Patents
Literature
237 results about "Lower priority" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
There is a simple way to lower the priority of a running program which is through the Windows Task Manager. You can view the current priority for all processes by going to View -> Select Columns… and ticking Base Priority. Then simply right click on the process -> Set Priority and drop it down to BelowNormal or Low.
Grouping intruder video events from smart security cameras into priority groups for efficient video monitoring
ActiveUS12462657B1Closed circuit television systemsBiometric pattern recognitionVideo monitoringEvent level
A system comprising security devices and a computing device. The security devices may each be configured to detect an event in response to video frames and audio and communicate the video frames, the audio and a notification of the event. The computing device may be configured to execute one or more steps, the steps comprising performing a classification of the notifications of the events into a plurality of event levels and displaying a list of the notifications of the events according to the classification. Each of the plurality of event levels determined to be high priority events are added to a top of the list as the high priority events are detected. Each of the plurality of event levels determined to be a lower priority than the high priority events are added to the list below the high priority events as the events with the lower priority are detected.
Owner:KUNA SYSTEMS CORP
Priority scheduling method and system for on-orbit data processing tasks
The invention discloses a priority scheduling method and system for an on-orbit data processing task. The method comprises the following steps: constructing a DAG model, decomposing a macroscopic task into subtasks, defining a subtask dependency relationship, and endowing a subtask node with a priority attribute; setting or dynamically adjusting the priorities of the sub-tasks according to task service types, processing delay requirements or external instructions; maintaining a schedulable queue containing subtasks which have completed precursor tasks and meet scheduling conditions; calculating task scheduling priority indexes based on the queue, sorting, and selecting optimal calculation resource allocation; the priority is dynamically adjusted according to task waiting time or an external instruction during execution, and hunger of low-priority tasks is avoided; the multiple processing units execute the high-priority tasks in parallel according to needs; and after the task is completed, updating a subsequent node dependency state, and adding a new schedulable task cycle. According to the method, high-priority task resource allocation can be guaranteed preferentially, low-priority task hunger is avoided, and the overall throughput rate of the system and the self-adaptive capacity to on-orbit diversified tasks are remarkably improved.
Owner:HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)
CAN message priority dynamic arbitration method and system based on event triggering
The invention discloses a CAN message priority dynamic arbitration method and system based on event triggering, and the method comprises the steps: obtaining a discrete sampling signal of a CAN node of an engineering vehicle and a state register value of a CAN controller, converting the discrete sampling signal into a working condition data sequence, and obtaining a bus load rate through the state register value; obtaining an event state sequence according to the working condition data sequence; all CAN messages to be sent are constructed into a message data record, and the message data record with event semantics and dynamic priority labels is obtained according to the protocol data unit and the event state sequence; and according to the bus load rate and the event state sequence, sending a message data record with event semantics and dynamic priority annotations by adopting a token bucket mechanism through a three-level priority queue linked with a three-state state machine. According to the invention, the security key message in the system can still be transmitted in time under high load, and the bandwidth occupation and delay jitter caused by the low-priority message are avoided at the same time.
Owner:JIANGSU ADVANCED CONSTR MASCH INNOVATION CENT LTD +1
Multi-factor collaborative dynamic priority task scheduling method based on waiting time feedback
PendingCN121541988AProgram initiation/switchingResource allocationSelf adaptiveDistributed computing
The invention provides a multi-factor collaborative dynamic priority task scheduling method based on waiting time feedback, which is characterized by comprising the following steps of: initializing waiting time, task criticality and weight values of queue length, initializing a mixed task set and a task waiting queue, and initializing the task waiting queue into an empty set; entering a task waiting queue; updating the priorities of all tasks in the task waiting queue; sorting the tasks in the task waiting queue according to the priority; monitoring whether a new task arrives in real time; judging whether the newly arrived task meets a preemption condition or not; updating the historical average waiting time of the task; updating weight values of task waiting time and queue length; and judging whether all tasks in the mixed task set are scheduled. According to the method, long-term hunger of low-priority tasks is avoided, and the average waiting time of the tasks is shortened; the preemption threshold value is dynamically adjusted, and the context switching overhead is reduced; a dynamic weight mechanism is designed, and the self-adaptive capacity of the system is improved.
Owner:SHANGHAI AEROSPACE CONTROL TECH INST
User-configurable object generation
A system may receive a request to generate an object. A system may generate, based on the request, a first portion of a prompt associated with a first layer of a hierarchy and a second portion of the prompt associated with a second layer of the hierarchy, where the second layer has a lower priority than the first layer. A system may generate the object based in part on providing the portions of the prompt as input to a machine learning model, where the object is formatted according to an object format and is internally consistent. To generate the object the machine learning model does not violate instructions associated with a layer of the hierarchy based on instructions associated with a layer of the hierarchy having a relatively lower priority.
Owner:AMAZON TECH INC
MoE batch reasoning method and system based on priority differential cache
PendingCN121636154AResource allocationGeneral purpose stored program computerVideo memoryThresholding
The invention belongs to the technical field of computers and artificial intelligence, and discloses a priority differential cache-based MoE batch reasoning method and system, and the method comprises the steps: recognizing global hot experts with higher activation frequency in each layer, enabling the global hot experts to remain in a high-priority cache during initialization, and building a priority list of the experts in each layer; in the reasoning stage, selecting an expert set needing to be activated in the current layer; the expert priority score is dynamically updated according to the activation and reuse behaviors of the experts, and the experts are migrated and replaced among the high-level cache, the middle-level cache and the low-level cache according to the priority score and a cache threshold value; according to a current layer gating result and a historical activation track, predicting an expert set which may be activated in a next layer, and asynchronously loading the expert set to a low-priority cache during current layer calculation so as to realize time overlapping of calculation and communication. According to the method, the expert migration frequency can be reduced, the cache hit rate and the throughput rate are improved, the video memory utilization rate is remarkably optimized, and good expansibility and universality are achieved.
Owner:HUAZHONG UNIV OF SCI & TECH
Adaptive data packet scheduling method based on approximate quantile and multiple queues
The invention provides a self-adaptive data packet scheduling method based on approximate quantiles and multiple queues on a programmable data plane, and aims to solve the problem that the scheduling performance and the resource efficiency are difficult to balance in the prior art. According to the method, lightweight ranking scoring, dynamic queue mapping and a cascade enqueue strategy are combined. A relative priority score of the data packet is efficiently calculated through a minimum-maximum normalization mechanism; adaptively mapping the data packets to one of a plurality of FIFO queues according to the scores and real-time congestion conditions of the queues, and providing a fast channel for extremely high priority traffic; and when the target queue is full, trying to store the data packet into a queue with a lower priority in a cascading manner so as to avoid unnecessary discarding. According to the method, resource consumption and implementation complexity are remarkably reduced while the approximate ideal PIFO scheduling performance is achieved, and the method is particularly suitable for resource-limited environments such as a software-defined network and edge computing.
Owner:JIANGSU UNIV
Electronic control device
To extremely restrain variation in time until a low-priority cyclic task starts to be executed even if an interruption task is executed when a high-priority cyclic task and a low-priority cyclic task are executed as cyclic tasks at each control period.SOLUTION: In a control period in which an interrupt task is executed and execution of at least one portion of a high-priority cyclic task is disabled, the start timing of a low-priority cyclic task is corrected at timing earlier than timing when it is assumed that the high-priority cyclic task is entirely completed. For this reason, even if an interrupt task is executed, an influence of time required for the interrupt task on the start timing of a low-priority cyclic task can be reduced. As a result, even if an interrupt task is executed, variation in time until low-priority processing starts to be executed after a control period is started can be restrained as much as possible.SELECTED DRAWING: Figure 2
Owner:DENSO CORP
Transmission method and terminal device
A transmission method and a terminal device are provided. The transmission method includes: when configuring a configured grant retransmission timer, a terminal device determining a hybrid automatic repeat request process and / or the state of the timer on the basis of a satisfied condition. By means of the embodiments of the present application, the transmission delay of a resource, especially a low-priority resource, can be reduced.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD
Intelligent power distribution control method of Internet of Things charging station fused with panoramic image comparison
The invention discloses an Internet of Things charging station intelligent power distribution control method fused with panoramic image comparison. The method comprises the following steps: deploying a sensing unit through an electric-red Internet of Things system to collect multiple pieces of panoramic sensing information; generating an initial sub-image, fusing the environment parameters to mark an abnormal region, and splicing to form a target panoramic image of the charging station; calling a preset panoramic image as a reference; comparing the target panoramic image with a preset panoramic image, and outputting an abnormal event when the difference exceeds a set range; calculating a priority score for the abnormal event, and generating an instruction execution sequence; cooperative instructions are generated according to a sequence, and conflicts are solved. During target conflicts, high-priority instructions cover low-priority instructions, compensation instructions are generated, and optimal redistribution is carried out according to efficiency during resource conflicts. And the target equipment issues a control instruction to realize dynamic adjustment of the power distribution parameters. Through power distribution parameter dynamic adjustment and instruction control, line loss and energy waste are reduced, and high-concurrency charging requirements are met.
Owner:CHINA SOUTHERN POWER GRID ELECTRIC VEHICLE SERVICE CO LTD
AUTOSAR multi-task-oriented nested lock management and real-time priority scheduling control system
The invention belongs to the technical field of automotive electronics AUTOSAR, and discloses an AUTOSAR multi-task-oriented nested lock management and real-time priority scheduling control system, a detection and prevention module establishes a dynamic resource allocation diagram by taking tasks and locks as nodes, real-time traversal is performed in combination with a depth-first search algorithm, and a task-lock-task circulation path is accurately identified; when a potential deadlock is detected, preferentially releasing a low optimal lock occupied by a low-priority task through priority arbitration, and triggering an overtime release mechanism when the priorities are the same; a scene of accessing multiple layers of shared resources by multi-task nesting under an AutoSar framework is adapted, so that the system is ensured to stably run in a complex concurrent scene, and function failure caused by deadlock is avoided; the priority scheduling module establishes a scheduling rule in combination with dual priorities of tasks and locks, optimizes a nested priority inheritance mechanism, temporarily improves the priority when a low-optimal task occupies a lock required by a high-optimal task, and configures a preemption right for the high-optimal lock.
Owner:JEE AUTOMATION EQUIP SHANGHAI CO LTD
WebWorker cooperative interrupt scheduling processing method and device for high-frequency time sequence monitoring data
The invention discloses a WebWorker cooperative interrupt scheduling processing method and device for high-frequency time sequence monitoring data. The method comprises the following steps: splitting original high-frequency time sequence monitoring data into a plurality of tasks according to a statistical dimension in a main thread, and endowing the tasks with priorities; utilizing the minimum heap maintenance task queue to split each task into fragmentation units which can be independently executed; dynamically creating a Web Worker pool according to the core number of the central processing unit, and executing a current fragmentation unit in any Worker in the Web Worker pool through a scheduling controller; if the task of which the priority is higher than that of the current fragmentation unit is detected, interrupting the current fragmentation unit, storing the execution state of the current fragmentation unit, and preempting the fragmentation unit for executing the high-priority task by the thread; and increasing the weight of the low-priority task along with time through a starvation detection mechanism until the low-priority task is executed, and transmitting a task processing result to the main thread for visual rendering.
Owner:WUHAN HONGXIN TECH SERVICE CO LTD
Resource scheduling method and device, equipment, medium and program product
The invention provides a resource scheduling method which can be applied to the fields of cloud computing and artificial intelligence. The resource scheduling method is applied to a service processing system containing heterogeneous computing resources and comprises the steps that service request load prediction information in a preset time period is obtained, the batch processing scale of each priority is determined by combining service priorities and a response time limit threshold value, and the batch processing scale of the high priority is smaller than the batch processing scale of the low priority; based on the batch processing scale and the memory consumption characteristic parameters, calculating the memory capacity required by the task, and screening candidate computing resources with sufficient available memories; according to the batch processing scale, the calculation feature parameters and the candidate resource performance parameters, calculation execution time delay and combination of queuing time delay, determining predicted completion time; and in the candidate resources meeting the response time limit threshold, selecting the resource with the smallest number of calculation units to execute the task. The invention further provides a resource scheduling device and equipment, a medium and a program product.
Owner:INDUSTRIAL AND COMMERCIAL BANK OF CHINA
Techniques for caching media content when streaming live events
In various embodiments, a live event caching application caches segments that are associated with live events. At a first point-in-time, the live event caching application stores a segment of a downloadable that is associated with a live event in a high priority list. At a second point-in-time, the live event caching application determines that the segment is at a tail of the high priority list, where the second point-in-time is subsequent to the first point-in-time. Upon determining that the segment is at the tail of the high priority list, further determining that an age of the segment is greater than a cutoff threshold. In response to determining that the age of the segment is greater than the cutoff threshold, moving the segment from the high priority list to a low priority list.
Owner:NETFLIX INC
System and method of exclusive memory access among multiple processing devices
A processing system including processing cores, a shared memory, a shift table that stores a maximum number of reservations to locations in the memory, and an exclusive monitor that uses the shift table and an eviction policy to enforce core synchronization. The eviction policy is based on priority, age of valid reservations, shift table fullness state, and reservation memory conflict. The shift table may include a memory address and a size value indicative of a flexible amount of reserved memory at the memory address. The exclusive monitor evicts an oldest reservation in the shift table having a same or lower priority level as the new reservation. The exclusive monitor rejects the new reservation when the shift table is full of higher priority reservations. Reservations are shifted to maintain age status. Stale reservations may be invalidated or have their priority lowered. Conflicting reservations may be made with the same priority level.
Owner:NXP USA INC
Electronic device and operation method thereof
ActiveUS12634534B2Selective content distributionTransmissionProcess engineeringIndustrial engineering
An operating method of an electronic apparatus includes receiving multi-streams that include a first to N-th streams in a descending order of priority, obtaining multi-content corresponding to the multi-streams, and outputting the multi-content in a multi-view mode so that the multi-content corresponding to the multi-streams is respectively output to a plurality of partial screens. The receiving of the multi-streams includes determining a bit rate of each of the multi-streams according to priorities among the multi-streams and buffering each stream at the determined bit rate, and the multi-streams include a main stream having a higher priority and one or more sub-streams having a lower priority than the main stream.
Owner:SAMSUNG ELECTRONICS CO LTD
Self-adaptive task priority management method based on dynamic entropy weight and time decay factor
The invention discloses a self-adaptive task priority management method based on a dynamic entropy weight and a time decay factor, and relates to the technical field of computer task scheduling and resource allocation. The method comprises the following steps: acquiring a to-be-processed task set and constructing a multi-dimensional feature matrix, dividing features into benefit type indexes and cost type indexes, and respectively carrying out same-direction standardization processing on data by adopting forward and reverse normalization formulas; calculating entropy values and difference coefficients of the characteristic indexes in real time based on an information entropy theory, determining dynamic weights reflecting current task flow characteristic distribution, and calculating static basic scores of the tasks; introducing an exponential time decay model containing a natural constant and a time sensitive coefficient, performing nonlinear acceleration compensation on the static basic score according to the queue residence time of the task, and generating a final dynamic priority index; and screening the task corresponding to the maximum value according to the index to preferentially allocate computing resources. According to the method, the blindness of manual weighting can be eliminated, the hunger and deadlock problems of low-priority tasks are effectively solved through an exponential-level time compensation mechanism, and the method has the advantages of low algorithm complexity, high environment adaptability, high scheduling fairness and the like.
Owner:NANJING INST OF MECHATRONIC TECH
A lightweight log generation method, system and electronic device
The application provides a lightweight log generation method, system and electronic equipment, and relates to the technical field of computer software.The method comprises the following steps: creating a running log management task and an operation log management task with lower priority than an application task, and establishing a message queue; when a log event is generated by the application task, a formatted log message containing a timestamp, a log level, a module identifier and content is generated and sent to the message queue; the log management task asynchronously acquires the log message, and distributes the log message to a running log folder or an operation log folder according to the log level and type; and the size of the log file is monitored, and when the capacity threshold is reached, a cover writing mechanism is enabled to recycle the file storage area.The application realizes asynchronous decoupling of log recording and the application task, supports hierarchical classified storage and cyclic coverage, significantly improves the maintainability and debugging efficiency of the embedded system while ensuring real-time performance, and meets the lightweight log demand in a resource-limited environment.
Owner:SOUTHWEST CHINA RES INST OF ELECTRONICS EQUIP
A GPU warp scheduling method and device based on a chessboard scheduling strategy
The application provides a GPU Warp scheduling method and device based on a chessboard scheduling strategy, and the method comprises the following steps: a stream multiprocessor assigns a Warp number to each task of different task types received through a facing Warp numbering mechanism, the priority of each Warp is determined according to the task type and the Warp number, the Warp with high priority is preferentially executed, if the current Warp execution is overdue, the priority of the Warp is dynamically adjusted, and the Warp with low priority is executed in turn. The facing Warp numbering mechanism is used to realize the priority ordering of the Warps of different task types, and the dynamic priority adjustment mechanism based on the execution time threshold can guarantee that the high-priority task is preferentially executed, also take into account that the low-priority task can be executed in a hidden manner, ensure fairness, and improve resource utilization.
Owner:WUHAN LINGJIU MICROELECTRONICS CO LTD
Io flow rate limiting control method and device, electronic equipment and storage medium
ActiveCN120891990BProgram initiation/switchingInput/output to record carriersRate limitingProcessing
The application discloses an IO flow rate limiting control method and device, electronic equipment and a storage medium, relates to the technical field of computer data storage, and comprises the following steps: configuring concurrent processing parameters and total capacity parameters of a task pool; identifying the request type of a newly arrived input / output request, and distributing the input / output request to a corresponding queue in the task pool or the cache pool according to the request type and the task pool state; checking the task pool and the cache pool state at a preset time interval, and scheduling the input / output request in the cache pool to the task pool according to a priority order; when a high-priority input / output request arrives and the task pool is full, transferring low-priority input / output requests in the task pool to the cache pool, and limiting the allocation of computing resources to IO requests. The technical problems that related technologies lack flexible and dynamic regulation and control mechanisms can be solved, the processing efficiency of the system for IO requests and the resource utilization rate are improved, and the stability and reliability of the distributed storage system are enhanced.
Owner:JINAN INSPUR DATA TECH CO LTD
Multitask priority determination method, resource allocation method and resource arbiter
The invention discloses a multi-task priority determination method, a resource allocation method and a resource arbiter, and relates to the technical field of computers. In the method, the initial priorities of the multiple tasks are adjusted based on the initial priorities of the multiple tasks and the access information when the multiple tasks access the shared resources, that is, fixed priorities are not set for the tasks, so that the fairness when the tasks access the shared resources is improved; the priority of the task is adjusted, so that the priority of the previous task with low priority may become higher, namely, the delay of the previous task with low priority is reduced; due to the fact that the tasks are sorted according to the priorities, when the tasks access the shared resources according to the priority sequence, low delay of the tasks with the high priorities is guaranteed, and the efficiency of accessing the shared resources by the tasks is improved; and thirdly, the weights of the tasks are determined based on various factors such as the classification levels of the tasks, the membership degrees when the tasks belong to the corresponding classification levels and the rule weights, so that the accuracy of the target priorities of the multiple tasks is improved.
Owner:SHANDONG YUNHAI GUOCHUANG CLOUD COMPUTING EQUIP IND INNOVATION CENT CO LTD
Priority-based cache line fitting in compressed memory systems of processor-based systems
ActiveCN118369652BMemory architecture accessing/allocationMemory adressing/allocation/relocationComputer hardwareParallel computing
A processor-based compressed memory system includes a memory partitioning circuit for dividing a memory region into data regions with different priority levels. The system also includes a cache line selection circuit for selecting a first cache line from a high-priority data region and a second cache line from a low-priority data region. The system further includes a compression circuit for compressing the cache line to obtain a first compressed cache line and a second compressed cache line. The system also includes a cache line encapsulation circuit for encapsulating the compressed cache line such that the first compressed cache line is written to a first predetermined portion of the candidate compressed cache line, and the second cache line, or a portion of the second compressed cache line, is written to a second predetermined portion of the candidate compressed cache line. The first predetermined portion is larger than the second predetermined portion.
Owner:QUALCOMM INC
Method for testing high-low priority scheduling mechanism of A664 switch
According to the test method for the high-low priority scheduling mechanism of the A664 switch, a minimum test environment is established, an A664 tester with four physical ports is used, and verification cases of high-priority data frame priority forwarding, priority data integrity and the number of high-low priority buffer areas in a congestion scene are designed. The integrity and accuracy of high-low priority transmission function verification are ensured, and the problem of verification test of the high-low priority working mechanism of the A664 network in the prior art is effectively solved. The method is high in universality and can be suitable for various A664 network devices and application scenes.
Owner:XIAN AVIATION COMPUTING TECH RES INST OF AVIATION IND CORP OF CHINA
Distributed secure communication protocol data synchronization method and system
The invention discloses a distributed secure communication protocol data synchronization method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining the header information of an initial data packet; according to the header information, classifying the initial data packet to obtain a target data packet; resource isolation processing is carried out on the data processing environment, a high-priority processing environment and a low-priority processing environment are obtained, and the high-priority processing environment and the low-priority processing environment both have independent computing resources; and performing data synchronization processing on the target data packet according to the high-priority processing environment and the low-priority processing environment. According to the method and the device, the high-priority processing environment and the low-priority processing environment can be combined to respectively process the data packets with different priorities so as to realize data synchronous processing, and the efficiency and the data security are improved.
Owner:SHENZHEN HAOCHENGTONG TECHNOLOGY CO LTD
A data center resource regulation method, system, program product and storage medium
A data center resource regulation method, system, program product and storage medium. The method comprises: when a high-priority first application is found to have a resource bottleneck due to waiting for an input / output operation, locating a second application that is positively correlated with the first application IO load change trend and has a lower priority; generating a response feature containing expected information entropy, data structure and size according to the request content of the first application through a pre-trained business logic model; comparing the actual response feature of the second application with the expected feature to calculate a content correlation score; when the score is lower than a trust threshold, it is proved that the response content is irrelevant to the business logic, and the upper limit of the IO resource quota of the second application is reduced, and the quota is increased again after the waiting problem of the first application is alleviated. The technical scheme provided by the application improves the accuracy of resource regulation of the data center under complex application relationship.
Owner:SHANDONG ZHENGYUN INFORMATION TECH CO LTD
Increased file loads using file based optimization and prefetch within a memory system
Methods, systems, and devices for increased file loads using file based optimization (FBO) and prefetch within a memory system are described. A system may support using a prefetch command to prioritize prefetching for artificial intelligence (AI) related data (or other high priority data). A host system may transmit a prefetch command for the AI-related data before performing one or more AI operations that use the data. In response, the memory system may prefetch the AI-related data and store the data in a cache. The storage of the AI-related data in the cache may be prioritized over other data types associated with lower priorities. The host system may transmit an FBO command to defragment the AI-related data in the memory system prior to the prefetch, which may reduce latency of the prefetch.
Owner:MICRON TECHNOLOGY INC
Method and device for connecting computers
Owner:TRUMPF WERKZEUGMASCHINEN GMBH & CO KG
Digital human generation method and system based on mobile terminal CPU real-time driving
The invention discloses a digital human generation method and system based on mobile terminal CPU real-time driving, belongs to the technical field of digital human generation, and aims to solve the problems that when a mobile terminal operates a digital human and multiple application tasks at the same time, digital human interaction is prone to being blocked, resources are idle or overloaded, and low-priority tasks are available without cores, so that the system is frozen. The method comprises the following steps: collecting, screening and quantifying core characteristics of digital human interaction and application task operation, and calculating priorities of the two; accounting load intensity and judging load types, obtaining the total quantity of CPU performance cores and energy efficiency cores, and calculating the demand interval of the two operation cores; reserving a shared operation core pool, dynamically allocating operation cores according to load types and priorities, and triggering a time slice rotation guarantee mechanism when resources are insufficient; according to the method, digital human interaction priority guarantee is achieved, the CPU resource utilization rate is improved, system freezing is avoided, the terminal is smoothly degraded when resources are exhausted, and overall operation stability and user experience are guaranteed.
Owner:HANGZHOU LIANGMAO TECHNOLOGY CO LTD
Methods for data prioritization in memory
Methods, systems, and devices for methods for data prioritization in memory are described. A memory device may be configured to prioritize data such that high-priority data may remain in a cache to await operations while low-priority data may be transferred to higher-latency memory. For example, the memory device may receive a command to write data associated with one or more user operations to the memory system. The memory device may also receive an indication associated with the data that indicates to the memory device that the data is high priority. The memory device may store the data in a cache of the memory device to await operations. In response to a trigger, the memory device may transfer data not associated with the indication from the cache to multi-level memory cells (MLCs) of the memory device, such that the high-priority files may remain in the cache.
Owner:MICRON TECHNOLOGY INC
A dynamic and static combined parallel computing method and system and a storage medium
ActiveCN120123058BProgram initiation/switchingResource allocationConcurrent computationParallel computing
The application provides a kind of dynamic and static combined parallel computing method, system and storage medium, method includes: the computing task to be processed is decomposed into multiple subtasks and constructs directed acyclic graph, after multiple subtasks are assigned to multiple CPU cores, the encoding value of each subtask is calculated and random exchange is carried out, and then the obtained multiple initial task execution sequences are updated by genetic algorithm iteration to obtain the optimal task execution sequence, after the fitness of multiple initial task execution sequences is calculated, part is reserved and is crossed and mutated, according to the optimal task execution sequence, the subtask is added to the low priority task queue;Subtask is selected in high priority task queue first, and it is judged whether to execute subtask, when resource is enough to process, then according to the preset multi-thread programming interface, subtask is distributed to idle CPU core and parallel execution is carried out to the subtask with the same level value, when it is not enough to process, it is added to high priority queue, and the parallel computing result is obtained after all subtasks are executed completely.
Owner:BEIJING UNIV OF POSTS & TELECOMM