CN112947857B - A data transfer method, device, equipment, and computer-readable storage medium - Google Patents

Abstract

The invention discloses a data migration method, which comprises the following steps: receiving configuration information corresponding to a target data migration task; parsing the configuration information to obtain a source address, a destination address, and a flow control type; judging whether the flow control type is Peripheral device flow control; if so, when receiving a data transfer request sent by the target peripheral device corresponding to the source address, move the data corresponding to the source address in the unified memory to the destination address. By applying the data transfer method provided by the present invention, it is not necessary to set FIFO memories in each peripheral device separately, which reduces system complexity, avoids waiting for data transmission, and greatly improves data transmission efficiency. The invention also discloses a data transfer device, equipment and storage medium, which have corresponding technical effects.

Description

A data transfer method, device, equipment, and computer-readable storage medium

technical field

The present invention relates to the field of storage technology, in particular to a data transfer method, device, equipment and computer-readable storage medium.

Background technique

With the increasingly widespread application of heterogeneous acceleration, accelerator cards based on Field Programmable Gate Array (Field Programmable Gate Array, FPGA) are also developing rapidly. The accelerator card FPGA is connected to the server host through the high-speed serial computer expansion bus standard (peripheral component interconnect express, PCIE) interface, and the server host sends the data to be accelerated to the accelerator card FPGA through the PCIE interface, and the accelerator card FPGA finishes processing through the PCIE interface Return relevant data. During data transmission, direct memory access (Direct Memory Access, DMA) is a commonly used data moving device.

At present, the existing direct access memory receives instructions from the host host, applies for bus control, moves data from address A to address B, and sends an interrupt or other signal to inform the host after the transfer is completed. However, general direct access to memory can only be used for data transfer between memories (memory), not directly for data transfer between streaming peripherals, such as Universal Asynchronous Receiver/Transmitter (UART), network ports, etc. equipment.

In the prior art, when devices such as UART and network ports need DMA to move data, the usual way is to add a FIFO (First Input First Output) memory between the DMA and UART, which is equivalent to changing the UART peripheral (peripheral) Becomes a memory-type peripheral. However, in a system with many peripherals, this method needs to increase FIFO memory in each peripheral, which increases the complexity of the system and is not conducive to product development. Because the data of the peripheral device is not stable, the waiting time for data transmission is long, resulting in low data transmission efficiency.

To sum up, how to effectively solve problems such as complex systems and low data transmission efficiency in existing data transfer methods is an urgent problem for those skilled in the art at present.

Contents of the invention

The object of the present invention is to provide a data transfer method, which reduces system complexity and improves data transmission efficiency; another object of the present invention is to provide a data transfer device, equipment and computer-readable storage medium.

In order to solve the above technical problems, the present invention provides the following technical solutions:

A method for moving data, comprising:

Receive the configuration information corresponding to the target data migration task;

Analyzing the configuration information to obtain a source address, a destination address, and a flow control type;

Judging whether the flow control type is peripheral flow control;

If yes, move the data corresponding to the source address in the unified memory to the destination address when receiving the data transfer request sent by the target peripheral device corresponding to the source address.

In a specific implementation manner of the present invention, moving the data corresponding to the source address in the unified memory to the destination address includes:

Determine whether there is currently a DMA flow control data moving task to be executed;

If so, then execute the DMA flow control data moving task;

Judging whether the DMA flow control data moving task has been executed;

If yes, execute the step of moving the data corresponding to the source address in the unified memory to the destination address.

In a specific implementation manner of the present invention, judging whether there is currently a DMA flow control data transfer task to be processed includes:

Determine whether the DMA flow control signal is enabled;

Execute the DMA flow control data moving task, including:

It is determined that the DMA flow control data moving task exists, and the DMA flow control data moving task is executed.

In a specific implementation manner of the present invention, after receiving the data transfer request sent by the target peripheral device corresponding to the source address, it further includes:

judging whether the data migration request is the last data migration request corresponding to the target data migration task;

If yes, after performing the step of moving the data corresponding to the source address in the unified memory to the destination address, it is determined that the execution of the target data moving task is completed.

In a specific implementation manner of the present invention, moving the data corresponding to the source address in the unified memory to the destination address includes:

The data corresponding to the source address in the unified memory is moved to the destination address through the Avalon bus.

A data transfer device, comprising:

An information receiving module, configured to receive configuration information corresponding to the target data migration task;

An information parsing module, configured to parse the configuration information to obtain a source address, a destination address, and a flow control type;

A first judging module, configured to judge whether the flow control type is peripheral flow control;

A data movement module, configured to unify the data corresponding to the source address in the memory when the flow control type is determined to be peripheral flow control, and when a data movement request sent by the target peripheral corresponding to the source address is received Move to the stated destination address.

In a specific implementation manner of the present invention, the data movement module includes:

The first judging sub-module is used to judge whether there is currently a DMA flow control data moving task to be executed;

The task execution submodule is configured to execute the DMA flow control data movement task when it is determined that there is currently a DMA flow control data movement task to be executed;

The second judging submodule is used to judge whether the DMA flow control data moving task has been executed;

The data moving sub-module is configured to move the data corresponding to the source address in the unified memory to the destination address when it is determined that the execution of the DMA flow control data moving task is completed.

In a specific embodiment of the present invention, it also includes:

The second judging module is configured to judge whether the data migration request is the last data migration request corresponding to the target data migration task after receiving the data migration request sent by the target peripheral device corresponding to the source address;

A task execution status determining module, configured to, when determining that the data migration request is the last data migration request corresponding to the target data migration task, after moving the data corresponding to the source address in the unified memory to the destination address, It is determined that the execution of the target data moving task is completed.

A data transfer device, comprising:

memory for storing computer programs;

The processor is configured to implement the steps of the aforementioned data moving method when executing the computer program.

A computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the aforementioned data moving method are implemented.

The data migration method provided by the present invention receives the configuration information corresponding to the target data migration task; parses the configuration information to obtain the source address, destination address, and flow control type; judges whether the flow control type is peripheral flow control; if so, Then, when a data transfer request sent by the target peripheral device corresponding to the source address is received, the data corresponding to the source address in the unified memory is moved to the target address. By pre-setting the unified memory and pre-configuring the flow control type of the data migration task corresponding to the peripheral, when the flow control type of the target data migration task is determined to be peripheral flow control, the method of actively initiating a data migration request through the target peripheral Trigger the execution of the data migration task. Therefore, there is no need to set FIFO memories in each peripheral device separately, which reduces the complexity of the system, avoids waiting for data transmission, and greatly improves the efficiency of data transmission.

Correspondingly, the present invention also provides a data migration device, device, and computer-readable storage medium corresponding to the above-mentioned data migration method, which have the above-mentioned technical effects, and will not be repeated here.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

Fig. 1 is a kind of implementation flowchart of the data moving method in the embodiment of the present invention;

Fig. 2 is another implementation flowchart of the data moving method in the embodiment of the present invention;

FIG. 3 is a structural block diagram of a data transfer system in an embodiment of the present invention;

FIG. 4 is a flow chart of data migration in an embodiment of the present invention;

5 is a structural block diagram of a data transfer device in an embodiment of the present invention;

Fig. 6 is a structural block diagram of a data moving device in an embodiment of the present invention.

Detailed ways

In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Embodiment one:

Referring to Fig. 1, Fig. 1 is a kind of implementation flowchart of the data moving method in the embodiment of the present invention, and this method may comprise the following steps:

S101: Receive configuration information corresponding to a target data migration task.

Set the configuration information of the data transfer task corresponding to each peripheral in the host host in advance. When there is a target data transfer task to be processed, the host sends the configuration information corresponding to the target data transfer task to the multi-stream empty DMA, and the multi-stream empty DMA receives Configuration information corresponding to the target data migration task.

The configuration information may include the source address, destination address, flow control type, data size, source address and destination address of the data to be moved, whether they belong to the incremental type or the constant type, etc.

Flow control types include DMA flow control and peripheral flow control. DMA flow control refers to DMA as data flow control, and peripheral flow control refers to peripherals as data flow control.

S102: Analyze the configuration information to obtain the source address, destination address, and flow control type.

After receiving the configuration information corresponding to the target data moving task, the configuration information is analyzed to obtain the source address, destination address, and flow control type.

S103: Determine whether the flow control type is peripheral flow control, if not, execute step S104, and if yes, execute step S105.

After analyzing the flow control type, it is judged whether the flow control type is peripheral flow control, if not, it means that the flow control type is DMA flow control, and step S104 is executed, and if so, step S105 is executed.

S104: When the DMA flow control signal is enabled, move the data corresponding to the source address in the unified memory to the destination address.

When it is determined that the flow control type is not peripheral flow control, it indicates that the flow control type is DMA flow control, and detects whether the DMA flow control signal is in an enabled state. For example, the ready (ready) signal can be set in advance as an indicator of the DMA flow control signal. And setting the low level of the preparation signal corresponds to the enable state of the DMA flow control signal, and when it is determined that the DMA flow control signal is in the enable state, the data corresponding to the source address in the unified memory is moved to the destination address. When DMA is used as flow control, because DMA can directly obtain the total amount of data that needs to be moved, when it is determined that the DMA flow control signal is enabled, it is sufficient to directly initiate data transmission until the execution of the target data movement task is completed.

S105: When receiving a data transfer request sent by the target peripheral device corresponding to the source address, move the data corresponding to the source address in the unified memory to the destination address.

When the flow control type is determined to be peripheral flow control, since the DMA cannot obtain the overall amount of data that needs to be moved, it needs to wait for the request from the peripheral before moving the data. When receiving the data transfer request sent by the target peripheral device corresponding to the source address, move the data corresponding to the source address in the unified memory to the destination address. By pre-setting the unified memory and pre-configuring the flow control type of the data migration task corresponding to the peripheral, when the flow control type of the target data migration task is determined to be peripheral flow control, the method of actively initiating a data migration request through the target peripheral Trigger the execution of the data migration task. Therefore, there is no need to set FIFO memories in each peripheral device separately, which reduces the complexity of the system, provides convenience for product development, avoids waiting for data transmission, and greatly improves the efficiency of data transmission.

The data migration method provided by the present invention receives the configuration information corresponding to the target data migration task; parses the configuration information to obtain the source address, destination address, and flow control type; judges whether the flow control type is peripheral flow control; if so, Then, when a data transfer request sent by the target peripheral device corresponding to the source address is received, the data corresponding to the source address in the unified memory is moved to the destination address. By pre-setting the unified memory and pre-configuring the flow control type of the data migration task corresponding to the peripheral, when the flow control type of the target data migration task is determined to be peripheral flow control, the method of actively initiating a data migration request through the target peripheral Trigger the execution of the data migration task. Therefore, there is no need to set FIFO memories in each peripheral device separately, which reduces the complexity of the system, avoids waiting for data transmission, and greatly improves the efficiency of data transmission.

It should be noted that, based on the first embodiment above, the embodiment of the present invention also provides a corresponding improvement solution. In subsequent embodiments, the same steps as in the first embodiment above or corresponding steps may be referred to each other, and the corresponding beneficial effects may also be referred to each other, and will not be repeated in the improved embodiments below.

Embodiment two:

Referring to Fig. 2, Fig. 2 is another implementation flowchart of the data moving method in the embodiment of the present invention, and the method may include the following steps:

S201: Receive configuration information corresponding to a target data migration task.

S202: Analyze the configuration information to obtain the source address, destination address, and flow control type.

S203: Determine whether the flow control type is peripheral flow control, if not, execute step S204, and if yes, execute step S205.

S204: When the DMA flow control signal is enabled, move the data corresponding to the source address in the unified memory to the destination address through the Avalon bus.

After determining that the flow control type is not peripheral flow control, when the DMA flow control signal is enabled, the data corresponding to the source address in the unified memory is moved to the destination address through the Avalon bus, thereby realizing data movement between peripherals.

S205: Receive a data move request sent by the target peripheral device corresponding to the source address.

When the flow control type is determined to be peripheral flow control, when the peripheral needs to perform data transmission, it actively sends a data movement request to the multi-flow control DMA, and the multi-flow control DMA receives the data movement request sent by the target peripheral corresponding to the source address.

S206: Determine whether there is currently a DMA flow control data moving task to be executed, if yes, perform step S207, and if not, perform step S209.

Since the data transmission speed of the DMA flow control is higher than that of the peripheral flow control, the priority of the preset DMA flow control is higher than that of the peripheral flow control. After receiving the data transfer request sent by the target peripheral device corresponding to the source address, determine whether there is currently a DMA flow control data transfer task to be executed, if so, it means that the DMA flow control data transfer task needs to be executed first at present, and step S207 is executed If not, execute step S209.

S207: Execute the DMA flow control data moving task.

When it is determined that there is currently a DMA flow control data moving task to be executed, the DMA flow control data moving task is executed.

In a specific implementation manner of the present invention, step S206 may include the following steps:

Determine whether the DMA flow control signal is enabled;

Correspondingly, step S207 may include the following steps:

Determine that there is a DMA flow control data moving task, and execute the DMA flow control data moving task.

The state of the DMA flow control signal is used as the basis for judging whether the DMA flow control data transfer task exists or not. After receiving the data transfer request sent by the target peripheral device corresponding to the source address, it is judged whether the DMA flow control signal is enabled. If so, Then it is determined that there is a DMA flow control data moving task, and the DMA flow control data moving task is executed.

S208: Determine whether the DMA flow control data moving task is completed, if yes, perform step S209, if not, do not process.

After determining that there is a DMA flow control data moving task and executing the DMA flow control data moving task, it is judged whether the DMA flow control data moving task has been executed, if so, it means that the peripheral flow control data moving task can be executed next, and step S209 , if not, it means that it still needs to wait for the completion of the DMA flow control data moving task, and no processing is performed.

S209: Move the data corresponding to the source address in the unified memory to the destination address through the Avalon bus.

When it is determined that the DMA flow control data movement task is completed, it means that the peripheral flow control data movement task can be executed next, and the data corresponding to the source address in the unified memory is moved to the destination address through the Avalon bus.

S210: Determine whether the data migration request is the last data migration request corresponding to the target data migration task, if yes, execute step S211, if not, repeatedly execute step S205.

When the peripheral is used as flow control, the DMA cannot obtain the overall amount of data that needs to be moved. It needs to wait for the request from the peripheral before moving the data. The DMA cannot automatically obtain whether the data transfer is complete. Therefore, when the data of the peripheral device is about to end, the DMA is notified by initiating the last data transfer request that this is the last data transfer. After the DMA completes the data transfer, the data transfer task ends. After receiving the data migration request sent by the target peripheral corresponding to the source address, judge whether the data migration request is the last data migration request corresponding to the target data migration task, and if so, it means that the current data migration is the last data migration request corresponding to the target data migration task For data migration, step S211 is executed. If not, it means that the current data migration is not the last data migration corresponding to the target data migration task, and step S205 is repeatedly executed.

S211: Determine that the execution of the target data moving task is completed.

When it is determined that the data migration request is the last data migration request corresponding to the target data migration task, it indicates that the current data migration is the last data migration corresponding to the target data migration task, and it is determined that the execution of the target data migration task is completed.

Referring to FIG. 3, FIG. 3 is a structural block diagram of a data migration system in an embodiment of the present invention. The system includes SRAM, DDR, SPI, UART, Ethernet (Ethernet) and other peripherals, multi-flow control DMA, and host. The peripherals and the multi-flow control DMA, and the multi-flow control DMA and the host are connected through the Avalon-MM interface. The multi-flow control DMA is set as FPGA-based multi-flow control DMA. All the logic is implemented in the FPGA, which is mainly divided into 8 modules: configuration module, status module, DMA flow control module, peripheral flow control module, Burst transmission module, Last transfer module, request module, interrupt module.

The configuration module mainly receives configuration information from the host, including the source address, destination address, data volume, flow control type, and whether the source address and destination address belong to the incremental type or the constant type, etc. for multi-flow control DMA.

The main function of the status module is to record the status information of the DMA flow control module and the peripheral flow control module, such as the internal FIFO is full, whether the current flow control channel is moving, waiting, or ending, the amount of remaining data, and so on.

The main function of the DMA flow control module is to use multi-flow control DMA as data flow control to perform data movement between memory (memory) or peripheral (peripheral). There are four types of flow control, memory to memory (m2m), memory to peripheral (m2p), peripheral to memory (p2m), peripheral to peripheral (p2p).

The main function of the peripheral flow control module is to use peripherals as data flow control to perform data movement between memory or peripheral. There are three types of flow control, memory to peripheral (m2p), peripheral to memory (p2m), peripheral to peripheral ( p2p).

The priority of setting DMA flow control is higher than peripheral flow control.

The main function of the interrupt module is that when the data transfer task of the multi-flow control DMA is completed, the interrupt module will send the corresponding interrupt or other information to inform the host, and the host can also be configured to shield these interrupts, and then obtain the corresponding information by reading the status module.

The Burst transmission module converts various flow control request types of multi-flow control DMA into Burst transmission that meets the Avalon bus protocol, continuously reads data from the source address, and writes to the destination address, regardless of whether DMA is used as flow control or peripherals are used as Flow control needs to pass through this module.

The Last transmission module is only for data migration when the peripheral is used as the flow control. When the peripheral is used as the flow control, the multi-flow control DMA cannot obtain the overall amount of data that needs to be moved, but only waits for the request from the peripheral before moving the data. The flow control DMA cannot know when the data movement is finished. When the data of the peripheral device is about to end, at this time, the multi-flow control DMA is notified by requesting to initiate the Last transfer that this is the last data transfer. After the multi-flow control DMA completes the Last transfer, the data transfer task is over. When the multi-flow control DMA is used as flow control, because the multi-flow control DMA can obtain the total amount of data that needs to be moved, it is enough to initiate a normal Burst transmission until the end of the task.

The main function of the request module is to receive the data movement request from the peripheral module, because the data of the peripheral is not stable, sometimes there is a lot, sometimes there is little, and sometimes there is no data. In this case, if you use multi-flow control As a flow control, DMA may need to wait for a long time, resulting in low efficiency. At this time, it is necessary to use the peripheral as a flow control. When the data arrives, it will actively initiate a request to the multi-flow control DMA. Under normal circumstances, the multi-flow control DMA initiates a Burst request. If it is the last piece of data, it initiates a Last request. The peripheral The flow control module initiates corresponding Burst/Last data transmission according to the request type.

Multi-flow control DMA can be encapsulated into IP for independent use, and can be applied to data transfer between various types of peripherals. The flexibility, portability and scalability are enhanced, and it can be called directly during project development, which facilitates product development and shortens the development cycle.

Referring to FIG. 4, FIG. 4 is a flow chart of data migration in an embodiment of the present invention. The workflow of multi-flow control DMA is illustrated by data transfer between SRAM, DDR and UART. The first configuration of the host is that the source address is SRAM address A, the destination address is DDR address B, the total amount of data is 256M, the flow control type is D_m2m, and both the source address and the destination address are incremented. The second configuration is that the source address is UART address C, the destination address is DDR address D, the flow control type is P_p2m, the source address is fixed, and the destination address is incremented.

First, the multi-flow control DMA starts to execute the task of D_m2m, initiates the Burst transmission through the Burst transmission module, reads the data from the SRAM and writes it into the multi-flow control DDR, and the address of each Burst read and write is incremented. If the data in the SRAM is insufficient when the data is moved to 64M and it needs to wait, then D_m2m waits first and starts the transmission of P_p2m at the same time. If the UART has sufficient data, the UART will initiate a req request to inform the multi-flow control DMA that the UART data can be read, and the multi-flow control DMA will read the UART data and write it to the multi-flow control DDR address D by initiating a Burst transmission. If the data in SRAM is sufficient at this time, the ready signal is pulled low, and the current burst transmission of P_p2m is completed, and D_m2m is started again, but it is necessary. When the transmission of D_m2m ends, the multi-flow control DMA initiates a corresponding interrupt to the host, notifying the host that the D_m2m transfer task is completed, and continues to execute P_p2m at the same time. Since the data rate of UART is relatively slow, it will take a long time to execute the next transfer. The multi-flow control DMA waits for the UART req request, and then executes Burst transmission to move data. When the multi-flow control DMA receives the Last req request, the multi-flow control DMA will initiate the Last transmission, and after completing the Last transmission, it will initiate a correspondence to the host. Interrupt, inform the host that the P_p2m task is completed at this time.

During the period, the status module will record the status information of D_m2m and P_p2m, and the host can shield the interrupt and obtain information by accessing the status module.

Embodiment three:

Corresponding to the above method embodiments, the present invention also provides a data migration device, and the data migration device described below and the data migration method described above can be referred to in correspondence.

Referring to FIG. 5, FIG. 5 is a structural block diagram of a data moving device in an embodiment of the present invention, and the device may include:

An information receiving module 51, configured to receive configuration information corresponding to the target data moving task;

An information parsing module 52, configured to parse the configuration information to obtain the source address, destination address, and flow control type;

The first judging module 53 is used to judge whether the flow control type is peripheral flow control;

The data movement module 54 is configured to move the data corresponding to the source address in the unified memory to the destination address when receiving a data movement request sent by the target peripheral corresponding to the source address when the flow control type is determined to be peripheral flow control.

In a specific embodiment of the present invention, the data movement module 54 includes:

The first judging sub-module is used to judge whether there is currently a DMA flow control data moving task to be executed;

The task execution sub-module is used to execute the DMA flow control data movement task when it is determined that there is currently a DMA flow control data movement task to be executed;

The second judging sub-module is used to judge whether the DMA flow control data moving task is executed;

The data moving sub-module is used to move the data corresponding to the source address in the unified memory to the destination address when it is determined that the execution of the DMA flow control data moving task is completed.

In a specific implementation manner of the present invention, the second judging submodule is specifically a module that judges whether the DMA flow control signal is in an enabled state;

The task execution sub-module is specifically a module that determines that there is a DMA flow control data moving task when it is determined that the DMA flow control signal is enabled, and executes the DMA flow control data moving task.

In a specific embodiment of the present invention, the device may also include:

The second judging module is used to judge whether the data migration request is the last data migration request corresponding to the target data migration task after receiving the data migration request sent by the target peripheral device corresponding to the source address;

The task execution state determination module is used to determine that the data movement request for the target data movement task is completed after the data corresponding to the source address in the unified memory is moved to the destination address when it is determined that the data movement request is the last data movement request corresponding to the target data movement task. implement.

In a specific implementation manner of the present invention, the data moving module 54 is specifically a module that moves the data corresponding to the source address in the unified memory to the destination address through the Avalon bus.

Corresponding to the above method embodiment, refer to FIG. 6, which is a schematic diagram of the data moving device provided by the present invention. The device may include:

memory 61 for storing computer programs;

When the processor 62 is used to execute the computer program stored in the memory 61, the following steps can be realized:

Receive the configuration information corresponding to the target data migration task; parse the configuration information to obtain the source address, destination address, and flow control type; determine whether the flow control type is peripheral flow control; if so, when receiving the target address corresponding to the source address When the data transfer request is sent by the peripheral, the data corresponding to the source address in the unified memory is moved to the destination address.

For the introduction of the device provided by the present invention, please refer to the above method embodiment, and the present invention will not repeat it here.

Embodiment four:

Corresponding to the above method embodiments, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps can be implemented:

Receive the configuration information corresponding to the target data migration task; parse the configuration information to obtain the source address, destination address, and flow control type; determine whether the flow control type is peripheral flow control; if so, when receiving the target address corresponding to the source address When the data transfer request is sent by the peripheral, the data corresponding to the source address in the unified memory is moved to the destination address.

The computer-readable storage medium may include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc., which can store program codes. medium.

For the introduction of the computer-readable storage medium provided by the present invention, please refer to the foregoing method embodiments, and the present invention will not repeat them here.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to each other. As for the device, equipment and computer-readable storage medium disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for relevant details, please refer to the description of the method part.

In this paper, specific examples are used to illustrate the principles and implementation methods of the present invention, and the descriptions of the above embodiments are only used to help understand the technical solutions and core ideas of the present invention. It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, some improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims (10)

1. A method for moving data, characterized in that, comprising: Receive the configuration information corresponding to the target data migration task; Analyzing the configuration information to obtain a source address, a destination address, and a flow control type; Judging whether the flow control type is peripheral flow control; If so, when receiving the data transfer request sent by the target peripheral device corresponding to the source address, the data corresponding to the source address in the unified memory is moved to the destination address, and the unified memory is used uniformly by each peripheral device FIFO memory. 2. The data moving method according to claim 1, wherein moving the data corresponding to the source address in the unified memory to the destination address comprises: Determine whether there is currently a DMA flow control data moving task to be executed; If so, then execute the DMA flow control data moving task; Judging whether the DMA flow control data moving task has been executed; If yes, execute the step of moving the data corresponding to the source address in the unified memory to the destination address. 3. The data moving method according to claim 2, wherein judging whether there is currently a DMA flow control data moving task to be processed comprises: Determine whether the DMA flow control signal is enabled; Execute the DMA flow control data moving task, including: It is determined that the DMA flow control data moving task exists, and the DMA flow control data moving task is executed. 4. The data migration method according to any one of claims 1 to 3, characterized in that, after receiving the data migration request sent by the target peripheral device corresponding to the source address, further comprising: judging whether the data migration request is the last data migration request corresponding to the target data migration task; If yes, after performing the step of moving the data corresponding to the source address in the unified memory to the destination address, it is determined that the execution of the target data moving task is completed. 5. The data moving method according to claim 4, wherein moving the data corresponding to the source address in the unified memory to the destination address comprises: The data corresponding to the source address in the unified memory is moved to the destination address through the Avalon bus. 6. A data transfer device, characterized in that it comprises: An information receiving module, configured to receive configuration information corresponding to the target data migration task; An information parsing module, configured to parse the configuration information to obtain a source address, a destination address, and a flow control type; A first judging module, configured to judge whether the flow control type is peripheral flow control; A data movement module, configured to unify the data corresponding to the source address in the memory when the flow control type is determined to be peripheral flow control, and when a data movement request sent by the target peripheral corresponding to the source address is received Moving to the destination address, the unified memory is a FIFO memory used uniformly by each peripheral device. 7. The data transfer device according to claim 6, wherein the data transfer module comprises: The first judging sub-module is used to judge whether there is currently a DMA flow control data moving task to be executed; The task execution submodule is configured to execute the DMA flow control data movement task when it is determined that there is currently a DMA flow control data movement task to be executed; The second judging submodule is used to judge whether the DMA flow control data moving task has been executed; The data moving sub-module is configured to move the data corresponding to the source address in the unified memory to the destination address when it is determined that the execution of the DMA flow control data moving task is completed. 8. The data transfer device according to claim 6 or 7, further comprising: The second judging module is configured to judge whether the data migration request is the last data migration request corresponding to the target data migration task after receiving the data migration request sent by the target peripheral device corresponding to the source address; A task execution status determining module, configured to, when determining that the data migration request is the last data migration request corresponding to the target data migration task, after moving the data corresponding to the source address in the unified memory to the destination address, It is determined that the execution of the target data moving task is completed. 9. A data transfer device, characterized in that it comprises: memory for storing computer programs; A processor, configured to implement the steps of the data transfer method according to any one of claims 1 to 5 when executing the computer program. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the data transfer as described in any one of claims 1 to 5 is realized. method steps.

Images