摘要:
The present invention discloses a memory access apparatus for a message-type memory module, where the apparatus includes: a read-write module, configured to store, to a corresponding DRAM, an SCBC to be stored within a current read-write cycle; and a processing module, configured to: calculate one group of error detecting code for each SCBC in a memory row, and calculate one group of error correcting code for all SCBCs in a memory row; where the read-write module is further configured to: store the error detecting code in an (M+2) th DRAM in the memory row, and store the error correcting code in a Z th DRAM in the memory row, where Z is a positive integer, 1 ‰¤ Z ‰¤ (M+1), and error correcting codes in consecutive (M+1) memory rows are stored in different DRAMs. Embodiments of the present invention further provide a corresponding method. According to the technical solutions of the present invention, fine-granularity encoding protection is performed in a basic read-write unit of SCBC, and variable-granularity memory access is supported, so that error-correcting can be implemented for any multi-bit error in a single DRAM.
摘要:
Embodiments of the present invention provide a memory access method, device, and system, so as to provide a hierarchical and flexible method for setting a memory reliability level to implement a memory access mechanism for different running object types and different reliability levels. The method provided in the embodiment of the present invention includes: receiving, by a memory device, reliability level information of a running object of a processor sent by the processor; establishing a first mapping relationship and a second mapping relationship according to the reliability level information of the running object; receiving an access request sent by the processor; and accessing data of the running object according to the access request and the first mapping relationship, and accessing error-tolerant code of the running object according to the access request and the second mapping relationship.
摘要:
Embodiments of this application disclose a shooting control method and a terminal and relate to the field of terminal technologies. Even if a user forgets to tap a recording start button on a video recording viewfinder screen, the terminal can still record a video, thereby improving human-machine interaction performance of the terminal. A specific solution includes: displaying, by a terminal, a first screen that is not a video recording viewfinder screen; receiving, by the terminal, a first operation of a user on the first screen; in response to the first operation, displaying a video recording viewfinder screen (namely, a second screen), starting to record a first video, and buffering the recorded first video; if the terminal detects a second operation, in response to the detected second operation, stopping, by the terminal, video recording, and displaying a third screen used to prompt the user to determine whether to save the first video; and saving or deleting the first video according to a selection operation of the user on the third screen. The second screen includes a recording start button, and the recording start button is used to trigger the terminal to start video recording.
摘要:
An electronic system (200), a camera module (190, or 210), a SoC (110, or 220), and an electronic device (100) are disclosed. The camera module (210) includes a first bidirectional interface (2101). The SoC (220) includes a second bidirectional interface (2201). The second bidirectional interface (2201) is coupled to the first bidirectional interface (2101), and the first bidirectional interface (2101) and the second bidirectional interface (2201) support a same bidirectional data communication interface protocol. The camera module (190, or 210) can obtain image data, and perform first image processing on the image data to obtain a first image processing result. The SoC (110, or 220) can perform second image processing on the first image processing result to obtain a second image processing result. In this way, the camera module (210) and the SoC (220) are connected to each other through the bidirectional interfaces (2101, and 2201) that support the bidirectional data communication interface protocol, to improve flexibility of an interface between the camera module (190, or 210) and the SoC (110, or 220), so that the camera module (190, or 210) flexibly processes the image data.
摘要:
The present invention discloses a memory access apparatus for a message-type memory module, where the apparatus includes: a read-write module, configured to store, to a corresponding DRAM, an SCBC to be stored within a current read-write cycle; and a processing module, configured to: calculate one group of error detecting code for each SCBC in a memory row, and calculate one group of error correcting code for all SCBCs in a memory row; where the read-write module is further configured to: store the error detecting code in an (M+2) th DRAM in the memory row, and store the error correcting code in a Z th DRAM in the memory row, where Z is a positive integer, 1 ≤ Z ≤ (M+1), and error correcting codes in consecutive (M+1) memory rows are stored in different DRAMs. Embodiments of the present invention further provide a corresponding method. According to the technical solutions of the present invention, fine-granularity encoding protection is performed in a basic read-write unit of SCBC, and variable-granularity memory access is supported, so that error-correcting can be implemented for any multi-bit error in a single DRAM.
摘要:
An apparatus and a method for performing an atomic operation are provided. The apparatus for performing an atomic operation includes a remote direct memory access network interface card RNIC and an input output memory management unit IOMMU. The RNIC is configured to send a memory reading instruction to the IOMMU, where the memory reading instruction includes a target storage address. The IOMMU is configured to: read, in an exclusive manner, arithmetical data from target storage space corresponding to the target storage address, and send the arithmetical data to the RNIC, where the target storage space is provided by a memory. The RNIC is further configured to: perform an arithmetical operation on the arithmetical data to obtain an arithmetical result, and write the arithmetical result into the target storage space by using the IOMMU. The apparatus basically ensures consistency of data storage in the memory, and avoids a data inconsistency problem.
摘要:
A data processing apparatus (100) and a method are disclosed. The data processing apparatus (100) includes a remote direct memory access RDMA module (110), a home agent HA module (120), and a memory module (130). The HA module (120) performs calculation on local data and an operand in an RDMA packet, and writes an obtained calculation result into the memory module (130) through a non-bus interface, which can help prevent reading of the local data from the memory module (130) through a bus and writing of the calculation result into the memory module (130) through the bus. Therefore, the data processing apparatus (100) can optimize a calculation part in a node that performs collective communication, which helps reduce an inter-node communication delay. In addition, the data processing apparatus (100) can reduce a quantity of bus access times, thereby helping reduce bandwidth consumption of the bus.
摘要:
Embodiments of this application provide an energy-efficient display processing method and a device, and relate to the field of electronic technologies, so that graphics processing subsystems with different performance and power consumption can be switched to based on complexity of different to-be-displayed GUIs, to perform GUI display processing. This can reduce overall power consumption of an electronic device and improve energy efficiency of the electronic device. A specific solution is as follows: The electronic device includes a first graphics processing subsystem, a second graphics processing subsystem, and a screen. The first graphics processing subsystem includes a first application processor, a first graphics processing unit, and a first memory. The second graphics processing subsystem includes a second application processor, a second graphics processing unit, and a second memory. The first graphics processing unit renders a first GUI. The screen displays the first GUI. The second graphics processing unit renders a second GUI, and the second GUI and the first GUI belong to different interface types. The screen displays the second GUI. Embodiments of this application are used for display processing.
摘要:
A data processing method and apparatus are disclosed. The method includes: obtaining R groups of proposal region sequences (201), where each group of proposal region sequence includes a plurality of proposal regions; invoking a VRPAC instruction to calculate an area of each proposal region in each group of proposal region sequence (202); for a j th group of proposal region sequence in the R groups of proposal region sequences, invoking a VIOU instruction and a VAADD instruction to determine j suppression matrices of the j th group of proposal region sequence and determine a suppression vector of the j th group of proposal region sequence based on the j suppression matrices (203); and determining an unsuppressed proposal region based on a suppression vector of each group of proposal region sequence (204). The method reduces invoked instructions, reduces instruction execution steps, and shortens a time used in NMS calculation.