4results about How to "High throughput" patented technology

This application provides a monolithic 3D integrated chip, relating to the field of semiconductor technology, primarily addressing the problem that current resistive random access memory (RRAM)-based logic architectures remain relatively fixed and lack flexible reconfigurability. The monolithic 3D integrated chip includes a logic layer, a memory computing layer, and a reconfigurable layer stacked sequentially, with interconnections between these layers. The logic layer transmits computation signals and data to the memory computing layer and configuration data and signals to the reconfigurable layer. The memory computing layer, under the control of the computation signals, performs matrix multiplication or addition on the computation data and outputs the computation results. The reconfigurable layer, under the control of the configuration signals, performs reconfigurable processing on the computation results according to the configuration data. This application endows the chip with flexible programmability and reconfigurability.

The invention discloses a data synchronization method based on dynamic adaptation of AST (Accelerated State Transfer) drive and Kubernetes. The method comprises the following steps: acquiring an application code of a to-be-synchronized service and performing grammar analysis to generate an abstract syntax tree AST; identifying a write operation point interacting with a target database based on AST, inserting batch processing logic into at least part of single write on the premise of not changing existing business semantics, realizing parameter aggregation and batch submission, and returning to single execution when constraint verification is not passed; a synchronization task is operated in a Kubernetes environment, an elastic scaling event is monitored, and access parameters such as a database connection pool and the like are dynamically calculated and subjected to hot update under the non-stop condition according to the number change of instances; and executing writing after rewriting and outputting a structured synchronization result. Through the method, the synchronization throughput is improved, and the stability in a scaling scene is enhanced.

This invention discloses a piecewise adaptive Kalman track tracking method and apparatus based on residual classification, relating to the field of radar track tracking technology. Addressing the problems of poor adaptability to non-stationary measurement noise environments, parameter dependence on human experience, and complex FPGA implementation in existing track tracking methods, this invention proposes introducing a residual classification decision and piecewise adaptive noise adjustment mechanism into the Kalman filter recursive framework. First, a residual vector is calculated based on the predicted state and measurement data. Then, a classification decision is made using the residual vector, the predicted covariance, and the measurement noise covariance of the previous cycle, outputting the measurement quality level. Next, the measurement noise covariance is updated piecewise adaptively based on the measurement quality level. Finally, the filter gain is calculated based on the updated measurement noise covariance and the predicted covariance to complete the correction and update of the state and covariance.

The invention relates to the technical field of station reactive power response, in particular to an Internet of Things edge device scheduling system and method based on AI reasoning hardware resources, and the system comprises an edge system module, a cloud storage module, an ML model data module and a reasoning data module. A computer cluster, an artificial intelligence reasoning service unit and a local storage unit are integrated in the edge system module; the edge system module, the cloud storage module, the ML model data module and the reasoning data module communicate with one another through the network service unit; wherein the edge system module is used for receiving Internet of Things equipment data at an edge side and executing an AI reasoning task, and providing a reasoning result for an upstream application with relatively low delay; and the cloud storage module is used for storing model backup, historical reasoning data and logs and providing cloud reasoning rollback capability. According to the invention, through intelligent sensing and scheduling of heterogeneous edge hardware, efficient deployment of the ML model in the resource-constrained IoT environment is realized.