58 results about "Write pointer" patented technology

The invention discloses a real-time data receiving and transmitting system and method based on a kernel bypass, and the method comprises the steps: processing the received data when the data receiving and transmitting system receives the data, and achieving the high-level data with complete semantics; updating a write pointer through atomic operation, and writing high-level data into a lockless annular queue in the shared memory module; the upper-layer application module reads the lock-free annular queue in the shared memory; when the data receiving and transmitting system transmits data, upper-layer data to be transmitted is transmitted to the shared memory module, and a write pointer is updated; the upper layer data in the shared memory is read in a polling or interruption mode, a read pointer is updated, the upper layer semantic data is segmented according to the format, a UDP data packet is obtained, the UDP data packet is written into a network card in the polling or interruption mode, and data sending is achieved. Through the data receiving and transmitting system disclosed by the invention, microsecond-level ultra-low delay of data certainty is realized, and efficient decoupling and stable throughput are realized.

The invention discloses a method for realizing accurate synchronization of a time sequence in a simulator based on a shared memory, which relates to the technical field of simulator development and cross-process communication, and comprises the following steps: constructing a standardized three-layer layout comprising a head control region, an annular data region and a compact storage unit, the annular data area circularly accesses, and the compact storage unit binds data and a time sequence; cross-platform zero-leakage resource management is realized through a global singleton handle manager, and interface multiplexing is provided or a shared memory is created and mapped; the sending end encodes data, binds a time sequence and atomically updates a write pointer, and the receiving end reads the data, calibrates the time sequence and atomically updates a read pointer; and executing time sequence precision, transmission delay, throughput and stability verification. According to the method, the lock competition overhead is eliminated, the cross-process data transmission efficiency is greatly improved, the time sequence synchronization accuracy is guaranteed, and the hardware bus refinement requirement is met.

Methods, systems, and devices for zoned random write operations are described. A memory system may receive a set of write commands associated with respective logical block addresses (LBAs) that may be in a sequential order, where the respective LBAs may be associated with a zone. The memory system may write first data to a first physical block address (PBA), where the first data may be associated with a first LBA of the respective LBAs. The memory system may determine whether a second LBA associated with second data is sequential relative to a write pointer associated with the zone. The memory system may write the second data to a second PBA that may be sequential to the first PBA in response to determining that the second logical block address is non-sequential relative to the write pointer and on a value of a bitmap corresponding to the second LBA.

A processing device writes file system data to a first area of a memory zone of a zoned block memory device based on a current position of a write pointer within the memory zone. The file system data comprises data files contained within a file system and file structure metadata describing a file structure of the file system. The processing device detects a write event based on the write pointer advancing past a predetermined memory address within the memory zone that corresponds to a checkpoint. The checkpoint is a second area within the memory zone that is designated for storing write event data. Based on detecting the write event, the processing device writes write event data to the checkpoint, the first write event data indicating a most recent memory address of a root node of the file structure within the memory zone.

The embodiment of the application provides a PXIe-based DMA data transmission processing method, system and device, and belongs to the technical field of data transmission. The method first sends a DMA data read request to a host controller, the host controller is used for applying a ring buffer area to a main memory, and the ring buffer area is used for storing key information corresponding to DMA data; then, a DMA data read instruction sent by the host controller is received, a read difference between a read pointer and a write pointer pointing to the ring buffer area is determined based on the DMA data read instruction, wherein the read difference is obtained by the host controller by calculating the difference between the read pointer and the write pointer; target key information corresponding to target DMA data is read from the ring buffer area according to the read difference, and the read pointer is updated, so that the read pointer points to the latest read key information. The application can improve the efficiency of DMA data transmission while improving the performance of the host control.

The invention provides a communication method and device, electronic equipment, a chip and a storage medium, and relates to the field of communication, and the method comprises the steps: receiving a first write pointer sent by a first communication node; the first write pointer is used for indicating a write-in position of the IP packet information in the first message queue; reading the IP packet information from the first message queue according to the first write pointer so as to update a first read pointer of the first message queue; carrying the IP data packet associated with the IP packet information to obtain a carrying result; writing the carrying result into a second message queue to update a second write pointer of the second message queue; and synchronizing the carrying result, the second write pointer and the first read pointer in the second message queue to the first communication node. Therefore, the carrying result obtained by carrying the IP data packet this time and the two pointers are synchronized to the first communication node together, the first communication node does not need to actively obtain the data through cross-bus in a multi-time interaction mode, and the data transmission efficiency can be improved.

The application discloses a multi-core debugging method, device and system and a storage medium, relates to the technical field of testing, and discloses a multi-core debugging method, which comprises the following steps: a BSP determines a currently started AP in an AP in a multi-core CPU; the BSP determines a first target AP in the started AP and determines a first information buffer area corresponding to the first target AP; the BSP acquires a target write pointer and a target read pointer corresponding to the first information buffer area; if the target read pointer is smaller than the target write pointer, the BSP reads target data in a two-dimensional array of the first information buffer area based on the target read pointer; the BSP stores the target data into an information set buffer area based on the first target AP; and the BSP outputs data in the information set buffer area based on a preset rule. The application realizes that all cores can output debugging information in parallel, so that the debugging of multi-core business logic in a UEFI environment is facilitated.

A storage device according to some example embodiments comprises a non-volatile memory including a first memory including a plurality of zones configured to sequentially store data based on a write pointer, the write pointer indicating a position to write the data, and a second memory configured to store preliminary data to be written in the plurality of zones, and a storage controller configured to receive a plurality of operation requests, each of the plurality of operation requests including a logical block address, a write command, and write data, and store first write data corresponding to a first operation request in the second memory as first preliminary data, if the position of a first logical block address corresponding to the first operation request among the plurality of operation requests and the write pointer does not match.

The invention belongs to the field of remote direct memory access, and discloses a bitmap-based RDMA (Remote Direct Memory Access) data packet out-of-order receiving circuit and method, a bitmap checking module verifies the validity of a data packet and outputs a bitmap switching identifier, and a bitmap management module maintains pointer information through three states of order, out-of-order and bitmap updating; the bitmap information storage module is used for storing bitmap information, calculating the offset of a bitmap writing pointer in an out-of-order state and starting a fragmentation timeout mechanism, generating a window sliding enable signal when the bitmap state is updated, the bitmap information storage module responds to the enable signal to execute bitmap writing and window sliding updating, and the bitmap pointer storage module manages a multi-queue bitmap state identifier and a pointer in an RAM (random access memory) structure. By adopting the circuit, the bandwidth waste and congestion risk caused by retransmission can be obviously reduced; the tail delay jitter is reduced; and the adaptive capacity to multi-path network disorder is enhanced, so that the bandwidth utilization rate and the transmission reliability are comprehensively improved.

A kind of DAS signal adaptive demodulation method and system based on FPGA, wherein, the method comprises: obtaining the in-phase component signal and quadrature component signal of DAS signal;When the address of write pointer occurs incremental change, the historical in-phase component signal and historical quadrature component signal in the preset history sampling window are read;The instantaneous amplitude energy of each time stamp is calculated, and the instantaneous amplitude energy sequence is obtained;The amplitude energy mean and variance eigenvalue of DAS signal are calculated;Adaptive gain factor is generated;The in-phase component signal and quadrature component signal are compensated and iteratively demodulated by adaptive gain, and the phase output value and demodulation module length value are obtained;The module length deviation amount of demodulation module length value and preset standard module length is calculated, and when the cumulative value is greater than preset locking threshold, the correction coefficient is calculated according to the current amplitude energy mean and module length deviation amount;The storage value of index address is updated based on correction coefficient.The application can improve the reliability of DAS system.

The embodiment of the invention discloses a data storage method, relates to the technical field of data storage, and is used for improving the security of WORM storage equipment. The method is applied to the storage device, the storage device comprises a tape reel, the tape reel comprises a controller, the controller comprises a one-time programmable module, and the method comprises the steps that a write instruction is obtained, and the write instruction carries a first write pointer; if a first identifier is stored in the one-time programmable module, security verification is carried out on the first write pointer, and the first identifier is used for identifying the storage device as a WORM device; and if the security verification is passed, writing data carried in the write instruction into a storage space provided by the tape disk.

The invention discloses a multi-core debugging method, device and system and a storage medium, and relates to the technical field of testing, and the multi-core debugging method comprises the steps that a BSP determines a currently started AP in APs in a multi-core CPU; the BSP determines a first target AP in the started APs, and determines a first information buffer area corresponding to the first target AP; the BSP obtains a target write pointer and a target read pointer corresponding to the first information buffer area; if the target read pointer is smaller than the target write pointer, the BSP reads the target data in the two-dimensional array of the first information buffer area based on the target read pointer; the BSP stores the target data to an information set buffer area based on the first target AP; and the BSP outputs the data in the information set buffer area based on a preset rule. According to the method and the device, all the Core can output the debugging information in parallel, so that the debugging of the multi-core service logic in the UEFI environment is realized.

Provided are a data compression storage device and a method thereof based on a ZNS standard. A method for processing an IO command is provided, comprising: a host providing a first command for writing data to a first storage area (Zone) to a storage device; the storage device allocating a first logical address index for data to be written by the first command according to a write pointer (WP) of the first storage area, the first logical address index and a first size of the data to be written by the first command defining a first logical address space; compressing the data to be written by the first command to obtain compressed data; storing the compressed data; recording an address of storing the compressed data in association with the first logical address index; and providing the first logical address index to the host; and the host recording a first host logical address (HLBA) accessed by the first command in association with the first logical address index.

A memory sub-system comprises a controller managing memory devices. The controller is configured to: maintain a write pointer referencing a next data item position within a log buffer; maintain a log retrieval pointer referencing a data retrieval position within the log buffer; store at a log buffer position specified by the write pointer, a data item reflecting a state of the system; advance the write pointer by a size of the data item; responsive to receiving, from a host, a log retrieval request, retrieve log data starting from the position within the log buffer referenced by the log retrieval pointer; transmit the retrieved log data to the host; advance the log retrieval pointer by a size of the retrieved log data; and responsive to determining that at least a part of log data has been overwritten in the log buffer, set the log retrieval pointer to match the write pointer.

The invention provides a heterogeneous computing system, a server and a heterogeneous computing method. The system comprises a server and a computing device, the server and the computing device share a data queue, and a shadow variable is arranged in the server; the server comprises n threads; when K threads in the n threads concurrently add messages to the data queue, the K threads are configured as follows: the K threads seize shadow variables through atomic operation respectively, when any one thread in the K threads successfully seize the shadow variables through the atomic operation, the shadow variables are updated, and when the shadow variables are not successfully seized through the atomic operation, the shadow variables are updated; the thread which successfully preempts the shadow variable can write the message into a sequence queue, and after the message is written into the data queue, the value of a write pointer of the data queue is updated according to the updated shadow variable; a thread in a computing device is configured to read a message from a data queue for processing, and after reading the message, update a value of a read pointer of the data queue. The performance of the heterogeneous computing system can be improved.

The application relates to a used ring updating method and module, a backend device, a medium, a device and a chip, and comprises the following steps: when receiving packet updating information of any queue, storing the packet updating information into a storage unit; if the number of the packet updating information of the queue in the storage unit is equal to n, generating a first write request and a second write request according to the n packet updating information, and sequentially sending the first write request and the second write request to a DMA processing module, so that the DMA processing module writes pointer values and data packet lengths of the n packet updating information into the used ring table according to the first write request, and writes the index of the last received packet updating information in the n packet updating information into the used ring table according to the second write request. According to the application, the data packet receiving speed is improved.

The invention discloses an audio controller, an audio control method, computing equipment and a chip, and belongs to the field of audio control. The audio controller comprises a register module and a command control module; the register module is used for storing a command writing pointer, the command writing pointer is used for indicating a next writable storage position in a command annular buffer area, and the command annular buffer area is used for storing a first control command which is sent by a remote host and aims at the audio codec; and the command control module is used for reading the first control command from the command ring buffer area according to the command write pointer and sending the first control command to the audio codec. In the application, the audio controller realizes control command transmission between the far-end host and the audio codec based on an annular buffer mechanism, and the problem of transmission of the control command between the far-end host and the audio codec is solved.

The invention relates to the technical field of embedded computing and system collaboration, in particular to a multi-operating system heterogeneous collaboration method based on a lightweight message bus and related equipment. According to the method, a cross-operating system data exchange basis is established by initializing a shared memory annular buffer area and setting access authority; a message bus application interface is used for completing multi-system service registration in the unified namespace, and a service identifier mapping table is generated; the sender operating system efficiently writes the message data into a target buffer area based on a zero copy mechanism and triggers a notification signal; the receiver operating system analyzes the message according to the read-write pointer and outputs a processing state; and finally, efficient communication and running state monitoring among multiple operating systems are realized through event synchronization and a watchdog mechanism. According to the method, efficient heterogeneous cooperative execution among multiple operating systems is realized in a light-weight, low-delay and low-power-consumption manner, and the cross-system data interaction efficiency and the operation stability are remarkably improved.

During a low power mode, a fast clock may not be provided to serial / parallel conversion circuitry. An asynchronous gating signal that controls the gating of the fast clock may be synchronized to a slow clock and the fast clock. The frequency of the fast clock may be an integer multiple of the slow clock, such that gating the fast clock based on the fast-slow clock synchronized gating signal results in the gating of the fast clock lasting for a duration that may be an integer multiple of the serialization factor multiplied by the conversion circuitry FIFO buffer depth. This maintains the relationship between the FIFO buffer's read and write pointers and associated clocking circuitry during the clock shutoff period. By maintaining these relationships during the clock shutoff period, the serial / parallel conversion circuitry may enter and exit the low power mode without requiring retraining as data path latencies remain unchanged.

The invention relates to the technical field of solid state disks, in particular to a ZNS SSD management command optimization processing method. The method comprises the following steps of: deploying a plug-in at a host end to realize regional information management and IO (Input / Output) truncation processing, dividing a physical region of a ZNS SSD into four queues, namely freezone (idle), invaridzone (ineffective), active zone (active) and finishingzone (to be completed), and dynamically managing the four queues, namely the free queue, the invaridzone (ineffective), the active zone (active) and the finishingzone (to be completed); according to the FINISH instruction, writing pointer information is modified to replace filling writing operation, and meanwhile, a corresponding physical area is added into a finishingzones queue; reconstructing on the basis of a physical region in the finishingzones queue, and mapping a free space of a plurality of regions which are not fully written into a new logic region; a delay execution strategy is adopted for the RESET instruction, and actual erasure operation is triggered only when physical area data is completely invalid or an idle threshold value exists. According to the method, the problems of high time delay, resource contention and unbalanced wear caused by FINISH instruction filling and writing in the ZNS SSD are solved, the interference of a management command on read-write IO is effectively reduced, the utilization rate of a storage space is improved, and the service life of the ZNS SSD is prolonged.

Techniques for providing a return address stack with branch mispredict recovery are disclosed. A processor core is accessed. The processor core includes a return address stack (RAS), a local cache hierarchy, and branch prediction logic. RAS state information, including a write pointer, a read pointer, and a RAS count, is sent to a branch execution unit. One or more call instructions are detected in an instruction stream. The detecting generates a predicted return address for each of the one or more call instructions which are pushed on the RAS. The pushing is directed by the write pointer. One or more return instructions are recognized in the instruction stream. The write pointer and the read pointer for the RAS are updated, based on information from the branch execution unit. The predicted return address for each of the one or more return instructions is popped from the RAS.

This application provides a method, apparatus, system, network chip, and network interface card for aging request processing. The method includes: allocating available resources to at least two aging requests based on available resource information of an aging queue, and recording the available resource indexes corresponding to the at least two aging requests, wherein the at least two aging requests write aging information into the same aging queue; sending the aging requests to the aging queue according to their order, and recording the order of the aging requests using a FIFO; receiving current response information returned by the aging queue after responding to the aging requests; and updating the write pointer of the aging queue according to the order, the current response information, and the available resource indexes. According to the technical solution of this application, the problem of degraded processing performance caused by prolonged locking / unlocking time can be solved.

The invention provides a visual identification optimization method and system, electronic equipment and a storage medium, and the method comprises the steps: checking a current parameter of equipment, and determining a checked equipment parameter; performing data capture on the equipment with the adjusted equipment parameters to obtain original byte data; converting the original byte data to obtain a floating-point array; preprocessing the floating point type array to obtain preprocessed data; and writing the preprocessed data into an index position of the memory mapping file in a specified format by using a write pointer to obtain the written memory mapping file. According to the visual identification optimization method, initialization adjustment and original byte data conversion are carried out on the current parameters of the equipment, so that the accuracy and reliability of original byte data input are ensured, and a solid foundation is laid for subsequent image processing and analysis.

This application discloses a data processing method, an electronic device, and a storage medium. The data processing method includes: in response to a data write request for a first disk, determining the target data to be written to the first disk and the first position information of the write pointer in the first disk; if the first position information is a preset endpoint position, moving the write pointer to a preset start position; if the first position information is not a preset endpoint position, moving the write pointer in a first preset direction by a first preset distance; determining whether a target cache fragment exists in a cache fragment of the first disk according to second position information; and in response to the existence of a target cache fragment in a cache fragment of the first disk, replacing historical data in the target cache fragment with the target data. This application can achieve both cleaning up aging data and saving resources.

Embodiments of this disclosure disclose a method for data security check in an integrated circuit, and a medium. The method includes: determining, according to an address corresponding to a write pointer, a first address segment in which a first set of data is written into a first memory located in the integrated circuit; storing the first set of data into a storage space of the first address segment in the first memory; determining target encoded data based on the first set of data; storing the target encoded data into a second memory located in the integrated circuit, where the first memory is different from the second memory; and performing, based on the target encoded data, security check on a second set of data that is read from the first memory.

The invention provides an FIFO circuit and electronic equipment, and relates to the technical field of circuit design. In the FIFO circuit, an input cache module comprises n input registers and is used for receiving n pieces of to-be-stored target data output by an upstream circuit; the storage module comprises a storage controller and a memory, the memory is divided into n virtual FIFOs, and the n virtual FIFOs are in one-to-one correspondence with the n input registers; the first address management module is used for determining a virtual FIFO meeting a first hit condition in the n virtual FIFOs as a first virtual FIFO in each clock cycle, generating a corresponding write address of a write pointer of the first virtual FIFO in the memory, sending the write address to the memory controller, and sending the write address to the memory controller; a first input register corresponding to the first virtual FIFO is controlled to output target data to a storage controller; the memory controller is to write the target data to the memory based on the write address. According to the invention, the occupied area of the whole circuit of a plurality of FIFOs can be effectively reduced, and the efficiency of the whole area is improved.

The present application relates to an integrated circuit, a cross-clock domain data transmission method, an electronic device, and a storage medium. The integrated circuit comprises a first clock domain and a second clock domain; the first clock domain comprises a first pointer control module; the second clock domain comprises a second pointer control module; the first pointer control module comprises a first synchronization pointer control module; the first synchronization pointer control module is configured to: in response to the frequency of the first clock signal being greater than that of the second clock signal, on the basis of a second clock phase and a second clock period of the second clock domain, the first clock signal and a first clock phase of the first clock domain, determine a phase relationship between the first clock signal and the second clock signal, and determine a first pointer control signal on the basis of the phase relationship; and in response to the frequency of the first clock signal being smaller than that of the second clock signal, determine that the first pointer control signal is a first value, so that a first read pointer and a first write pointer increase by the first value in each clock period of the first clock signal.

The application discloses a kind of based on shared memory implementation simulator in timing accurate synchronization method, it is related to simulator development and cross-process communication technical field, including the construction containing head control area, annular data area, compact storage unit Standardized three-layer layout, head control area uses Rust atomic type encapsulation control parameter, annular data area cyclic access, compact storage unit binding data and timing;Through global singleton handle manager, realize cross-platform zero leakage resource management, provide interface reuse or create shared memory and map;Sending end encodes data and binds timing, atomically updates write pointer, receiving end reads data and calibrates timing, atomically updates read pointer;Timing accuracy, transmission delay, throughput and stability verification are executed.The application eliminates lock competition overhead, greatly improves cross-process data transmission efficiency, guarantees timing synchronization accuracy, adapts hardware bus fine demand.

This invention relates to the field of chip design technology, and in particular to a method, electronic device, and storage medium for reading variable-length data from a circular buffer. The method divides the circular buffer into multiple consecutive fixed-length sub-regions and one variable-length sub-region based on the total capacity of the circular buffer and the maximum allowed data length for each read. Each time data is read from the circular buffer, the target data length of the valid data in the sub-region where the read pointer is located is determined comprehensively based on the relationship between the read and write pointers, whether they are in the same sub-region, and whether the sub-region where the read pointer is located is a variable-length sub-region. Data of the target data length, starting from the position pointed to by the read pointer, is read from the sub-region where the read pointer is located, and the read pointer is updated according to the target data length. This solves the problems of latency and consumption of additional hardware resources.