A chip data transmission method, apparatus, device, and storage medium
By introducing burst transmission reassembly and address interleaving control modules into the chip, the problem of insufficient bandwidth in chip data transmission is solved, multi-channel parallel transmission is realized, and the efficiency of the memory system is improved.
Patent Information
- Application Number
- CN202311347876.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-10-17
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-10-17
AI Technical Summary
In existing technologies, chips use only one channel for data transmission, which severely reduces the bandwidth of the memory system and fails to meet the requirements for efficient data transmission.
The burst transmission reassembly module splits the data to be transmitted and uses the address interleaving control module for address mapping to achieve multi-channel parallel data transmission.
It improves the overall bandwidth and operating efficiency of the memory system and enables multi-channel parallel transmission of the memory system.
Smart Images

Figure CN117435527B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data processing technology, and in particular to a chip data transmission method, apparatus, device, and storage medium. Background Technology
[0002] Chips contain on-chip networks or buses for data transmission, typically used to connect the core, DMA, IP, storage systems, and other peripherals. Among these, access to the storage system generally has the highest bandwidth requirements, determining the overall system efficiency.
[0003] Existing memory systems fall into two main categories: off-chip memory and on-chip memory. Off-chip memory, such as common DDR and HBM, consists of memory chips packaged outside the chip and connected to the system bus via a high-speed PHY and memory controller. On-chip memory includes Random Access Memory (RAM) and Read-Only Memory (ROM). RAM used for program execution and data processing, in particular, has higher system performance requirements.
[0004] In existing chips, only one channel is active during data transmission, failing to achieve parallel operation of the memory system, resulting in a significant reduction in bandwidth. Summary of the Invention
[0005] This invention provides a chip data transmission method, apparatus, device, and storage medium to achieve multi-channel parallel data transmission, effectively improving the transmission bandwidth and efficiency of chip memory systems.
[0006] According to one aspect of the present invention, a chip data transmission method is provided, the method comprising:
[0007] It acquires the data to be transmitted and operation instructions input from the external bus, and acquires the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions;
[0008] The data to be transmitted is split according to the configuration parameters to generate each split data;
[0009] Each split data segment is address-mapped to generate its own mapped data, and data is transferred based on the mapped data and operation instructions.
[0010] Optionally, obtaining the configuration parameters of the memory system includes: obtaining a list of configuration items, obtaining the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; obtaining the interleaving granularity set by the user, and using the target cluster bit width and interleaving granularity as configuration parameters.
[0011] Optionally, the data to be transmitted is split according to the configuration parameters to generate each split data, including: determining the target burst length according to the configuration parameters; performing a specified format conversion on the interleaving granularity to determine the number of bytes to be added to the address; splitting the data to be transmitted according to the target burst length and the number of bytes to be added to the address to generate each split data, wherein the corresponding address of each split data increases sequentially according to the number of bytes to be added to the address.
[0012] Optionally, the target burst length can be determined based on configuration parameters, including: converting the interleaving granularity to a specified unit to generate a conversion granularity; and using the ratio of the conversion granularity to the target cluster bit width as the target burst length.
[0013] Optionally, address mapping is performed on each split data to generate each mapped data, including: taking each split data as target data in sequence; determining the data address corresponding to the target data; and swapping the first specified position and the second specified position in the data address to generate the mapped data.
[0014] Optionally, data transmission is performed based on each mapping data and operation instruction, including: sequentially using each mapping data as target transmission data and determining the target address corresponding to the target transmission data; obtaining the address range of each channel of the memory system and determining the target channel corresponding to the target address based on the address range; transmitting the target transmission data according to the operation instruction and target channel, and obtaining response data, wherein the response data includes success and error; and generating prompt information based on each response data.
[0015] Optionally, a prompt message can be generated based on each response data, including: determining whether each response data is successful; if so, generating a prompt message indicating successful transmission; otherwise, using the data that is erroneous as the target response data and generating a prompt message based on the target response data.
[0016] According to another aspect of the present invention, a chip data transmission device is provided, the device comprising:
[0017] The data and configuration parameter acquisition module is used to acquire the data to be transmitted and operation instructions input from the external bus, and to acquire the configuration parameters of the memory system. The operation instructions include read instructions and write instructions.
[0018] The split data generation module is used to split the data to be transmitted according to the configuration parameters to generate each split data;
[0019] The data mapping and transmission module is used to map the addresses of each split data to generate each mapped data, and to transmit data according to each mapped data and operation instructions.
[0020] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0021] At least one processor; and
[0022] A memory communicatively connected to the at least one processor; wherein,
[0023] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform a chip data transmission method according to any embodiment of the present invention.
[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement a chip data transmission method according to any embodiment of the present invention.
[0025] The technical solution of this invention uses a burst transmission and reassembly module to split the data to be transmitted according to the interleaving granularity in the memory system configuration parameters, and an address interleaving control module to perform address mapping on the split data, thus realizing address-interleaved data transmission, achieving parallel operation of the multi-channel memory system, improving the overall bandwidth of the memory system, and also improving the operating efficiency of the memory system.
[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0028] Figure 1 This is a flowchart of a chip data transmission method provided according to Embodiment 1 of the present invention;
[0029] Figure 2 This is a flowchart of another chip data transmission method provided in Embodiment 1 of the present invention;
[0030] Figure 3 This is a schematic diagram of data splitting for a write instruction according to Embodiment 1 of the present invention;
[0031] Figure 4 This is a schematic diagram of the structure of a burst transmission reassembly module according to Embodiment 1 of the present invention;
[0032] Figure 5 This is a schematic diagram of address interleaving mapping provided in Embodiment 1 of the present invention;
[0033] Figure 6 This is a flowchart of another chip data transmission method provided according to Embodiment 2 of the present invention;
[0034] Figure 7 This is a schematic diagram of a chip data transmission device according to Embodiment 3 of the present invention;
[0035] Figure 8 This is a schematic diagram of the structure of an electronic device that implements a chip data transmission method according to an embodiment of the present invention. Detailed Implementation
[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0038] Example 1
[0039] Figure 1 This is a flowchart illustrating a chip data transmission method according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving data writing and reading from a chip memory system. The method can be executed by a chip data transmission device, which can be implemented in hardware and / or software and can be configured within the chip. Figure 1 As shown, the method includes:
[0040] S110. Obtain the data to be transmitted and operation instructions input from the external bus, and obtain the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions.
[0041] The external bus refers to the external AXI bus connected to the chip and used to access the memory system. The external bus width is generally higher than the internal memory system bus width to ensure the memory system can achieve higher system bandwidth. Operation instructions include read and write instructions, used to read and write data to the chip's memory system, respectively. Configuration parameters refer to the configuration parameters of the memory system's external interface, including the user-configured chip width and interleaving granularity. In this embodiment, data transmission is mainly achieved through two modules: a burst transmission reassembly module and an address interleaving control module. The burst transmission reassembly module splits the data to be transmitted according to the configuration parameters, while the address interleaving control module maps addresses, thereby achieving parallelism in the multi-channel memory system and improving the overall bandwidth of the memory system.
[0042] Optionally, obtaining the configuration parameters of the memory system includes: obtaining a list of configuration items, obtaining the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; obtaining the interleaving granularity set by the user, and using the target cluster bit width and interleaving granularity as configuration parameters.
[0043] Specifically, the burst transmission and reassembly module allows for parameter configuration, meaning the data bit width supported by the slave device can be configured. This can be done via parameter transmission, where users can select the target slave bit width from a configuration item list, which can include 32 / 64 / 128 / 256 / 512 / 1024 bits, etc. Simultaneously, users can also configure the interleaving granularity, with options including 4 / 8 / 16 / 32 / 64 / 128 / 256 bytes. The chip uses the target slave bit width and interleaving granularity as configuration parameters. The downstream slave bit width can be flexibly parameterized through the burst transmission and reassembly module, adapting to different downstream slave systems; the interleaving granularity can be flexibly configured through the parameterized interleaving granularity within the burst transmission and reassembly module.
[0044] S120. The data to be transmitted is split according to the configuration parameters to generate each split data.
[0045] Specifically, when splitting data, the burst transmission reassembly module divides the relatively wide external AXI bus into burst transmissions with narrower data bit widths, according to the flexibly configurable interleaving granularity.
[0046] Figure 2This invention provides a flowchart of a chip data transmission method according to Embodiment 1. Step S120 mainly includes the following steps S121 to S123:
[0047] S121. Determine the target burst length based on the configuration parameters.
[0048] Optionally, the target burst length can be determined based on configuration parameters, including: converting the interleaving granularity to a specified unit to generate a conversion granularity; and using the ratio of the conversion granularity to the target cluster bit width as the target burst length.
[0049] Specifically, when determining the target burst length, the interleaving granularity needs to be converted to a specified unit to generate a converted granularity. The unit of the converted granularity is the same as the unit of the target cluster bit width. Then, the target burst length can be determined based on the ratio of the converted granularity to the target cluster bit width.
[0050] For example, when the slave bit width is 512 bits, the interleaving granularity is 128 bytes, the master data bit width is 1024 bits, and the burst length of the transmission is 8, such as Figure 3 As shown. Figure 3 This invention provides a schematic diagram of data splitting for write instructions in Embodiment 1. Figure 3 The diagram shows the data before and after splitting the AW channel data. The burst transmission reassembly module needs to split the burst transmission input from the external AXI bus. Since the interleaving granularity is 128 bytes, the corresponding conversion granularity is 1024 bits, and the slave bit width is 512 bits, the target burst length can be determined to be 2, that is, the original burst transmission needs to be split into transmissions with a fixed burst length of 2.
[0051] S122. Perform a specified format conversion on the interleaving granularity to determine the number of bytes added to the address.
[0052] Specifically, when the interleaving granularity is 1024 bits, the interleaving granularity can be converted to hexadecimal, so the number of bytes added to the address each time is 0x80.
[0053] S123. The data to be transmitted is split into segments based on the target burst length and the number of bytes added to the address, thereby generating each segmented data segment. The address of each segmented data segment is incremented sequentially according to the number of bytes added to the address.
[0054] Specifically, Figure 3In this process, each instruction on the external AXI bus AW channel is broken down into eight sub-instructions, with the address increasing by the number of bytes interleaved each time. For the W data channel, the first AW command carries W channel data in two separate transactions: bits 0-511 and bits 1023-512 of the original data. The second AW command carries W channel data in two separate transactions: bits 511-0 and bits 1023-512 of the original data 1, and so on. Similarly, when the operation instruction is to read data, a similar operation occurs: an external AXI bus AR read command is broken down into eight internal AXI bus AR read command operations, with the address increasing by 0x80 each time. For reading data, the internal AXI bus returns 512 bits of data. Two consecutive 512-bit data points at address 0x0 are concatenated to form 1024 bits of data, which is used as data 0 on the external AXI bus, and so on for data 1 through data 7.
[0055] In one specific implementation, Figure 4 This is a schematic diagram of the structure of a burst transmission reassembly module provided in Embodiment 1 of the present invention. Figure 4This includes: AW Channel Receive FIFO: Receives requests from the external AXI bus for the AW channel; W Channel Receive FIFO: Receives data from the external AXI bus for the W channel; Write Channel Splitting Control: Receives relevant configuration information from the software control module, including interleaving granularity, splits the requests in the AW Channel Receive FIFO into requests to the downstream AW channels of the Slave, and pushes them into the AW Channel Send FIFO. Simultaneously, it controls the data in the W Channel Receive FIFO, splits it, and pushes it into the W Channel Send FIFO; AW Channel Send FIFO: Receives the split AW channel requests and sends them downstream; W Channel Send FIFO: Receives the split W channel data and sends it downstream; B Channel Receive FIFO: Receives response information from the downstream B channel; Response Merging: Merges multiple response data returned from the downstream and pushes them into the B Channel Send FIFO. During the merging process, all eight responses must be correct to return a correct result. Otherwise, an error will be returned. The specific slave port from which the error originated will be recorded in the software register for the upper-level processor to query and handle exceptions. B Channel Transmit FIFO: Receives merged response information and returns it to the external AXI; Software Control Module: Receives the values of the software configuration registers and provides relevant registers for software access; AR Channel Receive FIFO: Receives AR channel requests from the external AXI bus; Read Channel Splitting Control: Receives relevant configuration information from the software control module, including interleaving granularity, splits the requests in the AR channel receive FIFO into requests sent to the downstream AR channels of the Slave, and pushes them into the AR channel transmit FIFO. Simultaneously, it controls the data in the R channel receive FIFO, merges them, and pushes them into the R channel receive FIFO. AR Channel Transmit FIFO: Receives the split AR channel requests and sends them downstream; R Channel Receive FIFO: Receives response data from the downstream R channel; Response Merging: Merges multiple response data and information returned from the downstream, and pushes the merged response data and information into the R channel transmit FIFO. During the merging process, a correct response is only returned if all eight response messages are correct. Otherwise, an error is returned. The specific slave port from which the error originated is recorded through software registers for the upper-layer processor to query and handle exceptions. R channel transmits FIFO: receives the merged response data and response information, and returns it to the external AXI.
[0056] S130. Map each split data to an address to generate each mapped data, and transmit data according to each mapped data and operation instructions.
[0057] Specifically, since the on-chip network determines which memory AXI channel the request should be sent to based on the address range, the address interleaving control module needs to remap the addresses to achieve address interleaving.
[0058] Optionally, address mapping is performed on each split data to generate each mapped data, including: taking each split data as target data in sequence; determining the data address corresponding to the target data; and swapping the first specified position and the second specified position in the data address to generate the mapped data.
[0059] For example, Figure 5 This invention provides a schematic diagram of address interleaving mapping in Embodiment 1. Figure 5 In the text, the first specified location is address [8:7], and the second specified location is [21:20]. Figure 5 The total address width sent from the upstream is 48 bits, and the address width sent downstream is also 48 bits. The address interleaving control module can map the [8:7] bits of the original address to the [21:20] bits, and vice versa. Table 1 below illustrates the address mapping relationship:
[0060] Table 1
[0061]
[0062]
[0063] In this configuration, the hexadecimal address before mapping Request 1 is 0*80, the binary address is 0000_0000_0000_0000_1000_0000, corresponding to channel 0, and the hexadecimal address after mapping is 0*10_0000, the binary address is 0001_0000_0000_0000_0000_0000, corresponding to channel 1. It should be noted that this configuration supports a full matrix mapping method, mapping each bit of the address before mapping to any arbitrary bit position. It flexibly supports address interleaving mapping relationships and can support mapping of up to 48 bits of address. Table 2 below shows the configuration relationship of the full mapping register:
[0064] Table 2
[0065]
[0066] The register named MATRIX_MAP_BIT1, with a bit width of 8, is mapped to the cursor number of the first bit of the output address. It should be noted that in this implementation, registers MATRIX_MAP_BIT7 are set to 20, MATRIX_MAP_BIT8 to 21, MATRIX_MAP_BIT20 to 7, and MATRIX_MAP_BIT21 to 8. The remaining registers are set to their corresponding cursor numbers; for example, MATRIX_MAP_BIT0 is set to 0, MATRIX_MAP_BIT1 to 1, MATRIX_MAP_BIT2 to 2, and so on. This matrix mapping of addresses allows different applications to be mapped in different address spaces, achieving independent management and control of different address spaces.
[0067] The technical solution of this invention uses a burst transmission and reassembly module to split the data to be transmitted according to the interleaving granularity in the memory system configuration parameters, and an address interleaving control module to perform address mapping on the split data, thus realizing address-interleaved data transmission, achieving parallel operation of the multi-channel memory system, improving the overall bandwidth of the memory system, and also improving the operating efficiency of the memory system.
[0068] Example 2
[0069] Figure 6 This is a flowchart of a chip data transmission method provided in Embodiment 2 of the present invention. This embodiment adds a specific process for data transmission based on various mapping data and operation instructions, building upon Embodiment 1. The specific content of steps S210-S220 is largely the same as steps S110-S120 in Embodiment 1, and therefore will not be repeated in this embodiment. Figure 6 As shown, the method includes:
[0070] S210. Obtain the data to be transmitted and operation instructions input from the external bus, and obtain the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions.
[0071] Optionally, obtaining the configuration parameters of the memory system includes: obtaining a list of configuration items, obtaining the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; obtaining the interleaving granularity set by the user, and using the target cluster bit width and interleaving granularity as configuration parameters.
[0072] S220. The data to be transmitted is split according to the configuration parameters to generate each split data.
[0073] Optionally, the data to be transmitted is split according to the configuration parameters to generate each split data, including: determining the target burst length according to the configuration parameters; performing a specified format conversion on the interleaving granularity to determine the number of bytes to be added to the address; splitting the data to be transmitted according to the target burst length and the number of bytes to be added to the address to generate each split data, wherein the corresponding address of each split data increases sequentially according to the number of bytes to be added to the address.
[0074] Optionally, the target burst length can be determined based on configuration parameters, including: converting the interleaving granularity to a specified unit to generate a conversion granularity; and using the ratio of the conversion granularity to the target cluster bit width as the target burst length.
[0075] S230. Map the addresses of each split data to generate each mapped data.
[0076] S240. Sequentially use each mapped data as target transmission data and determine the target address corresponding to the target transmission data.
[0077] S250: Obtain the address range of each channel in the memory system, and determine the target channel corresponding to the target address based on the address range.
[0078] Specifically, during data transmission, the on-chip network determines the target channel corresponding to each target address based on the address range of each channel in the memory system, as shown in Table 3 below:
[0079] Table 3
[0080] aisle Memory capacity Address range Channel 0 1MB 0x0~0xFFFFF Channel 1 1MB 0x100000~0x1FFFFF Channel 2 1MB 0x200000~0x2FFFFF Channel 3 1MB 0x300000~0x3FFFFF
[0081] Among them, the memory capacity corresponding to channel 0 is 1MB, and the corresponding address range is 0x0~0xFFFFF.
[0082] S260. Transmit target data according to the operation instructions and target channel, and obtain response data, including success and error; generate prompt information based on each response data.
[0083] Optionally, a prompt message can be generated based on each response data, including: determining whether each response data is successful; if so, generating a prompt message indicating successful transmission; otherwise, using the data that is erroneous as the target response data and generating a prompt message based on the target response data.
[0084] Specifically, the on-chip network transmits target data according to the operation instructions and target channel, and obtains response data. The target data includes multiple split data, so a response data is generated for each transmission. The response data includes success and error. Only when all response data are successful will a transmission success prompt message be generated and returned to the external AXI bus. When a transmission error response data occurs, the on-chip network can record the erroneous target response data and generate a prompt message based on the target response data to prompt the user.
[0085] For example, for a write command, the burst transfer reassembly module needs to collect the responses from all eight write commands, combine them into a single command, and then return it to the external AXI bus. During this response combination process, a successful transfer message will only be generated if all eight responses are successful. Otherwise, an error message will be displayed as the target response to alert the user, allowing the upper-level processor to query and handle the exception. Since the original AXI bus only had one write command operation, while the split bus contains eight write commands, the burst transfer reassembly module needs to collect the responses from all eight commands, combine them into a single command, and then return it to the external AXI bus.
[0086] The technical solution of this invention uses a burst transmission and reassembly module to split the data to be transmitted according to the interleaving granularity in the memory system configuration parameters, and an address interleaving control module to perform address mapping on the split data, thus realizing address-interleaved data transmission, achieving parallel operation of the multi-channel memory system, improving the overall bandwidth of the memory system, and also improving the operating efficiency of the memory system.
[0087] Example 3
[0088] Figure 7 This is a schematic diagram of a chip data transmission device provided in Embodiment 3 of the present invention. Figure 7 As shown, the device includes: a data and configuration parameter acquisition module 310, used to acquire the data to be transmitted and operation instructions input from the external bus, and to acquire the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions;
[0089] The split data generation module 320 is used to split the data to be transmitted according to the configuration parameters to generate each split data;
[0090] The data mapping and transmission module 330 is used to perform address mapping on each split data to generate each mapped data, and to transmit data according to each mapped data and operation instructions.
[0091] Optionally, the data and configuration parameter acquisition module 310 specifically includes: a configuration parameter acquisition unit, used to: acquire a list of configuration items, acquire the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; acquire the interleaving granularity set by the user, and use the target cluster bit width and interleaving granularity as configuration parameters.
[0092] Optionally, the split data generation module 320 specifically includes: a target burst length determination unit, used to: determine the target burst length according to configuration parameters; an address increment byte determination unit, used to: convert the interleaving granularity to a specified format to determine the address increment byte; and a split data generation unit, used to: split the data to be transmitted according to the target burst length and the address increment byte to generate each split data, wherein the corresponding address of each split data increases sequentially according to the address increment byte.
[0093] Optionally, the target burst length determination unit is specifically used to: convert the interleaving granularity to a specified unit to generate a conversion granularity; and use the ratio of the conversion granularity to the target cluster bit width as the target burst length.
[0094] Optionally, the data mapping and transmission module 330 specifically includes: a mapping data generation unit, used to: sequentially take each split data as target data; determine the data address corresponding to the target data, and swap the first specified position and the second specified position in the data address to generate mapping data.
[0095] Optionally, the data mapping and transmission module 330 further includes: a target address determination unit, used to: sequentially use each mapped data as target transmission data and determine the target address corresponding to the target transmission data; a target channel determination unit, used to: obtain the address range of each channel of the memory system and determine the target channel corresponding to the target address based on the address range; a response data acquisition unit, used to: transmit the target transmission data according to the operation instruction and the target channel, and acquire response data, wherein the response data includes success and error; and a prompt information generation unit, used to: generate prompt information based on each response data.
[0096] Optionally, the prompt message generation unit is specifically used to: determine whether each response data is successful; if so, generate a prompt message indicating successful transmission; otherwise, take the data that is erroneous as the target response data and generate a prompt message based on the target response data.
[0097] The technical solution of this invention uses a burst transmission and reassembly module to split the data to be transmitted according to the interleaving granularity in the memory system configuration parameters, and an address interleaving control module to perform address mapping on the split data, thus realizing address-interleaved data transmission, achieving parallel operation of the multi-channel memory system, improving the overall bandwidth of the memory system, and also improving the operating efficiency of the memory system.
[0098] The chip data transmission device provided in this embodiment of the invention can execute a chip data transmission method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.
[0099] Example 4
[0100] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0101] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0102] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0103] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a chip data transfer method.
[0104] In some embodiments, a chip data transfer method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the chip data transfer method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a chip data transfer method by any other suitable means (e.g., by means of firmware).
[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0106] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0107] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0109] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0110] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0111] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A chip data transmission method, characterized in that, include: The system acquires the data to be transmitted and operation instructions input from the external bus, and acquires the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions; The data to be transmitted is split according to the configuration parameters to generate each split data; Each of the split data is address-mapped to generate each mapped data, and data is transmitted according to each of the mapped data and the operation instructions; The acquisition of the configuration parameters of the memory system includes: Obtain a list of configuration items, and obtain the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; Obtain the interleaving granularity set by the user, and use the target cluster bit width and the interleaving granularity as the configuration parameters; The step of splitting the data to be transmitted according to the configuration parameters to generate each split data includes: The target burst length is determined based on the configuration parameters. The interleaving granularity is converted to a specified format to determine the number of bytes added to the address; The data to be transmitted is split into segments based on the target burst length and the number of bytes added to the address to generate segments, wherein the addresses of each segment are sequentially increased by the number of bytes added to the address.
2. The method according to claim 1, characterized in that, Determining the target burst length based on the configuration parameters includes: The interlacing granularity is converted to a specified unit to generate a converted granularity; The ratio of the conversion granularity to the target cluster bit width is used as the target burst length.
3. The method according to claim 1, characterized in that, The step of mapping each of the split data to generate each mapped data includes: Each of the aforementioned split data points is used as the target data in turn; Determine the data address corresponding to the target data, and swap the first and second specified positions in the data address to generate the mapping data.
4. The method according to claim 1, characterized in that, The data transmission based on the mapping data and the operation instructions includes: Each of the mapped data is sequentially used as the target transmission data, and the target address corresponding to the target transmission data is determined. Obtain the address range of each channel of the memory system, and determine the target channel corresponding to the target address based on the address range; Transmit the target transmission data according to the operation instructions and the target channel, and obtain response data, wherein the response data includes success and error; A prompt message is generated based on the response data described above.
5. The method according to claim 4, characterized in that, The step of generating prompt information based on each of the response data includes: Determine whether all the response data are successful; if so, generate a message indicating successful transmission. Otherwise, the erroneous response data is taken as the target response data, and a prompt message is generated based on the target response data.
6. A chip data transmission device, characterized in that, include: The data and configuration parameter acquisition module is used to acquire the data to be transmitted and operation instructions input from the external bus, and to acquire the configuration parameters of the memory system, wherein the operation instructions include read instructions and write instructions; The split data generation module is used to split the data to be transmitted according to the configuration parameters to generate each split data; The data mapping and transmission module is used to perform address mapping on each of the split data to generate each mapped data, and to perform data transmission according to each of the mapped data and the operation instructions; Specifically, the data and configuration parameter acquisition module is used for: Obtain a list of configuration items, and obtain the target cluster bit width selected by the user based on the list of configuration items, wherein the list of configuration items includes the bit width of each cluster; Obtain the interleaving granularity set by the user, and use the target cluster bit width and the interleaving granularity as the configuration parameters; Specifically, the split data generation module is used for: The target burst length is determined based on the configuration parameters. The interleaving granularity is converted to a specified format to determine the number of bytes added to the address; The data to be transmitted is split into segments based on the target burst length and the number of bytes added to the address to generate segments, wherein the addresses of each segment are sequentially increased by the number of bytes added to the address.
7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
8. A computer storage medium, characterized in that, The computer storage medium stores computer instructions that are used to cause a processor to execute the method of any one of claims 1-5.
Citation Information
Patent Citations
Method and device for detecting bus behavior of system on chip
CN106708671A
Memory bandwidth control in core
CN115129624A
