118 results about "FeiTeng" patented technology

The invention relates to a UEFI (Unified Extensible Firmware Interface) firmware implementation method based on a Feiteng portable computer, and belongs to the technical field of computer firmware. Firmware is divided into a hardware abstraction layer, a firmware core layer, an equipment protocol layer and a firmware application layer, wherein the hardware abstraction layer is used for realizing the initialization of key hardware components such as a processor, an internal memory and a chipset, packaging and abstracting other board-level hardware and realizing the initialization, and also providing a function interface for accessing bottom-layer hardware equipment for an upper module; the firmware core layer is used for establishing a system service table in a UEFI to carry out the unified management of all modules in the firmware and the management of various resources; the equipment protocol layer is used for realizing various standard industrial specifications; the firmware application layer is used for realizing all functions of the firmware, such as interface configuration, system monitoring, file system and operating system guiding. The UEFI firmware implementation method can realize firmware products, with high expandability and perfect functions, meeting international mainstream UEFI firmware specifications on the Feiteng portable computer so as to support the normal start and operation of the Feiteng portable computer.

The invention discloses a method for controlling a battery status based on a domestic Fei Teng processor. The method is used for obtaining in real time various information of an intelligent battery and controlling a charge and discharging status of the battery. The technical scheme is that a battery status control system of Smart Battery formed by the Smart Battery, a Fei Teng 1000A processor, battery status control software and a power supply management application is built first, battery status information is obtained by the battery status control software according to the cycle T by accessing a register related to LTC 4100, the battery status information is wrote in a proc file system, the power supply management application is provided with upper limit threshold value of the charge quantity of electricity and lower limit threshold value of discharge quantity of electricity, structured battery status information is obtained by the power supply management application from the Proc file system according to the cycle T, and the charge and discharge of the battery of the Smart Battery is controlled. According to the method, the control of the battery status of the Smart Battery based on a Fei Teng processor platform can be implemented at low cost, and the compatibility, the adaptability, the flexibility and the extendibility are good.

The invention discloses an interrupt control method for a Feiteng server. The method comprises the following steps: initialization is performed; a hardware interrupt source generates corresponding types of interrupt signals through a hardware control logic component of a south bridge CS5536, outputs a public interrupt trigger signal through a router of an interrupt controller 8259A of the south bridge CS5536 and modifies corresponding interrupt bits in an internal register of the interrupt controller 8259A, and the public interrupt trigger signal is mapped by a bridge chip to be converted into interrupt messages and transmitted to a PCIE bus; and a Feiteng processor acquires the interrupt messages from the PCIE bus, enters an interrupt state, invokes a public interrupt receptance function and reads the internal register of the interrupt controller 8259A to acquire the interrupt bits so as to determine the hardware interrupt source and treat interrupts. The method provided by the invention can enable the Feiteng processor to receive interrupt messages of equipment CS5536 in a real-time manner and to respond and treat various interrupts accurately and in a real-time manner.

The invention discloses an X graphics system parallel acceleration method based on an FT processor. The implementation steps includes that 1) input and output devices are initialized through an X server main thread, an input event processing subsystem thread is created, an X client program request, a display card management and display output processing request and an input device event are respectively listened, the X client program request is responded through the X server main thread, a display card management drawing subsystem thread used for processing the display card management and processing display output is created by the X server main thread, and the display card management and processing display output request is executed by the display card management drawing subsystem thread; the input device event is read and responded by the input event processing subsystem thread. According to the X graphics system parallel acceleration method based on the FT processor, the X graphic system performance of the FT processor is improved through the multi-core and multi-thread advantage of the FT processor, and the method has the advantages that the utilization rate of hardware resource is high, the user experience is smooth, and the graphic processing performance is high.

The invention discloses an FT-processor based trust management system and method. The system comprises: 1) a terminal management module; 2) a TCM (Trusted Cryptography Module) initialization module; 3) a terminal trust module; 4) a BIOS (Basic Input Output System) measurement module; 5) a USBKey; and 6) a TCM. According to the system and the method, the integrity measurement of a BIOS and an operating system is realized through the TCM, the BIOS and the operating system are ensured to be legal, and the attack caused by destruction of the BIOS or the operating system is avoided; the operational control of a terminal program is realized through the terminal trust module, and the operational environment of the operating system is ensured to be secure and trusted; and flexible management of a trust policy is realized through the terminal management module and the terminal trust module.

The invention provides a Feiteng platform-based double-independent graphics card synchronous display device. The device comprises a system mainboard, two domestic independent graphics cards and a double-graphics card synchronous display module, the system mainboard comprises a domestic Feiteng CPU, Kunlun BIOS firmware, a Kylin operating system, a general PCIE switching chip, a PCIE configurationchip, two PCIE * 16 slots, namely a PCIE * 16 slot A and a PCIE * 16 slot B, wherein the PCIE * 16 slot A and the PCIE * 16 slot B are used for being connected with independent graphics cards in an inserted mode; a display card A on the PCIE * 16 slot A is a main card and is connected with a display to provide display information to the outside; and a display card B on the PCIE * 16 slot B is an auxiliary card and does not directly output display information to the outside. The invention provides a double-graphics-card synchronous display method of a domestic Feiteng platform. The number of primitives rendered by a single display card is reduced, the rendering time is shortened, the rendering speed is finally increased, the graphic performance of the whole machine is remarkably improved, the fluency under the condition that multiple videos are played at the same time is improved, the target scaling roaming response time of a situation system is shortened, and the fluency and user experience are improved.

The invention discloses an intelligent multi-architecture fusion type secure desktop cloud system, which is based on a multi-architecture fusion type autonomous controllable cloud computing platform and a centralized management and control online vocational education and office information system, wherein the multi-architecture fusion type autonomous controllable cloud computing platform is based on autonomous controllable, safe and reliable KunPeng, Loongson/Zhaoxin, Feiteng and Kylin chip processors and a domestic operating system. The system is characterized by comprising a quantum security desktop cloud terminal unit or desktop cloud terminal unit, a cloud resource pool unit, a cloud management platform unit and a security authentication auditing mechanism unit. The invention has the beneficial effects that the system integrates and unifies VDI, IDV and VOI mirror images, and introduces an RDS mode, so that the problem that different and different hardware configurations of various user scenes in different industry fields start a proper cloud desktop is solved, and the resource waste of customers is reduced. Meanwhile, according to the hardware configuration of the user, the appropriate cloud desktop is automatically allocated, the user does not need to think which kind of cloud desktop is used, time and labor are saved for the user, and resources are saved. And the stability of cloud desktop connection is improved, and the user experience can be effectively improved.

The invention discloses a machine type identification method for a multi-hardware-platform FeiTeng server. The method includes the steps of firstly, establishing a platform information field address in an extended ROM (read-only memory) of a computer, and using a virtual machine monitor to package a read-write interface function of the platform information field address and supply the read-write interface function to a kernel of an operating system for calling; secondly, during startup of the operating system, acquiring a bootstrap loading routine instruction received by the operating system first and analyzing hardware platform parameters of the bootstrap loading routine instruction, and writing the hardware platform type information corresponding to the hardware platform parameters into the platform information field address in the extended ROM if the hardware platform parameters are included; and thirdly, reading the hardware platform type information in the hardware platform field address through the read-write interface function of the platform information field address, and identifying a hardware platform of the FeiTeng virtual server according to the platform type information. The method has the advantages of high compatibility, convenience to use and simplicity to operate.

The invention discloses a multi-display output method based on a Feiteng processor platform. The method includes steps of (1) mounting at least two graphics cards; (2) initiating each graphics card and CRTC (cathode ray tube controller) thereof sequentially when an operating system starts up, obtaining total size of buffer frame space of the CRTC, reserving reserved virtual memory space as large as the buffer frame space, one to one mapping frame buffer of the CRTC with virtual memory addresses in the reserved virtual memory space sequentially; (3) caching a picture to be output in the reserved virtual memory space in real time, the CRTC reads the picture segment stored in the virtual memory addresses mapped with the frame buffer of the CRTC, transforms the picture segment into output signals and outputs the signals to the display. The multi-display output method based on the Feiteng processor platform needs no modification of existing video card, is fine in video card compatibility, low in hardware performance requirement, high in display output efficiency, and low in implementation cost.

The invention provides a multi-channel communication system based on a Feiteng platform LPC bus. A programmable logic device supporting various level standards is used as a communication data intermediate processing module between the Feiteng chip and a plurality of external devices, so that a level conversion and protocol conversion chip is omitted, and the Feiteng chip can access a plurality oftypes of external devices through one LPC bus. The multi-channel communication system is simple in circuit structure; manufacturing cost is low, meanwhile, main modules of the multi-channel communication system are integrated in the programmable logic device; and only one path of LPC bus is needed for data transmission of the Feiteng chip, so that the multi-channel communication system is easy toexpand, high in real-time performance, good in portability and low in hardware resource requirement, the software workload is remarkably reduced, and the multi-level requirement of an application system is greatly met.

The invention discloses a dual-verification face comparison system and method based on a Feiteng platform. The comparison system comprises an identity information reading module, a field face visiblelight photograph collection module, a living body detection module, a public security high-definition photograph extraction module, a face comparison module and a Feiteng central processor. The comparison method comprises the following steps that: S1: collecting an infrared photograph via the living body detection module; S2: on the basis of the infrared photograph, carrying out living body detection; S3: comparing a visible light photograph with an identity card photograph by the face comparison module; and S4: comparing the visible light photograph with a Ministry of Public Security photograph by the face comparison module. The system has the beneficial effects that face comparison is carried out on the basis of a domestic Feiteng processor framework, and system performance is better; through the living body detection based on the infrared photograph, various types of "face deceiving type" attacks are effectively avoided; and through a technical scheme that a field face photograph isindependently subjected to dual verification with the identity card photograph and the Ministry of Public Security photograph, face identification accuracy is higher.

The invention discloses a double independent graphics card dynamic switching device and method based on a Feiteng platform. By using the device and method, free switching between foreign high-performance independent display card display and domestic independent display card display can be realized on a universal Feiteng platform, and convenience is brought to a user. A foreign high-performance independent display card and a domestic independent display card are connected with a Feiteng CPU through PCIE slots. A display card existing in a system is actively recognized through a display card switching control module, and display output is conducted according to display card information and display priority setting of the display card information. When the user needs to switch the video cards, the domestic independent video card and the foreign high-performance independent video card can be freely switched for the display only by triggering the button, so that the use of the user is greatly facilitated, and the balance between an autonomous controllable requirement and a high-end graphic application requirement is met.

The invention provides an RAID6 data recovery optimization method based on a Phytium platform. The RAID6 data recovery optimization method based on the Phytium platform comprises the following steps that S1, using an NEON register to carry out single-time multi-byte access; S2, performing recovery factor conversion; S3, carrying out single-time multi-byte double-parity inspection; And S4, storingthe recovered data. The method has the beneficial effects that the design and implementation of the acceleration algorithm are autonomous, and the autonomous controllability is high; the originality of the implementation mode is achieved, the parallelism of data recovery is realized by fully utilizing the NEON characteristic of the Phytium processor and the mathematical relationship between the RAID6 Galois field multiplication tables; The implementation effect is obvious, the single-byte processing before optimization is broadened to 16-byte processing after optimization, and the CPU instruction period occupied by RAID6 data recovery is greatly saved.

A dual BIOS system based on a Feiteng platform is provided. The system comprises a Feiteng processor, a switch connection circuit, a BIOS_1 system, and a BIOS_2 system. The Feiteng processor controlsthe two BIOS systems through the switch connection circuit and a chip select signal. The online upgrade and synchronization process can be implemented on the system, and the synchronization process comprises power-on synchronization and reset synchronization. The technical scheme of the present invention has the beneficial effects that the problem of possible inconsistency of the dual BIOS systemcontent in the Feiteng platform can be solved, and the online upgrade problem of the BIOS system in the Feiteng platform and the possible out-of-synchronization problem of the upgraded dual BIOS system can be solved.

The invention particularly relates to a CAN bus information monitoring method based on a Feiteng processor. The CAN bus information monitoring method based on the Feiteng processor involves a Feiteng processor FT1500A platform, upper computer software and a far-end CAN communication device. The Feiteng processor FT1500A platform is provided with a data processing module, an information monitoring module and a CAN communication module. The data processing module is connected with the information monitoring module and the CAN communication module through an I2C bus and a PCIE bus respectively. The CAN communication module and the far-end CAN communication device are connected through a CAN bus external connecting line and carry out data communication. The upper computer software is connected with the Feiteng processor FT1500A platform through the data processing module. The CAN bus information monitoring method based on the Feiteng processor is scientific in design, convenient to use, applicable to the field of domestic computer servers, convenient to use and popularize and capable of being applied in the field of aviation, ground vehicles, naval vessels, satellites and the like.

The invention provides a method for implementing standby, hibernation and wake-up on a domestic FeiTeng processor, which relates to the field of computer information security. An operating system and a CPU (central processing unit) send standby and hibernation operation commands to a programmable control chip via the SMBUS protocol, and after receiving the commands, the programmable control chip executes the power management of standby and hibernation. The method has the characteristics of simple hardware circuit design and low software code development load, and is a simple and high-efficiency standby and hibernation scheme for FeiTeng portable computers.

The invention discloses a method for realizing interrupt response by using a BMC on a Feiteng platform, and relates to the technical field of computer signal response. The method includes adopting a CPLD to establish communication between a Feiteng platform CPU and a BMC; configuring a GPIO pin in a BMC as an interrupt pin, monitoring an external interrupt signal by using the interrupt pin, sending the interrupt signal and a corresponding interrupt condition to the Feiteng platform CPU through the BMC, and performing a corresponding interrupt response control operation according to the interrupt processing command. By using the method provided by the invention, the interrupt response is completed on the Feiteng platform through the cooperation of the CPU and the BMC; the problem that theCPU performance bottleneck is easily generated due to the fact that the Feiteng platform can only carry out interrupt response through a polling method is solved, and meanwhile the technical scheme has the advantages of being easy and convenient to implement and the like and is suitable for being applied and popularized on the Feiteng platform or other similar platforms.

A monitoring management system of a Phytium server comprises a server main board and a monitoring management board card; a server main body function module, a remote updating BIOS module, a monitoringmodule and a server intelligent monitoring interface are installed on the server main board, and the monitoring management board card is inserted into the server main board through the server intelligent monitoring interface; the server main body function module comprises a Feiteng multi-core processor, a memory slot, a hard disk interface, a communication interface, a multi-specification PCIE slot, a + 5VSTBY independent power supply and an RTC data acquisition module; the Phytium multi-core processor is connected with the remote BIOS updating module; the monitoring management board card comprises a Loongson 2K processor function module, a monitoring upper layer module and a board card intelligent monitoring interface matched with the server intelligent monitoring interface. The monitoring management system can monitor the server mainboard as short as possible, meanwhile, the monitoring chip is convenient to replace, the occupied space is small, and the server can operate quietly like a PC.

The invention discloses a realization method for displaying a Feiteng platform-based AMD display card system LOGO in advance. The method comprises the steps of determining a display card architectureaccording to a device ID of a display card so as to determine a corresponding initialization function; reading an ATOMBIOS from a PCIE ROM space of the display card; extracting parameters such as a memory frequency, a voltage, a working frequency and the like of the display card through the ATOMBIOS, and according to the parameters, initializing the display card; initializing an I2C bus of the display card through the ATOMBIOS, judging connection states of CONNECTORS by utilizing the I2C bus and reading CONNECTORS EDID information in the connection states; according to the EDID information, initializing a frame caching region and finishing corresponding mode setting; enabling corresponding CRTC and ENCODER; and writing corresponding contents in the frame caching region to perform display.

The invention discloses a dual-bridge chip structure of a domestic feiteng processor, wherein, the dual-bridge chip structure of the domestic feiteng processor comprises a feiteng processor, a low-speed bridge chip, a high-speed bridge chip, a SATA interface, a network interface, a USB interface and a plurality of PCI-E expansion grooves; the Feiteng processor and the PCI-E expansion groove are connected with the expansion slot, and the low-speed bridge piece and the flying processor are connected with each other through the PCI-E2.0 signal bi-directional connection, high-speed bridge and flying processor via PCI-E3.0 signal bi-directional connection. The low-speed bridge chip is connected with SATA controller, network controller and USB controller through PCI-E2.0 signal bi-directional connection; the SATA interface and the SATA controller are bidirectionally connected through the SATA signal. The network interface is bidirectionally connected with the network controller through the network signal. USB interface and USB controller are bidirectionally connected through USB signal; High Speed Bridge are connected with Multiple Other PCI-E Expansion slots via PCI-E3.0 signal bi-directional connection.

The invention discloses a network message high-speed processing system and method and relates to the field of network security. A multi-core group framework of a Feiteng processor is utilized, parallel running of functional core groups and a multi-core assembly line way in the functional core groups are adopted, and network message are efficiently processed in parallel; multiple core groups parallel network data packets, the core groups can be beneficially flexible according to network flow, multi-core utilization efficiency is improved, software development is also relatively simple, and smooth migration to the next generation processor platform is facilitated; the network data packets are processed and transferred in an assembly line way by multiple cores in each core group, each core task in an assembly line is single and clear, cache hit ratio is obviously improved, network throughput is improved, and network message processing speed is improved. The network message high-speed processing system and method are applied to network security equipment, so that application field of domestic processors is expanded, domestication level of the network security equipment is improved, andsignificance is produced in the aspect of autonomous controllability of information security.

The invention provides a cloud platform building method based on FT processors. The cloud platform building process comprises the following steps that firstly, a server containing the FT processors is used for building a hardware platform, an operating system based on a domestic architecture is installed, and meanwhile, platform software related to a cloud platform is deployed; then, on the basis of hardware and a system platform, the operating system is added to a cloud platform system by executing relevant operation of the cloud platform, and the operating system is directed at different architecture directories and used for multi-level management of the cloud platform. Compared with the prior art, the cloud platform building method based on the FT processors has the advantages that the cloud platform can support nationwide-produced platform systems, so that the purposes that the cloud platform is higher in compatibility, safe and controllable are achieved; besides, all the systems are managed through the cloud platform, and unified management, unified deployment and unified dispatching are realized.

The invention discloses a security and credibility integrated machine based on a Feiteng processor. The security and credibility integrated machine comprises a machine enclosure and a mainboard, the mainboard is arranged in the machine enclosure, the Feiteng processor is installed on the mainboard and is connected with a TCM chip, a radio frequency card reader is connected to the TCM chip and is connected with a radio frequency recognition card through a radio frequency signal, the Feiteng processor is internally provided with a PCI controller, a storage controller, a display controller, a USB controller and a communication bus, an SSD and a mechanical hard disk are connected to the storage controller, an HDMI interface is connected to the display controller, a high-definition display screen is connected to the HDMI interface, and the mainboard is provided with a heat-dissipation module and is connected with a battery. By using the domestic Feiteng processor, the manufacturing cost of the integrated machine is drastically lowered, equipment can be more conveniently repaired, the service life of the integrated machine is drastically prolonged, the potential safety hazard caused by the adoption of foreign core hardware is reduced, and the integrated machine is worthy of popularization.

The invention discloses a network checksum algorithm optimization method based on a Feiteng platform, and the method comprises the steps: firstly loading 128bit data into an NEON 128-bit register, so as to reduce the number of cycles; dividing the data in the NEON 128-bit register into eight 16-bit data by adopting an NEON vector pairwise addition instruction for pairwise addition, and switching to arc64 assembly for processing when the data stream is processed to a certain length; and then carrying out 64-bit to 16-bit algorithm operation. Compared with the prior art, the network checksum algorithm optimization method based on the Feiteng platform effectively reduces time delay caused by a checksum algorithm when a network UDP receives data, thereby achieving the purpose of improving the UDP packet data transmission efficiency, and has the advantages of autonomous controllability, originality of an implementation mode, obvious implementation effect and the like.

The invention relates to a method for accelerating the read-write efficiency of a nonvolatile memory under a Feiteng server platform, which comprises the following steps of: applying a virtual addressspace in a linux kernel virtual address space, and mapping the virtual address space with a nonvolatile memory physical address space by establishing a page table; if the nonvolatile memory needs toread and write a large amount of data, the data is read and written in parallel through the established multiple device file nodes, the application layer blocks and divides the data needing to be readand written, multiple processes are established, and each process corresponds to one data object; copying the data of the source address space into the destination address space by a read and write function of an equipment driving operation function of a newly established equipment node; and judging whether the result fed back by the driving program is correct or not, if so, continuing copying the next data block, and if not, returning to the abnormal state and terminating transmission.