000012546 transfer Methods 0.000 description 23
- 238000013461 design Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000005477 standard model Effects 0.000 description 2
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7807—System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package
- G06F15/7825—Globally asynchronous, locally synchronous, e.g. network on chip
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
Landscapes
- Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer And Data Communications (AREA)
Abstract
The invention provides a data transmission modeling method, a data transmission modeling system, data transmission modeling equipment and a data transmission modeling medium, wherein the method comprises the following steps: adding a plurality of control parameters to the transmission request at a transmission request initiating end according to a simulation modeling standard; receiving a transmission request at a target end of the transmission request, analyzing a plurality of corresponding control parameters in the transmission request, reading the control parameters according to a configuration strategy, processing the transmission request based on the configuration strategy and the control parameters, and counting the number of the transmission requests processed in a preset time and the corresponding control parameters; carrying out simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters; and establishing a new configuration strategy according to the simulation analysis result, applying the new configuration strategy to the next simulation transmission in preset time, and repeating the simulation process until an optimal configuration strategy is obtained. The modeling method for data transmission provided by the invention optimizes the code structure, meets the analysis requirement of more detailed performance simulation, has high simulation speed and good compatibility.
Description
Technical Field
The invention belongs to the field of computers, and particularly relates to a data transmission modeling method, a data transmission modeling system, data transmission modeling equipment and a storage medium.
Background
The design of SoC (System on Chip) is difficult due to its complexity, which encourages SystemC and electronic System level design (ESL) methodologies, and transaction level modeling is the key to electronic System level design. For a complex SoC, before performing RTL (Register Transfer Level) design, deep system Level simulation is required to confirm whether a designed architecture is proper, whether a bus can meet throughput and real-time requirements, and whether a memory is wasted. In order to shorten the design period of the key IP of SoC and assist the design process, and at the same time, in order to shorten the gap from the System architecture design to the implementation of the hardware RTL circuit, a modeling methodology is required to describe the functions and architecture of the whole circuit System, and at the same time, the functions and architecture are not involved in the complicated signal sequence and gate circuit of the hardware circuit, so that the ESL (Electronic System Level) Electronic System Level design comes into force. The system is described at a proper abstract level by adopting an ESL design methodology, a virtual hardware prototype platform is constructed, the exploration of a hardware architecture and the development of a software program are carried out, and the rapid system modeling and simulation analysis are realized. The core of ESL is TLM, a Transaction Level Modeling (TLM) method.
The TLM is higher than the RTL in abstraction level, and can quickly establish the executable specification of hardware and quickly establish a system model according to the initial functional specification of the system. By adding timing details into the system, the performance of the system can be evaluated, and the structure of the system can be explored.
With the increase of the computational complexity of communication terminals and devices in the future, the demand for the integration scale of real-time complex system chips will increase rapidly, tens or hundreds of processing units may be integrated on one chip, and the multi-core based signal processing platform becomes the development trend of software radio. In such a comprehensive System, designing a reliable, high-speed, low-power consumption, high-performance on-Chip communication System becomes a challenge and opportunity for System on Chip (SoC) development. Taking the SoC of a web server as an example, the key performance indexes include response delay, throughput, maximum concurrent connection number, system reliability and the like, and how to quickly and accurately perform quantitative evaluation and analysis on the performance indexes of the architecture design is a crucial topic.
In the process of performance modeling, when an important module which may become a performance bottleneck is modeled (for example, DDR, etc.), especially in the process of statistically analyzing the bandwidth of a module port, the module is required to record a notification of received read request/write request information, and also record information of an originating end of the request, such as an engine ID, data stream information, priority information, etc. of the originating end, so as to complete statistics of some specific information, such as statistics of a bandwidth ratio accessed by different engines on the port, thereby being capable of optimizing the design of the port and a system architecture.
However, when data in the system is communicated between modules, especially after being forwarded by a multi-level NoC (Network on Chip), after the modules receive information of a read request/write request, more information of an initiating end of the information cannot be obtained, so that it is difficult to further analyze performance on a port. Therefore, how to optimize the data transmission among the modules becomes a problem to be concerned in the performance modeling.
The existing data transmission method which can be realized by the open source model and the public data and meets the requirements has the following problems:
(1) Referring to public information, the standards of OSCI TLM2.0 (The Transaction Level Modeling standard of The Open system c Initiative, OSCI organization issued Transaction Level Modeling library version 2.0) provide a unified interface for communication between modules, separate The internal functions of The model from communication, and design a set of relatively universal transmission data structure and transmission protocol, wherein The data structure definition specified by The protocol includes: command type, initial address, data pointer, data length, byte enable width, response status, etc. In order to meet the requirement of characteristic customization, other information of the initiating terminal which necessarily represents control can be packaged and uniformly stored in a general transmission data structure in the implementation process, and then the information is transmitted. Although the mode meets the transmission format required by the protocol, the coupling of data is damaged, the functional data information and some control information cannot be conveniently distinguished, and the additional control information occupies the bandwidth resources of the ports of the initiating terminal and the target terminal, so that the accuracy of the bandwidth performance evaluation of the ports is influenced.
(2) At present, an open-source model is generally based on TLM2.0 universal interface transmission or customized expansion for a specific scene, and the requirement of a performance simulation refined scene cannot be met.
Therefore, an effective simulation modeling method is needed to solve the above problems.
Disclosure of Invention
In order to solve the above problem, the present invention provides a data transmission modeling method, which includes:
adding a plurality of control parameters to the transmission request at a transmission request initiating end according to a simulation modeling standard;
receiving the transmission request at a target end, analyzing a plurality of corresponding control parameters in the transmission request, reading the control parameters according to a configuration strategy, processing the transmission request based on the configuration strategy and the control parameters, and counting the number of the transmission requests processed in a preset time and the corresponding control parameters;
carrying out simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
and establishing a new configuration strategy according to the simulation analysis result, applying the new configuration strategy to the next simulation transmission in preset time, and repeating the simulation process until an optimal configuration strategy is obtained.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises: and adding the number of the initiator as the engine sequence number of the initiator into the transmission request.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
and generating a corresponding transmission request unique identifier for each transmission request, and adding the transmission request unique identifier into the transmission request.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
a priority is set for each transmission request and the priority is added to the transmission request.
In some embodiments of the invention, the method further comprises:
and sequencing the priorities of the plurality of transmission requests at the target end according to the priorities of the transmission requests, and preferentially processing the transmission requests sequenced at the top according to a sequencing result.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
a lock flag is set for each transmission request according to a transmission mode of the transmission request, and the lock flag is added to the transmission request.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
creating a data storage pool at a data starting end, and managing a transmission request of the starting end through the data storage pool; and
and adding corresponding control parameters for the transmission request in the data storage pool.
In some embodiments of the present invention, managing the transfer request of the initiator over the data storage pool comprises:
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to a target end.
In another aspect of the present invention, a data transmission modeling system is further provided, including:
the system comprises an initiating end and a target end, wherein the initiating end is configured to add a plurality of control parameters to a transmission request according to a simulation modeling standard and send the transmission request added with the control parameters to the target end;
the target terminal is configured to receive the transmission request, analyze a plurality of corresponding control parameters in the transmission request, read the control parameters according to a configuration policy, process the transmission request based on the configuration policy and the control parameters, and count the number of transmission requests processed within a predetermined time and the corresponding control parameters;
the data analysis module is configured to perform simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
and the simulation control module is configured to make a new configuration strategy according to the simulation analysis result of the data analysis module, apply the new configuration strategy to the simulation transmission of the next preset time, and repeat the simulation process until the optimal configuration strategy is obtained.
In some embodiments of the invention, the initiating end further comprises:
a data storage pool configured to manage the originating transport request.
In some embodiments of the invention, the initiating end is further configured to:
adding corresponding control parameters for the transmission request in the data storage pool; and
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to a target end.
In some embodiments of the invention, the system further comprises:
the control parameter resetting interface is configured with an engine serial number parameter for resetting an initiating end, a unique identification parameter for resetting a transmission request, a priority information parameter for resetting the transmission request and a locking mark corresponding to the transmission request;
the control parameter setting interface is configured to set an engine serial number parameter of an initiating end, set a unique identification parameter of a transmission request, set a priority information parameter corresponding to the transmission request, and set a locking mark corresponding to the transmission request.
In some embodiments of the invention, the system further comprises:
the system comprises a control parameter query interface, a control parameter query interface and a control parameter query interface, wherein the control parameter query interface is configured to acquire an engine serial number parameter of an initiating end, acquire a unique identification parameter of a transmission request, acquire a priority information parameter corresponding to the transmission request and acquire a locking mark corresponding to transmission of the transmission request.
Yet another aspect of the present invention also provides a computer apparatus, including:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method of any one of the above embodiments.
Yet another aspect of the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program realizes the steps of the method of any one of the above embodiments when executed by a processor.
By the modeling method for data transmission, disclosed by the invention, not only the TLM2.0 general clean core is effectively expanded, but also higher-layer management such as application, release, sequencing and the like is carried out on the expanded data structure. The code structure is optimized, the analysis requirement of more detailed performance simulation is met, and the simulation speed is high; has good compatibility. The expanded data part is encapsulated, functional data and control information are separated, a single access interface is provided inside, communication can be carried out with a standard model which accords with the TLM2.0 universal protocol, and the compatibility is better; when the scene does not need the extended information, the extended set of interfaces can be ignored, and special conversion logic is not required to be written; and the model of the standard protocol is convenient to interface. When the model has more new requirements, related parameters and methods can be conveniently added in the extension class, the original data management structure is not required to be changed, the extension cost is low, and more requirements can be met.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method of modeling data transmission according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a data transmission modeling system according to an embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a data transmission modeling system according to an embodiment of the present invention;
fig. 6 is a network topology relationship diagram of an initiating end and a target end in a data transmission modeling system according to an embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating the structural relationship of data storage pools, according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
The invention aims to solve the problem that when data are communicated among modules in a simulation system for data transmission of an AXI bus, particularly after the data are forwarded by a multi-stage NoC, the modules cannot acquire more information of an initiating end of the information after receiving information of a read request/write request, so that the performance on a port is difficult to further analyze.
As shown in fig. 1, to solve the above problem, the present invention provides a data transmission modeling method, including:
s1, adding a plurality of control parameters into a transmission request at a transmission request initiating end according to a simulation modeling standard;
s2, receiving the transmission request at a target end, analyzing a plurality of corresponding control parameters in the transmission request, reading the control parameters according to a configuration strategy, processing the transmission request based on the configuration strategy and the control parameters, and counting the number of transmission requests processed in a preset time and the corresponding control parameters;
s3, carrying out simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
and S4, establishing a new configuration strategy according to the simulation analysis result, applying the new configuration strategy to the next simulation transmission in preset time, and repeating the simulation process until an optimal configuration strategy is obtained.
In the embodiment of the present invention, in step S1, when performing simulation modeling on a chip, a plurality of control parameters are encapsulated into a new data structure (denoted as a transport structure) on the basis of a transport data structure (denoted as a general structure) specified by the standard of TLM2.0, and the transport structure is combined with the general structure in an additional manner to form a new transport request without changing the original general structure. When the initiating end sends a corresponding transmission request (only the original transmission request with a general structure), the process is executed to add corresponding control parameters to the transmission request to form a new transmission request and send the new transmission request to the bus.
It should be noted that the additional transmission structure adopted in the embodiment of the present invention does not affect data transmission on the bus, a module without the identification transmission structure can identify corresponding general structure data according to data specified by the TLM2.0 standard, the data of the transmission structure is not regarded as the data of the general structure, and only a target with identification capability can identify the corresponding additional transmission structure.
In step S2, the destination refers to a data receiving end on the bus, which is capable of receiving data of the conventional TLM2.0 and receiving a transmission request with a transmission structure. The configuration policy is a scheduling mechanism for handling transmission requests from each initiator, and is a request management policy for a data bus, such as, for example, a scheduling mechanism for preferentially handling transmission requests from a certain initiator, or a scheduling mechanism for allowing a certain initiator to transmit a large number of transmission requests within a certain time. Further, the target terminal analyzes the received transmission request, acquires the control parameter in the corresponding transmission structure, and judges whether to process the corresponding transmission request according to the set configuration strategy and the numerical content of the control parameter. The processing refers to a scheduling mechanism for different transmission requests, that is, a part of the transmission requests are preferentially processed, or transmission requests of a plurality of initiators are preferentially processed, or the number of transmission requests corresponding to the initiators is limited according to a configuration policy.
Further, all transmission requests received by the target end within a certain time are counted, and the corresponding transmission structure is stored. The general structure in the transmission request does not need to be stored, and only a plurality of control parameters in the transmission structure are stored, so that subsequent analysis is facilitated.
In step S3, the distribution of the initiator corresponding to the transmission request received by the target in step S2 and the transmission request initiated by the corresponding initiator are analyzed to determine which of the transmission requests of the initiator occupies the transmission request or the transmission bandwidth received by the current target, which affects the transmission balance of the system bus, and which of the initiators corresponding to which of the modules corresponds, and generate a corresponding constraint or excitation configuration policy for the next simulation. For example, in a mode of pursuing balance, if a data transmission request sent by a corresponding initiator is too high or a transmission request of one initiator processed by a target is too much, resulting in a large amount of blocked transmission requests of other initiators, then the transmission request of the initiator with too many transmission requests in the current simulation time is limited during simulation of the next predetermined time.
In step S4, according to the analysis result in step S3, that is, the corresponding configuration policy, the configuration policy is applied to the current target as a processing policy when the target receives the transmission request in the next predetermined time. Further, the above simulation process is repeated at intervals of a predetermined time until the analysis result in step S3 satisfies a predetermined performance index.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises: and adding the number of the initiator as the engine sequence number of the initiator into the transmission request.
In this embodiment, the engine serial number parameter of the originating terminal represents a unique identifier of the originating terminal, so as to distinguish which module the corresponding transmission request comes from. If the target end is interconnected with a plurality of initiating ends through the bus, when the target end receives data of a transmission request, the target end can know which initiating end the current request comes from through the engine sequence number parameter, and can perform statistical analysis on the request data received within a period of time to obtain the proportional relation between the request received within the period of time and different initiating ends, further, the target end can judge which initiating end the possibly existing bandwidth bottleneck comes from according to the proportional relation, and can further perform operations such as flow control and the like on a certain initiating end according to requirements, thereby providing effective help for the performance analysis of the system.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
and generating a corresponding transmission request unique identifier for each transmission request, and adding the transmission request unique identifier into the transmission request.
In this embodiment, the unique identifier of the transmission request refers to an ID number parameter of the transmitted request, which indicates that when an originating terminal continuously sends the request, the unique identifier of each request, for example, when an originating terminal continuously sends the request, the ID number of the request is: 0,1,2, …. Through the unique identification, it can be analyzed which transmission requests sent by the initiator are continuously sent in a short time in the transmission requests received by the current target, so as to analyze the data initiating capability of the corresponding initiator, and reasonably allocate tokens of the corresponding transmission requests.
Further, in some embodiments, in bus data transmission, an initiator sends data to a bus without free sending, and sends a corresponding number of tokens to a corresponding initiator by a target, and the corresponding initiator sends a corresponding transmission request according to the tokens, and consumes one token every time a transmission request is sent. Based on the data transmission requirement rule, the unique identification of the transmission request can distinguish the transmission request, and the data transmission requirement rule of the corresponding module behind the initiating terminal can be analyzed, so that the configuration strategy meeting the corresponding initiating terminal is formulated based on the rule.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiating end comprises:
a priority is set for each transmission request and the priority is added to the transmission request.
In this embodiment, the priority of the transmission request indicates whether a transmission request needs to be preferentially executed, and the priority level of the preferential execution may be divided according to actual requirements, for example, into 0 level, 1 level, and 2 level, taking a priority policy with a lower number and a higher priority as an example, when the priority of the first request is 1 level and the priority of the second request is 0 level, the second request may be preferentially executed in the requests buffered at the target end compared with the first request. In addition, the priority of the transmission request issued by the originating terminal is set by the application behind the corresponding originating terminal according to the needs of data transmission, the priority is usually multiple top levels, and the range of the priority acquired by each originating terminal in the predetermined time is different. For example, the highest priority of an initiator may be 0 for a predetermined time, that is, the initiator may send out request data with the highest priority, and the target port may preferentially process the transmission request when receiving the transmission request. At some time, the available range of the highest priority of the originating end may only be up to 1. In particular, different transmission priorities are determined according to different configuration strategies.
In some embodiments of the invention, the method further comprises:
and sequencing the priorities of the plurality of transmission requests at the target end according to the priorities of the transmission requests, and preferentially processing the transmission requests sequenced at the top according to a sequencing result.
In this embodiment, the target will sort according to the priority of the transmission request in the queue or buffer, and process the data with the highest priority preferentially.
In particular, in some embodiments of the present invention, during a period of simulation time, a target end may continuously receive multiple requests from multiple initiators, and the target end may further manage the received requests according to two information, i.e., an engine ID of the initiator and a transmitted request ID, individually buffer the multiple requests of each request end, and reorder the buffered requests according to priorities, thereby ensuring that some requests labeled as high priorities can be processed as soon as possible, so as to implement simulation analysis at the target end, configure different priorities of the requests according to simulation conditions, evaluate what influence may be brought at a system level, and find an optimal solution of request priority configuration that can improve system performance.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
a lock flag is set for each transmission request according to a transmission mode of the transmission request, and the lock flag is added to the transmission request.
In this embodiment, the locking flag indicates whether a port needs to lock a parameter when a current transmission request is transmitted, and indicates whether a configuration performed by a corresponding port needs to be locked when a certain transmission request of an initiator passes through a sending port of the initiator and a receiving port of a target. If the port needs to be locked, the port is in a locked state when the request passes through the current port, and any other request needs to be blocked and waited. If the configuration does not need to lock the port, when the request passes through the port, the behavior is non-invasive, other requests passing through the port are not influenced, and when some debugging analysis is carried out and the request not influencing normal communication is not wanted, the parameter can be configured to be in a non-locking state. The receiving port is also the same judgment mechanism. By configuring a request as either a locked port or an unlocked port, its impact on system performance metrics can be evaluated against each other.
In some embodiments of the present invention, the transmission of the bus data of the target end and the initiator end corresponding to the simulation phase is controlled by the four control parameters, i.e., the engine serial number, the unique identifier of the transmission request, the priority of the transmission request, and the locking flag, and different configuration strategies are specified, so that the optimal configuration strategy is found by multiple times of simulation.
In some embodiments of the present invention, adding a plurality of control parameters to the transfer request according to the simulation modeling standard at the transfer request initiation end comprises:
creating a data storage pool at a data starting end, and managing a transmission request of the starting end through the data storage pool; and
and adding corresponding control parameters for the transmission request in the data storage pool.
In some embodiments of the present invention, managing the transfer request of the initiator over the data storage pool comprises:
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to a target end.
In this embodiment, a virtual data storage pool is defined inside the initiator, which may be a continuous space. And a method of managing the data storage pool is devised. The method specifically comprises the steps of applying for, releasing, prioritizing and the like for the data storage pool. When receiving a transmission request (general structure) which is sent by other application modules from the rear end of an initiating end and needs to be sent by the initiating end, preferentially applying for a space at the level of a data storage pool, wherein the unit of application is the data type of a transmission structure; and then further data processing is carried out at the level of the transmission structure, namely the general structure and the transmission structure are spliced and sent out.
The method for managing the data storage pool is described in detail as follows:
(1) The application method of the data storage pool comprises the following steps: when data to be transmitted is constructed, firstly, space application is carried out in a data storage pool, and the unit of the application is the data type of a transmission structure; initializing and transmitting the transmission structure through a corresponding control parameter setting interface for setting control parameters;
(2) The method for releasing the data storage pool comprises the following steps: when the transmission is finished (for example, a request processing completion flag from the target end is received), the block space in the data storage pool needs to be released;
(3) The priority ordering method of the data storage pool comprises the following steps: in the transmission process, due to the continuous transmission mode of the request supporting multiple transmissions, multiple data to be transmitted may be prepared at the initiating end, and the data in the data pool can be prioritized according to the actually required strategy, and the priority information is supplemented to the transmission and is preferentially transmitted.
In some embodiments of the invention, a method interface is provided in the simulation system that operates on the above-described control parameters based on these parameters. The method specifically comprises method interfaces such as parameter setting, parameter query, parameter resetting and the like. Generally, an initiating terminal calls a parameter setting method and a parameter resetting method; the method for querying the parameters is called by the target terminal.
The parameter setting method comprises the following steps: setting an engine serial number parameter of an initiating end, setting an ID serial number parameter of a transmitted request, setting a priority information parameter of a current request, and setting whether a port needs to lock the parameter when the current request is transmitted;
the parameter query method comprises the following steps: inquiring an engine serial number parameter of an initiating end, inquiring an ID serial number parameter of a transmitted request, inquiring a priority information parameter of a current request, and inquiring whether a port needs to lock the parameter when the current request is transmitted;
the parameter resetting method comprises the following steps: resetting an engine serial number parameter of an initiating end, resetting an ID serial number parameter of a transmitted request, resetting a priority information parameter of a current request, and resetting whether a port needs to lock the parameter when the current request is transmitted.
Example (b):
the building model in the simulation software constructs a virtual platform, and the interconnection architecture among the modules is shown in fig. 6: the modules A, B, …, N and the like are interconnected with the target end by adopting the transaction-level port through the interconnection network to communicate the read-write request of the AXI protocol.
The module A, the module B, the module … and the module N are all initiating end modules, the middle NoC module is an interconnection component, the module A, the module B and the module N … are connected to corresponding receiving ports of the interconnection component of the NoC (Network on Chip) module through respective initiating end ports, and after address routing is carried out on the NoC module, the NoC module is connected to a receiving port of a target end through the initiating end port, so that a simple interconnection relation is realized. In the interconnection bus, a module A, a module B, …, a module N is an initiating terminal, a target terminal is a target terminal, and the module A, the module B, … communicate with the target terminal through forwarding and connection of the interconnection bus.
Taking the module a as an example, a modeling method for transmission data expansion is designed inside. A virtual data storage pool myTransPool is defined at the initiator.
At the transmission starting moment, firstly, space application is carried out in a data storage pool, the unit of the application is the data type of one transmission structure (denoted as myTrans), and the application method of the data storage pool is called sequentially, and the transmission structure is applied and denoted as: myTrans0, …, myTrans n, each of which includes a generic structure (denoted gen _ tlm _ payload) and an extended portion (the extended portion is recorded as my _ payload); and when the transmission is finished, releasing the applied transmission structure. The topological relationship of the data storage pools defined within module A is shown in FIG. 7:
the module a calls an internal parameter setting method to initialize the myTrans0, … and myTrans n, for example: setting the engine sequence number parameter of an initiating end to be 0 for each myTrans call, and indicating that the current request comes from the module A; setting ID serial number parameters of transmitted requests, and sequentially setting the ID serial number parameters to be 0,1,2,3 and … N; setting the priority information parameter of the current request as priority 0, which indicates that the priorities of the requests of the module A are all the highest; and setting whether the port needs to be locked when the current request is transmitted as a lock, wherein the lock indicates that the port is locked when the request is transmitted through the port.
In the same way, the sending data of module B is initialized: setting the engine sequence number parameter of an initiating end to be 1 for each myTrans call, and indicating that the current request comes from the module B; setting ID serial number parameters of transmitted requests, and sequentially setting the ID serial number parameters to be 0,1,2,3 and … N; setting the priority information parameter of the current request as priority 1, which indicates that the priority of the request of the module B is lower than that of the request of the module A; and setting whether the port needs to be locked when the current request is transmitted as a lock, wherein the lock indicates that the port is locked when the request is transmitted through the port.
At the target, all requests from module a and module B are received: the total number of requests from the module A and the module B and the proportion of the requests on a receiving port can be respectively counted through the engine serial number parameter of the initiating end of each request; for example: if the request from module A is found to account for 90% of the time, the request from module B accounts for 10%; at this time, if the performance indexes of the system, such as IOPS, do not meet the design requirements, the performance indexes can be fed back to the architecture designer, the bandwidth occupied by each module on the port of the receiving end can be limited, or the request priorities of the module a and the module B are adjusted, so that the influence on the performance is explored and evaluated.
And re-performing simulation modeling operation according to the reset configuration strategy to verify the performance of the configuration strategy.
By the modeling method for data transmission, disclosed by the invention, not only the TLM2.0 general clean core is effectively expanded, but also higher-layer management such as application, release, sequencing and the like is carried out on the expanded data structure. The code structure is optimized, the analysis requirement of more detailed performance simulation is met, and the simulation speed is high; has good compatibility. The expanded data part is encapsulated, functional data and control information are separated, a single access interface is provided inside, communication can be carried out with a standard model which accords with the TLM2.0 universal protocol, and the compatibility is better; when the scene does not need the extended information, the extended set of interfaces can be ignored, and special conversion logic is not required to be written; and the model of the standard protocol is convenient to interface. When the model has more new requirements, related parameters and methods can be conveniently added in the extension class, the original data management structure is not required to be changed, the extension cost is low, and more requirements can be met.
As shown in fig. 2, another aspect of the present invention further provides a data transmission modeling system, including:
the system comprises an initiating terminal 1, a target terminal and a plurality of control parameters, wherein the initiating terminal 1 is configured to add a plurality of control parameters to a transmission request according to a simulation modeling standard and send the transmission request added with the control parameters to the target terminal;
a target 2, where the target 2 is configured to receive the transmission request and analyze a plurality of corresponding control parameters in the transmission request, read the control parameters according to a configuration policy, process the transmission request based on the configuration policy and the control parameters, and count the number of transmission requests processed within a predetermined time and the corresponding control parameters;
the data analysis module 3 is configured to perform simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
and the simulation control module 4 is configured to make a new configuration strategy according to a simulation analysis result of the data analysis module, apply the new configuration strategy to simulation transmission of the next preset time, and repeat a simulation process until an optimal configuration strategy is obtained.
As shown in fig. 5, in some embodiments of the present invention, the initiating terminal 1 further comprises:
a data storage pool 5, said data storage pool 5 configured to manage said originating transport request.
In some embodiments of the present invention, the initiating terminal 1 is further configured for:
adding corresponding control parameters for the transmission request in the data storage pool 5; and
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to the target end 2.
As shown in fig. 5, in some embodiments of the invention, the system further comprises:
a control parameter reset interface 6, wherein the control parameter reset interface 6 is configured to reset an engine serial number parameter of an initiating terminal, reset a unique identification parameter of a transmission request, reset a priority information parameter of the transmission request, and reset a locking flag corresponding to the transmission request;
a control parameter setting interface 7, wherein the control parameter setting interface 7 is configured to set an engine sequence number parameter of an initiating terminal, set a unique identification parameter of a transmission request, set a priority information parameter corresponding to the transmission request, and set a locking flag corresponding to the transmission request.
As shown in fig. 5, in some embodiments of the invention, the system further comprises:
and the control parameter query interface 8 is configured to acquire an engine serial number parameter of an initiating end, acquire a unique identification parameter of a transmission request, acquire a priority information parameter corresponding to the transmission request, and acquire a locking mark corresponding to transmission of the transmission request.
As shown in fig. 3, another aspect of the present invention also provides a computer device, including:
at least one processor 21; and
a memory 22, wherein the memory 22 stores computer instructions 23 executable on the processor 21, and when executed by the processor 21, the instructions 23 implement the steps of the method according to any one of the above embodiments.
As shown in fig. 4, a further aspect of the present invention also proposes a computer-readable storage medium 401, which stores a computer program 402, and the computer program 402 implements the steps of the method according to any one of the above embodiments when being executed by a processor.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of an embodiment of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (15)
1. A data transmission modeling method, comprising:
adding a plurality of control parameters to the transmission request at a transmission request initiating end according to a simulation modeling standard;
receiving the transmission request at a target end, analyzing a plurality of corresponding control parameters in the transmission request, reading the control parameters according to a configuration strategy, processing the transmission request based on the configuration strategy and the control parameters, and counting the number of the transmission requests processed in a preset time and the corresponding control parameters;
carrying out simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
making a new configuration strategy according to the simulation analysis result, applying the new configuration strategy to the next simulation transmission in preset time, and repeating the simulation process until an optimal configuration strategy is obtained;
the adding a plurality of control parameters to the transmission request according to the simulation modeling standard at the transmission request initiating end comprises:
packaging the control parameters into a new data structure, and combining the data structure with a general structure in an additional mode to generate a new transmission request;
the step of making a new configuration strategy according to the simulation analysis result, applying the new configuration strategy to the next simulation transmission in preset time, and repeating the simulation process until an optimal configuration strategy is obtained comprises the following steps:
and repeating the simulation process at intervals of preset time until the analysis result meets the preset performance index.
2. The method of claim 1, wherein adding a plurality of control parameters to the transmission request at the transmission request initiation end according to a simulation modeling standard comprises: and adding the number of the initiator as the engine sequence number of the initiator into the transmission request.
3. The method of claim 1, wherein adding a plurality of control parameters to the transmission request at the transmission request initiation end according to a simulation modeling standard comprises:
and generating a corresponding transmission request unique identifier for each transmission request and adding the transmission request unique identifier into the transmission request.
4. The method of claim 1, wherein adding a plurality of control parameters to the transmission request at the transmission request initiation end according to a simulation modeling standard comprises:
a priority is set for each transmission request and the priority is added to the transmission request.
5. The method of claim 4, further comprising:
and sequencing the priorities of the plurality of transmission requests at the target end according to the priorities of the transmission requests, and preferentially processing the transmission requests sequenced at the top according to a sequencing result.
6. The method of claim 1, wherein adding a plurality of control parameters to the transmission request at the transmission request initiation end according to a simulation modeling standard comprises:
a lock flag is set for each transmission request according to a transmission mode of the transmission request, and the lock flag is added to the transmission request.
7. The method of claim 1, wherein adding a plurality of control parameters to the transmission request at the transmission request initiation end according to a simulation modeling standard comprises:
creating a data storage pool at a data starting end, and managing a transmission request of the starting end through the data storage pool; and
and adding corresponding control parameters for the transmission request in the data storage pool.
8. The method of claim 7, wherein managing the originating transport request over the data storage pool comprises:
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to a target end.
9. A data transmission modeling system, comprising:
the system comprises an initiating end and a target end, wherein the initiating end is configured to add a plurality of control parameters to a transmission request according to a simulation modeling standard and send the transmission request added with the control parameters to the target end;
the target end is configured to receive the transmission request, analyze a plurality of corresponding control parameters in the transmission request, read the control parameters according to a configuration policy, process the transmission request based on the configuration policy and the control parameters, and count the number of transmission requests processed in a predetermined time and the corresponding control parameters;
the data analysis module is configured to perform simulation analysis through the counted transmission request number processed in the preset time and the corresponding control parameters;
the simulation control module is configured to make a new configuration strategy according to a simulation analysis result of the data analysis module, apply the new configuration strategy to simulation transmission of the next preset time, and repeat a simulation process until an optimal configuration strategy is obtained;
the adding of the plurality of control parameters to the transmission request according to the simulation modeling standard comprises:
packaging the control parameters into a new data structure, and combining the data structure with a general structure in an additional mode to generate a new transmission request;
the step of formulating a new configuration strategy according to the simulation analysis result of the data analysis module, applying the new configuration strategy to the simulation transmission of the next preset time, and repeating the simulation process until the optimal configuration strategy is obtained comprises the following steps:
and repeating the simulation process at intervals of preset time until the analysis result meets the preset performance index.
10. The system of claim 9, wherein the initiating end further comprises:
a data storage pool configured to manage the originating transport request.
11. The system of claim 10, wherein the initiating end is further configured to:
adding corresponding control parameters for the transmission request in the data storage pool; and
and sequencing the transmission requests in the data storage pool according to the transmission request priority in the control parameters of the transmission requests and preferentially sending the transmission requests with high priority to a target end.
12. The system of claim 9, further comprising:
the control parameter resetting interface is configured with an engine serial number parameter for resetting an initiating end, a unique identification parameter for resetting a transmission request, a priority information parameter for resetting the transmission request and a locking mark corresponding to the transmission request;
the control parameter setting interface is configured to set an engine serial number parameter of an initiating end, set a unique identification parameter of a transmission request, set a priority information parameter corresponding to the transmission request, and set a locking mark corresponding to the transmission request.
13. The system of claim 9, further comprising:
the system comprises a control parameter query interface, a control parameter query interface and a control parameter query interface, wherein the control parameter query interface is configured to acquire an engine serial number parameter of an initiating end, acquire a unique identification parameter of a transmission request, acquire a priority information parameter corresponding to the transmission request and acquire a locking mark corresponding to transmission of the transmission request.
14. A computer device, comprising:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method of any one of claims 1 to 8.
15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271372.9A CN115348181B (en) | 2022-10-18 | 2022-10-18 | Data transmission modeling method, system, equipment and storage medium |
| PCT/CN2023/082590 WO2024082537A1 (en) | 2022-10-18 | 2023-03-20 | Data transmission modeling method and system, device, and non-volatile readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211271372.9A CN115348181B (en) | 2022-10-18 | 2022-10-18 | Data transmission modeling method, system, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115348181A CN115348181A (en) | 2022-11-15 |
| CN115348181B true CN115348181B (en) | 2023-03-17 |
Family
ID=83957681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211271372.9A Active CN115348181B (en) | 2022-10-18 | 2022-10-18 | Data transmission modeling method, system, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115348181B (en) |
| WO (1) | WO2024082537A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115348181B (en) * | 2022-10-18 | 2023-03-17 | 苏州浪潮智能科技有限公司 | Data transmission modeling method, system, equipment and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4656929B2 (en) * | 2003-11-18 | 2011-03-23 | クイックターン・デザイン・システムズ・インコーポレイテッド | Optimized interface for simulation and visualization data transfer between emulation system and simulator |
| CN103970939A (en) * | 2014-04-22 | 2014-08-06 | 南京航空航天大学 | Layering and reconfigurable on-chip network modeling and simulation system |
| US10635843B2 (en) * | 2015-06-04 | 2020-04-28 | Synopsys, Inc. | Simulation modeling frameworks for controller designs |
| CN111173510A (en) * | 2020-03-14 | 2020-05-19 | 天地科技股份有限公司 | Intelligent control method and system for fully mechanized mining equipment for complex condition working face |
| CN113408139B (en) * | 2021-06-30 | 2023-01-20 | 中国南方电网有限责任公司 | Power communication network path control simulation verification method, device, equipment and medium |
| CN114238177B (en) * | 2021-12-01 | 2022-05-31 | 苏州浪潮智能科技有限公司 | AXI bus communication method, apparatus, device, and medium |
| CN114064562A (en) * | 2022-01-17 | 2022-02-18 | 苏州浪潮智能科技有限公司 | ESL modeling method, device, equipment and medium for network on chip |
| CN115348181B (en) * | 2022-10-18 | 2023-03-17 | 苏州浪潮智能科技有限公司 | Data transmission modeling method, system, equipment and storage medium |
-
2022
- 2022-10-18 CN CN202211271372.9A patent/CN115348181B/en active Active
-
2023
- 2023-03-20 WO PCT/CN2023/082590 patent/WO2024082537A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024082537A1 (en) | 2024-04-25 |
| CN115348181A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6353084B2 (en) | Transactional traffic specifications for network-on-chip designs | |
| US7069204B1 (en) | Method and system for performance level modeling and simulation of electronic systems having both hardware and software elements | |
| US9213666B2 (en) | Providing a sideband message interface for system on a chip (SoC) | |
| US9495290B2 (en) | Various methods and apparatus to support outstanding requests to multiple targets while maintaining transaction ordering | |
| US6970966B2 (en) | System of distributed microprocessor interfaces toward macro-cell based designs implemented as ASIC or FPGA bread boarding and relative common bus protocol | |
| JP5948628B2 (en) | Storage system and method | |
| US20160188501A1 (en) | Reordering Responses in a High Performance On-Chip Network | |
| WO2001093477A1 (en) | Communication system and method for different quality of service guarantees for different data flows | |
| CN113656227B (en) | Chip verification method and device, electronic equipment and storage medium | |
| KR20100017897A (en) | Shared storage for multi-threaded ordered queues in an interconnect | |
| US8504992B2 (en) | Method and apparatus for establishing a quality of service model | |
| US20020124085A1 (en) | Method of simulating operation of logical unit, and computer-readable recording medium retaining program for simulating operation of logical unit | |
| CN115348181B (en) | Data transmission modeling method, system, equipment and storage medium | |
| US10896476B2 (en) | Repository of integration description of hardware intellectual property for NoC construction and SoC integration | |
| WO2023169032A1 (en) | Memory delay modeling method and apparatus, device and medium | |
| Klingauf et al. | GreenBus: a generic interconnect fabric for transaction level modelling | |
| CN115622896A (en) | AXI4 high-speed bus and multi-queue simulation verification method and simulation verification device | |
| CN115809620A (en) | Method for simulating logic system design, electronic device and storage medium | |
| CN113553279B (en) | RDMA communication acceleration set communication method and system | |
| Harbin et al. | GMCB: An industrial benchmark for use in real-time mixed-criticality networks-on-chip | |
| Ma et al. | AXI, APB and AXI NOC Model Design Based on SysmteC | |
| Kosonen | NETWORK-ON-CHIP PERFORMANCE MODELING | |
| Medina et al. | Full System Exploration of On-Chip Wireless Communication on Many-Core Architectures | |
| CN115114876A (en) | Method, system, equipment and storage medium for accessing internal bus | |
| CN116932151A (en) | Transaction processing method, device, equipment and storage medium |
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 |