CN112000594B - PCIe equipment management method and operation system thereof - Google Patents

PCIe equipment management method and operation system thereof Download PDF

Info

Publication number
CN112000594B
CN112000594B CN202010757559.4A CN202010757559A CN112000594B CN 112000594 B CN112000594 B CN 112000594B CN 202010757559 A CN202010757559 A CN 202010757559A CN 112000594 B CN112000594 B CN 112000594B
Authority
CN
China
Prior art keywords
upper computer
pcie
controller
address
equipment
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010757559.4A
Other languages
Chinese (zh)
Other versions
CN112000594A (en
Inventor
林涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Rockchip Electronics Co Ltd
Original Assignee
Rockchip Electronics Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Rockchip Electronics Co Ltd filed Critical Rockchip Electronics Co Ltd
Priority to CN202010757559.4A priority Critical patent/CN112000594B/en
Publication of CN112000594A publication Critical patent/CN112000594A/en
Application granted granted Critical
Publication of CN112000594B publication Critical patent/CN112000594B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/10Program control for peripheral devices
    • G06F13/12Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor
    • G06F13/124Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor where hardware is a sequential transfer control unit, e.g. microprocessor, peripheral processor or state-machine
    • G06F13/126Program control for peripheral devices using hardware independent of the central processor, e.g. channel or peripheral processor where hardware is a sequential transfer control unit, e.g. microprocessor, peripheral processor or state-machine and has means for transferring I/O instructions and statuses between control unit and main processor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38Information transfer, e.g. on bus
    • G06F13/42Bus transfer protocol, e.g. handshake; Synchronisation
    • G06F13/4282Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI bus
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2213/00Indexing scheme relating to interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F2213/0026PCI express

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Information Transfer Systems (AREA)

Abstract

A PCIe device management method and its operation system, the method runs in PCIe terminal and its upper computer, the method includes the following steps, S100, presume first controller and second controller in PCIe terminal control the first equipment, second equipment separately; s102, establishing a data forwarding layer, accessing the address of the first controller and the address of the second controller through the data forwarding layer, and mapping the addresses to a first base address and a second base address in the physical function respectively; s104, the equipment type reported by the physical function to the upper computer is a non-universal type, and a base address to be allocated exists in the reported mode; by the aid of the scheme, the data forwarding layer and the physical function are established, the upper computer can call data of the multiple device controllers through the virtual addresses, and then the devices are loaded through the drive operation of the upper computer end, so that the technical effect that the multiple devices are connected into the upper computer through the PCIe channel is finally achieved.

Description

PCIe equipment management method and operation system thereof
Technical Field
The invention relates to the field of PCIe access equipment, in particular to a design method of PCIe composite equipment.
Background
Currently, commercially available PCIe devices access a host system and can only be used as fixed devices, such as PCIe network cards, sound cards, and SSDs. However, due to the existence of the concept of USB composite device, and more SoC manufacturers design the devices of their own chips as PCIe interface devices, the devices can be conveniently accessed to a host system, such as an AI computing card. Given the precedent of the USB composite device model, which allows one USB device accessing the host system to implement multiple functions, the PCIe device accessing the host system can also implement multiple composite functions.
In the prior art, technical solutions including CN201910893668.6 and CN 201380002531.8 are all combined at a host end by a dual-mode and multi-mode method, and multiple PCIe interfaces need to be occupied, and in some other prior arts, in order to use a compound device at an EP end in a host system, a driver at the host end needs to be placed at the host end, and a driver of multiple compound devices needs to be placed at the EP end. This has the problem that two drives need to be maintained simultaneously, and the performance of the EP may be affected by occupying a large memory in a small-sized EP device, thereby reducing the efficiency of the host system using the EP.
Disclosure of Invention
Therefore, a new PCIe device management method needs to be provided, which can achieve the effect that the same PCIe port simultaneously operates multiple composite sub-devices;
in order to achieve the above object, the inventor provides a PCIe device management method, which is executed in a PCIe terminal and an upper computer thereof, and the method includes the following steps,
s100, respectively controlling a first device and a second device by a first controller and a second controller in the PCIe terminal;
s102, establishing a data forwarding layer, accessing the address of the first controller and the address of the second controller through the data forwarding layer, and mapping the addresses to a first base address and a second base address in the physical function respectively;
s104, the equipment type reported by the physical function to the upper computer is a non-universal type, and a base address to be allocated exists in the reported mode;
s106, the upper computer allocates a first virtual address and a second virtual address according to the reporting condition;
s108, the user-defined driving layer in the upper computer receives and identifies the equipment type reported by the physical function to the upper computer, loads the external drives corresponding to the first controller and the second controller according to the equipment type, and finally calls the first equipment and the second equipment.
Further, the method specifically comprises the step that when the upper computer performs equipment enumeration, the equipment type reported by the physical function to the upper computer is a non-universal type, and a base address to be allocated exists in the report.
Specifically, in step S102, the address of the first controller and the address of the second controller are accessed through the data forwarding layer, and are mapped to the first base address and the second base address in the physical function through the address translation service, respectively.
Further, the method also comprises the step that the physical function reports the equipment identification code to the upper computer; and the user-defined driving layer in the upper computer receives the equipment identification code of the upper computer and loads the corresponding external drive according to the equipment identification code.
Specifically, the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
An operation system of PCIe equipment is characterized by comprising a PCIe terminal and an upper computer,
the PCIe terminal comprises a first controller and a second controller, wherein the first controller and the second controller respectively control a first device and a second device; the data forwarding layer is used for accessing the address of the first controller and the address of the second controller and mapping the addresses to a first base address and a second base address in the physical function respectively; the physical function is also used for reporting that the equipment type reported to the upper computer is a non-universal type and reporting that a base address to be allocated exists;
the upper computer is used for distributing a first virtual address and a second virtual address according to the reporting condition;
the upper computer further comprises a custom driver layer, the custom driver layer is used for receiving and identifying the equipment type reported by the physical function to the upper computer, and is also used for loading external drivers corresponding to the first controller and the second controller according to the equipment type, and finally calling the first equipment and the second equipment.
Further, the physical function is specifically used for reporting that the device type reported to the upper computer is a non-universal type when the upper computer performs device enumeration, and reporting that a base address to be allocated exists.
Further, the data forwarding layer is configured to map the address of the first controller and the address of the second controller to the first base address and the second base address in the physical function through an address translation service, respectively.
Further, the physical function is also used for reporting the equipment identification code to the upper computer; and the custom drive layer in the upper computer is also used for receiving the equipment identification code of the upper computer and loading the corresponding external drive according to the equipment identification code.
Specifically, the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
By the aid of the scheme, the data forwarding layer and the physical function are established, the upper computer can call data of the multiple device controllers through the virtual addresses, and then the devices are loaded through the drive operation of the upper computer end, so that the technical effect that the multiple devices are connected into the upper computer through the PCIe channel is finally achieved.
Drawings
Fig. 1 is a flowchart of a PCIe device management method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a PCIe device operating system according to an embodiment of the invention;
FIG. 3 is a flowchart of a PCIe device management method according to another embodiment of the invention;
fig. 4 is a schematic diagram of a PCIe device operating system according to another embodiment of the present invention.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Please refer to fig. 1, which is a flowchart of a PCIe Device management method, where the method may be executed in a PCIe terminal and an upper computer, where the PCIe terminal is assumed to be an soc (system on chip) and may be referred to as a Device or an ep (endpoint), and the upper computer may be a PC terminal and an RC terminal (root complex). PCIe slave equipment is subordinate to the PCIe terminal, and the equipment comprises a PCIe sound card, a PCIe network card, a PCIe memory or a PCIe video card. The PCIe terminal is used for managing the PCIe equipment so that the PCIe equipment can be loaded by an upper computer.
The management method comprises the following steps of,
s100, respectively controlling a first device and a second device by a first controller and a second controller in the PCIe terminal; with continued reference to fig. 2, it is seen that at the EP side, the first controller IP1(intellectual property core) of the chip can be used, the second controller IP2 establishes communication with the first device α and the second device β modules, and the drivers of IP1 and IP2 continue to be responsible for the implementation of the communication.
S102, establishing a data forwarding layer, accessing the address of the first controller and the address of the second controller through the data forwarding layer, and mapping the addresses to a first base address and a second base address in a physical function PF (physical function), respectively. Specifically, the address of the first controller and the address of the second controller may be accessed by using an ats (address translation service) address translation service on the SOC, and the addresses are mapped by mapping to the first base address bar1 and the second base address bar2 in the physical function, respectively.
S104, the PCIe terminal reports the device type (generally character strings) reported to the upper computer as a non-universal type, and reports that the base address to be distributed exists. The step can be actively carried out when the terminal is connected to the upper computer, and can also be carried out when the RC carries out scanning or enumeration on the slave equipment. In a specific embodiment, reporting as a non-generic type enables the upper computer to skip a conventional loading program of a single device, without causing the problem of loading only a single device, but may also set a class code (generally a number) that is reported to the RC by the EP, and inform the RC that there are two bar spaces to be allocated in the EP. Thus, at the RC end, step S106 is performed, and the upper computer allocates the first virtual address and the second virtual address according to the reporting condition. The upper computer allocates a segment of PCIe bus domain address (namely a virtual address), and the first bus domain address and the second bus domain address are written into the corresponding two base addresses bar. After the execution is finished, the used physical address of the data forwarding layer and the PCIe bus domain address in the bar can be mapped by using the IP address pointed by the base address in the two virtual addresses through the ATS of the EP. Therefore, at the RC end, according to the system protocol, the virtual address VA corresponding to the PCIe bus domain address needs to be reserved for two bars. Through the ATS layer of the RC, the mapping relationship between VA and the physical address PA of the RC is established.
We also need to install an external EP function driver at the upper computer end for our chip, which has the function of identifying and processing the same product IDs as those of the Soc chip, such as pid (product ID)/vid (vendor ID), and these product IDs can be set by user and designed device identification codes. Step S108 is further specifically carried out, a user-defined drive layer (EP function) in the upper computer receives the device types reported by the physical functions to the upper computer and identifies the device types, and since the non-universal device types are reported in the enumeration process, a single device driver cannot be loaded, then external drivers corresponding to the first controller and the second controller are loaded according to the device identification codes, and finally the first device and the second device are called. Generally, a product line of a type of Soc has a device identification code. Corresponding to the attached combination of composite equipment. In some embodiments, the device identification code may also be used as a device class at the time of the previous declaration. The EP function driver registers different device interfaces in the OS (operating system) of the host system, for example, the α module is a network card, and the β module is an EMMC, and then the EP function driver registers a network card device and a disk device in the OS, and is responsible for receiving and sending data access from the host system, and then communicates with the terminal device EP through the physical addresses PA of Bar1 and Bar 2. And after the data forwarding of the EP terminal receives the data request, forwarding and replying are carried out. Which is equivalent to two PCIe devices being loaded normally.
Fig. 2 shows an operating system of a PCIe device, which is characterized by including a PCIe terminal and an upper computer,
the PCIe terminal comprises a first controller IP1 and a second controller IP2, wherein the first controller and the second controller respectively control a first device alpha device and a second device beta device; the system further comprises a data forwarding layer, wherein the data forwarding layer is used for accessing the address of the data of the first controller and the address of the data of the second controller, and respectively mapping the addresses to a first base address Bar1 and a second base address Bar2 in the physical function PF; the physical function PF is also used for reporting that the equipment type reported to the upper computer is a non-universal type and reporting that a base address to be allocated exists. The upper computer is used for allocating a first virtual address Bar1VA and a second virtual address Bar2VA according to the reporting condition. The upper computer further comprises a user-defined driving layer EP function, the user-defined driving layer is used for receiving and identifying the equipment type reported by the physical function to the upper computer, and is also used for loading external drives corresponding to the first controller and the second controller according to the equipment type and finally calling the first equipment and the second equipment.
By the aid of the scheme, the data forwarding layer and the physical function are established, the upper computer can call data of the multiple device controllers through the virtual addresses, and then the devices are loaded through the drive operation of the upper computer end, so that the technical effect that the multiple devices are connected into the upper computer through the PCIe channel is finally achieved.
As can be seen from the figure, the PF supports 5 base addresses at maximum, and in fact, the PCIe terminal may also be docked with a third device, a fourth device, and a fifth device, and the third device, the fourth device, and the fifth device may be configured through the same process as the first device and the second device in the above scheme, and thus, more than three PCIe devices may be accessed, and an effect of accessing the composite device to the upper computer is better achieved.
Further, the physical function is specifically used for reporting that the device type reported to the upper computer is a non-universal type when the upper computer performs device enumeration, and reporting that a base address to be allocated exists.
Further, the data forwarding layer is configured to map the address of the first controller and the address of the second controller to the first base address and the second base address in the physical function through an address translation service, respectively.
Further, the physical function is also used for reporting the equipment identification code to the upper computer; and the custom drive layer in the upper computer is also used for receiving the equipment identification code of the upper computer and loading the corresponding external drive according to the equipment identification code.
Specifically, the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
In a further optimized embodiment, we also find that if it is attempted to directly access the first controller and the second controller by the physical address of the upper computer, rather than accessing the driving address of the first controller and the driving address of the second controller through the data forwarding layer, it is possible to omit the data forwarding layer and the customized driving layer EP function, and achieve the saving of the device design. Therefore, please refer to fig. 3 showing another flowchart of the Device management method, which may be executed in a PCIe terminal and an upper computer, where the PCIe terminal is assumed to be an soc (system on chip) and may be referred to as a Device or an ep (endpoint), and the upper computer may be a PC terminal or an RC terminal (root complex). PCIe slave equipment is subordinate to the PCIe terminal, and the equipment comprises a PCIe sound card, a PCIe network card, a PCIe memory or a PCIe video card. The PCIe terminal is used for managing the PCIe equipment so that the PCIe equipment can be loaded by an upper computer.
The management method as shown in figure 3 comprises the following steps,
s300, setting a first controller and a second controller in the PCIe terminal to respectively control a first device and a second device; at the EP side, a first controller IP1(intellectual property core) of the chip may be used, a second controller IP2 establishes a connection with the first device alpha and the second device beta modules,
s302, mapping the memory mapping I/O (MMIO) addresses of the first controller and the second controller with a first base address Bar1 and a second base address Bar2 in a physical function by using an address translation service ATS,
s304, reporting the equipment category to the upper computer by the physical function, and reporting that a base address to be allocated exists;
s306, the upper computer allocates a first virtual address Bar1VA and a second virtual address Bar2VA to correspond to the first base address and the second base address respectively according to the reporting condition;
s308, the upper computer end respectively establishes the mapping from the first virtual address to the first physical address BAR1PA and from the second virtual address BAR2 PA to the second physical address through the address translation service.
S310, loading a first controller driver and a second controller driver by the upper computer according to the reported equipment types, wherein the first controller driver operates aiming at the first physical address and the second controller driver operates aiming at the second physical address.
In a further embodiment, the method may further include step S312, where the first controller drives or the second controller drives an operating system registration interface of the upper computer. Registering the interface with the operating system can facilitate the operator to operate the corresponding device at the user interaction interface.
Specifically, the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
Specifically, in S304, the physical function reports the device type to the upper computer when the upper computer performs device enumeration, and reports that a base address to be allocated exists.
By the scheme, mapping from a physical address of the upper computer end to a controller end of the equipment end can be established, the two PAs are accessed by directly operating the two controllers IP1 and IP2 of the EP, the purpose of operating the two modules alpha and beta is achieved, the upper computer can directly call the equipment drive to drive the equipment controllers of the equipment end, then the equipment is loaded by running through an upper computer end system, and finally the technical effect that the multiple equipment is accessed into the upper computer through a PCIe channel is achieved.
Also shown in the embodiment shown in fig. 4, another PCIe device operating system is further described, which includes a PCIe terminal and an upper computer,
the PCIe terminal comprises a first controller IP1 and a second controller IP2, wherein the first controller and the second controller respectively control a first device alpha device and a second device beta device; the system further comprises an address translation service layer ATS, wherein the address translation service layer is used for mapping a memory mapping IO address (MMIO address) of the first controller and a memory mapping IO address of the second controller to a first base address Bar1 and a second base address Bar2 in the physical function PF respectively; the physical function is also used for reporting the equipment category to the upper computer and reporting the existence of a base address to be allocated to the upper computer;
the upper computer is used for allocating a first virtual address Bar1VA and a second virtual address Bar2VA to correspond to a first base address Bar1 and a second base address Bar2 respectively according to reporting conditions;
the upper computer is further used for establishing mapping from a first virtual address to a first physical address Bar1PA and mapping from a second virtual address to a second physical address Bar1PA, and is further used for loading a first controller driver IP1 driver and a second controller driver IP2 driver, and the first controller driver operates on the first physical address and the second controller driver operates on the second physical address.
Specifically, the upper computer end is further used for loading the first controller driver or the second controller driver to an operating system registration interface of the upper computer end.
Specifically, the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
Specifically, the physical function is further configured to report the device type to the upper computer when the upper computer performs device enumeration, and report that a base address to be allocated exists.
The mapping from the physical address of the upper computer end to the controller end of the equipment end is established through the scheme, the upper computer can directly call the equipment drive to drive the equipment controllers of the equipment end, then the equipment is loaded through the operation of the upper computer end system, and finally the technical effect that the equipment is accessed into the upper computer through a PCIe channel is achieved.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. Therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.

Claims (10)

1. A PCIe device management method is characterized in that the method is operated on a PCIe terminal and an upper computer thereof and comprises the following steps,
s100, respectively controlling a first device and a second device by a first controller and a second controller in the PCIe terminal;
s102, establishing a data forwarding layer, accessing the address of the first controller and the address of the second controller through the data forwarding layer, and mapping the addresses to a first base address and a second base address in the physical function respectively;
s104, reporting the device type to be a non-universal type by the physical function to an upper computer, and reporting that a base address to be allocated exists; the upper computer skips over a loader that loads only a single device,
s106, the upper computer allocates a first virtual address and a second virtual address according to the reporting condition;
and S108, the user-defined driving layer in the upper computer receives the physical function, reports the equipment type to the upper computer, identifies the equipment type, loads the external drives corresponding to the first controller and the second controller according to the equipment type, and finally calls the first equipment and the second equipment.
2. The PCIe device management method according to claim 1, specifically comprising a step of, when the upper computer performs device enumeration, reporting that the device class reported by the physical function to the upper computer is a non-generic class, and reporting that there is a base address to be allocated.
3. The PCIe device management method according to claim 1, wherein the step S102 is specifically to access the address of the first controller and the address of the second controller through a data forwarding layer, and map the addresses to the first base address and the second base address in the physical function through an address translation service, respectively.
4. The PCIe device management method of claim 1, further comprising the step of the physical function further reporting a device identification code to an upper computer; and the user-defined driving layer in the upper computer receives the equipment identification code of the upper computer and loads the corresponding external drive according to the equipment identification code.
5. The PCIe device management method of claim 1, wherein the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe video card.
6. An operation system of PCIe equipment is characterized by comprising a PCIe terminal and an upper computer,
the PCIe terminal comprises a first controller and a second controller, wherein the first controller and the second controller respectively control a first device and a second device; the data forwarding layer is used for accessing the address of the first controller and the address of the second controller and mapping the addresses to a first base address and a second base address in the physical function respectively; the physical function is also used for reporting that the equipment type reported to the upper computer is a non-universal type and reporting that a base address to be allocated exists; the upper computer skips over a loader that loads only a single device,
the upper computer is used for distributing a first virtual address and a second virtual address according to the reporting condition;
the upper computer further comprises a custom driver layer, the custom driver layer is used for receiving and identifying the equipment type reported by the physical function to the upper computer, and is also used for loading external drivers corresponding to the first controller and the second controller according to the equipment type, and finally calling the first equipment and the second equipment.
7. The PCIe device operating system of claim 6, wherein the physical function is specifically configured to, when the upper computer performs device enumeration, report that the device type reported to the upper computer is a non-generic type, and report that there is a base address to be allocated.
8. The operating system for PCIe devices of claim 6, wherein the data forwarding layer is configured to map the address of the first controller and the address of the second controller to the first base address and the second base address in the physical function respectively through the address translation service.
9. The operating system for PCIe devices according to claim 6, wherein the physical function is further configured to report a device identification code to an upper computer; and the custom drive layer in the upper computer is also used for receiving the equipment identification code of the upper computer and loading the corresponding external drive according to the equipment identification code.
10. The operating system of the PCIe device of claim 6, wherein the device comprises a PCIe sound card, a PCIe network card, a PCIe memory, or a PCIe graphics card.
CN202010757559.4A 2020-07-31 2020-07-31 PCIe equipment management method and operation system thereof Active CN112000594B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010757559.4A CN112000594B (en) 2020-07-31 2020-07-31 PCIe equipment management method and operation system thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010757559.4A CN112000594B (en) 2020-07-31 2020-07-31 PCIe equipment management method and operation system thereof

Publications (2)

Publication Number Publication Date
CN112000594A CN112000594A (en) 2020-11-27
CN112000594B true CN112000594B (en) 2022-04-19

Family

ID=73463588

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010757559.4A Active CN112000594B (en) 2020-07-31 2020-07-31 PCIe equipment management method and operation system thereof

Country Status (1)

Country Link
CN (1) CN112000594B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112631969B (en) * 2020-12-30 2024-01-30 凌云光技术股份有限公司 Virtual multichannel data transmission method and system based on PCIE interface
CN113010470B (en) * 2021-03-30 2023-06-20 上海西井信息科技有限公司 Edge node remote control system, method, equipment and storage medium
CN114268514B (en) * 2021-11-30 2022-11-08 国汽智控(北京)科技有限公司 Communication method, device and system of vehicle and upper computer
CN117234743B (en) * 2023-11-14 2024-02-20 苏州元脑智能科技有限公司 Data transmission method, device, equipment and storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8249089B2 (en) * 2006-09-29 2012-08-21 Intel Corporation Methods for pushing address translations mappings to PCI express endpoints
US8271604B2 (en) * 2006-12-19 2012-09-18 International Business Machines Corporation Initializing shared memories for sharing endpoints across a plurality of root complexes
CN103714034A (en) * 2013-12-26 2014-04-09 中国船舶重工集团公司第七0九研究所 SOC applied to PC system
US11556437B2 (en) * 2018-08-22 2023-01-17 Intel Corporation Live migration of virtual devices in a scalable input/output (I/O) virtualization (S-IOV) architecture

Also Published As

Publication number Publication date
CN112000594A (en) 2020-11-27

Similar Documents

Publication Publication Date Title
CN112000594B (en) PCIe equipment management method and operation system thereof
CN112000593B (en) PCIe equipment management method and operation system thereof
US5586268A (en) Multiple peripheral adapter device driver architecture
US8683110B2 (en) I/O system and I/O control method
EP1787207B1 (en) Dynamic resource allocation
US20070260901A1 (en) System power state broadcast through the use of a bus protocol
US6591309B1 (en) I/O bus abstraction for a cluster interconnection fabric
US6070204A (en) Method and apparatus for using universal serial bus keyboard to control DOS operations
US5146605A (en) Direct control facility for multiprocessor network
CN103873489A (en) Device sharing system with PCIe interface and device sharing method with PCIe interface
US20120183001A1 (en) Network apparatus, network configuration method and program recording medium which records a network apparatus program
CN106227683A (en) Electronic equipment and information processing method
EP3716084A1 (en) Apparatus and method for sharing a flash device among multiple masters of a computing platform
US7636797B2 (en) LPC configuration sharing method
US5968174A (en) Method and apparatus for implementing a 32-bit operating system which supports 16-bit code
CN113010470A (en) Edge node remote control system, method, device and storage medium
WO2023221753A1 (en) Serial port communication method and related apparatus
DE102021107336A1 (en) DEVICES, SYSTEMS, AND METHODS FOR PCIe ENDPOINT INTERRUPT
CN110795373B (en) I2C bus-to-parallel bus conversion method, terminal and storage medium
KR100316190B1 (en) Increasing i/o performance through storage of packetized operational information in local memory
CN107967223B (en) Multi-product line universal code architecture system
CN116048640A (en) Method for driving IIC equipment in computer system to work normally
CN112130904B (en) Processing system, inter-processor communication method, and shared resource management method
CN108228496B (en) Direct memory access memory management method and device and master control equipment
JPH04230556A (en) Computer system, common system for address space with a plurality of input/output adapters and communication control method between a plurality of input/output devices and computer processors

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant