Abstract: A remote mapping method, apparatus and device for computing resources, and a storage medium, which are applied to a server. Said method comprises: identifying each FPGA heterogeneous accelerator card in an FPGA BOX; establishing a network communication connection with each FPGA heterogeneous accelerator card via a network interface of each FPGA heterogeneous accelerator card in the FPGA BOX, and establishing a network communication connection between FPGA heterogeneous accelerator cards; mapping each FPGA heterogeneous accelerator card to the server; establishing network transmission for the established network communication connections, and migrating a control flow and a data flow that are performed by the PCIE to the network transmission; and deploying a target application in the FPGA BOX through the established network transmission, and when running the target application, performing data exchange with the FPGA BOX via the network transmission.

Abstract: A task scheduling method includes: when a task requirement is obtained, splitting the task requirement to obtain the plurality of subtasks having a constraint relationship; performing execution condition detection on non-candidate subtasks, determining a non-candidate subtask that satisfies an execution condition as a candidate subtask, and putting the candidate subtask into a task queue; performing state detection on a server network composed of edge servers to obtain server state information and communication information; inputting the server state information, the communication information, and queue information corresponding to the task queue into an action value evaluation model to obtain the plurality of evaluated values respectively corresponding to the plurality of scheduling actions; and determining a target scheduling action from the plurality of scheduling actions by using the evaluated values, and scheduling the candidate subtask in the task queue on the basis of the target scheduling action.

Abstract: A task scheduling method includes: when a task requirement is obtained, splitting the task requirement to obtain the plurality of subtasks having a constraint relationship; performing execution condition detection on non-candidate subtasks, determining a non-candidate subtask that satisfies an execution condition as a candidate subtask, and putting the candidate subtask into a task queue; performing state detection on a server network composed of edge servers to obtain server state information and communication information; inputting the server state information, the communication information, and queue information corresponding to the task queue into an action value evaluation model to obtain the plurality of evaluated values respectively corresponding to the plurality of scheduling actions; and determining a target scheduling action from the plurality of scheduling actions by using the evaluated values, and scheduling the candidate subtask in the task queue on the basis of the target scheduling action.

Abstract: The optical device includes: a first coupler having an adjustable beam splitting ratio; a sensing arm and a programmable modulation arm which are connected to the first coupler; and a second coupler having an input port connected to the sensing arm and the programmable modulation arm and an output port connected to a photodetector. The sensing arm is used for generating, by means of a slot waveguide, a first signal from a first light wave beam outputted by the first coupler. The programmable modulation arm is used for obtaining, by utilizing a grating, a second signal according to a second light wave beam outputted by the first coupler, and the grating is a nano grating generated under a pre-programmed voltage parameter of a programmable piezoelectric transducer of the programmable modulation arm. An electronic device and a programmable photonic integrated circuit are also disclosed herein.

Abstract: A remote mapping method, apparatus and device for computing resources, and a storage medium, which are applied to a server. Said method comprises: identifying each FPGA heterogeneous accelerator card in an FPGA BOX; establishing a network communication connection with each FPGA heterogeneous accelerator card via a network interface of each FPGA heterogeneous accelerator card in the FPGA BOX, and establishing a network communication connection between FPGA heterogeneous accelerator cards; mapping each FPGA heterogeneous accelerator card to the server; establishing network transmission for the established network communication connections, and migrating a control flow and a data flow that are performed by the PCIE to the network transmission; and deploying a target application in the FPGA BOX through the established network transmission, and when running the target application, performing data exchange with the FPGA BOX via the network transmission.

Abstract: The present application discloses an automatic driving control method. In the method, parameters are optimally set by using a noisy and noiseless dual-strategy network, identical vehicle traffic environment state information is input into the noisy and noiseless dual-strategy network, a motion space perturbation threshold is set by using a noiseless strategy network as a comparison and a benchmark so as to adaptively adjust noise parameters, and motion noise is indirectly added by adaptively injecting noise into a strategy network parameter space, such that exploration of an environment and a motion space by a deep reinforcement learning algorithm may be effectively improved, automatic driving exploration performance and stability based on deep reinforcement learning is improved, and full consideration of influence of an environment state and driving strategies in vehicle decision-making and motion selection is ensured, thereby improving the stability and safety of an automatic vehicle.

Abstract: A three-dimensional reconstruction method, a system, and a non-transitory computer readable storage medium are disclosed herein. The method includes: performing local pose optimization by using a target image frame to obtain a local pose error; performing neural network prediction on the target image frame to obtain an initial reconstruction error; performing three-dimensional reconstruction according to the local pose error and the initial reconstruction error to obtain an initial reconstruction model; performing global pose optimization by using historical image frames to obtain a global optimization result and a global pose error; performing neural network completion on the global optimization result to obtain a final reconstruction error; and optimizing the initial reconstruction model according to the global pose error and the final reconstruction error to obtain a final reconstruction model.

Abstract: An image recognition method and apparatus based on a systolic array, and a medium are disclosed. The method includes: converting obtained image feature information into a one-dimensional feature vector; converting an obtained weight matrix into a one-dimensional weight vector, and allocating a corresponding weight group to each node in a trained three-dimensional systolic array model; performing multiply-accumulate of the feature vector and a weight value on the one-dimensional feature vector in parallel by using the three-dimensional systolic array model, to obtain a feature value corresponding to each node, the feature values with different values reflecting article categories contained in an image; and determining an article category contained in the image according to the feature value corresponding to each node and a pre-established corresponding relationship between the feature value and the article category.

Abstract: An automatic driving method includes following steps: S101: acquiring real-time traffic environment information in a travel process of an autonomous vehicle at a current moment; S102: mapping the real-time traffic environment information based on a preset mapping relationship to obtain mapped traffic environment information; S103: adjusting a target deep reinforcement learning model based on a pre-stored existing deep reinforcement learning model and the mapped traffic environment information; and S104: judging whether automatic driving is finished, and in response to the automatic driving is not finished, returning to perform the step of acquiring the real-time traffic environment information in the travel process of the autonomous vehicle at the current moment. An automatic driving system, an automatic driving device and a computer medium storing the automatic driving method are further provided.

Abstract: The present application discloses an automatic driving control method. In the method, parameters are optimally set by using a noisy and noiseless dual-strategy network, identical vehicle traffic environment state information is input into the noisy and noiseless dual-strategy network, a motion space perturbation threshold is set by using a noiseless strategy network as a comparison and a benchmark so as to adaptively adjust noise parameters, and motion noise is indirectly added by adaptively injecting noise into a strategy network parameter space, such that exploration of an environment and a motion space by a deep reinforcement learning algorithm may be effectively improved, automatic driving exploration performance and stability based on deep reinforcement learning is improved, and full consideration of influence of an environment state and driving strategies in vehicle decision-making and motion selection is ensured, thereby improving the stability and safety of an automatic vehicle.

Abstract: The present invention provides a method and apparatus for data caching. The method comprises: output matrixes are acquired one by one, a plurality of acquired output matrixes are written alternately into two queue sets of a first cache unit according to a sequence in which the output matrixes are acquired, and the output matrixes stored line by line in a first cache unit are written into a second cache unit one by one, according to the sequence in which the output matrixes are written into the second cache unit, valid data of each output matrix of the second cache unit is determined one by one according to preset parameters, and the valid data of each output matrix is written into a third cache unit, and the valid data of the output matrixes stored in the third cache unit are configured to be sequentially written into a memory according to a sequence in which the valid data are written into the third cache unit.

Abstract: An image recognition method and apparatus based on a systolic array, and a medium are disclosed. The method includes: converting obtained image feature information into a one-dimensional feature vector; converting an obtained weight matrix into a one-dimensional weight vector, and allocating a corresponding weight group to each node in a trained three-dimensional systolic array model; performing multiply-accumulate of the feature vector and a weight value on the one-dimensional feature vector in parallel by using the three-dimensional systolic array model, to obtain a feature value corresponding to each node, the feature values with different values reflecting article categories contained in an image; and determining an article category contained in the image according to the feature value corresponding to each node and a pre-established corresponding relationship between the feature value and the article category.

Abstract: A quantum data erasure method, system and device, and a readable storage medium. The method includes: acquiring an equal-probability quantum state system; measuring the equal-probability quantum state system to collapse the equal-probability quantum state system into a binary random number sequence; generating a corresponding random angle value according to the binary random number sequence; and performing a bitwise rotation operation on quantum data in a quantum device according to the random angle value to complete this quantum data erasure. In the present application, the introduction of a quantum true random number can ensure that erased data will not be recovered and reversely cracked, and is of great value in protecting data assets; moreover, randomly processed data still has the characteristics such as quantum coherence and quantum entanglement, and can be used in subsequent operations, whereby a time-consuming labor-intensive process of preparing a quantum system is not required every time.

Abstract: A system for accelerating an RNN network including: a first cache, which is used for outputting Wx1 to WxN or Wh1 to WhN in parallel in N paths in a cyclic switching manner, and the degree of parallelism is k; a second cache, which is used for outputting xt or ht-1 in the cyclic switching manner; a vector multiplication circuit, which is used for, by using N groups of multiplication arrays, respectively calculating Wx1xt to WxNxt, or respectively calculating Wh1ht-1 to WhNht-1; an addition circuit, which is used for calculating Wx1xt+Wh1ht-1+b1 to WxNxt+WhNht-1+bN; an activation circuit, which is used for performing an activation operation according to an output of the addition circuit; a state updating circuit, which is used for acquiring ct-1, calculating ct and ht, updating ct-1, and sending ht to the second cache; a bias data cache; a vector cache; and a cell state cache.

Abstract: A hybrid quantum-classical cloud platform and a task execution method. The cloud platform comprises: an SaaS layer for providing a user interface so as to acquire, by means of the user interface, a hybrid quantum-classical programming language corresponding to a task to be executed; a PaaS layer for performing algorithm compilation and task separation on the hybrid quantum-classical programming language to obtain a quantum computing task and a classical computing task corresponding to the task to be executed, and respectively allocating resources to the quantum computing task and the classical computing task; and an IaaS layer for executing the quantum computing task using a quantum virtual machine and executing the classical computing task using a classical server according to the resource allocation condition of the PaaS layer. Therefore, the communication overhead and the data delay can be reduced, the task processing efficiency is improved, and the quantum computing advantage is exerted.

Abstract: Provided are a turbulence field update method, apparatus, and device, and a computer-readable storage medium. The method includes: obtaining sample turbulence data; performing model training by use of the sample turbulence data to obtain a reinforcement learning turbulence model; calculating initial turbulence data of a turbulence field by use of a Reynolds Averaged Navior-Stokes (RANS) equation; processing the initial turbulence data by use of the reinforcement learning turbulence model to obtain a predicted Reynolds stress; and performing calculation on the predicted Reynolds stress by use of the RANS equation to obtain updated turbulence data.

Abstract: A video data processing method, including: obtaining three-dimensional feature data and three-dimensional weight data corresponding to video data; separately preprocessing the three-dimensional feature data and the three-dimensional weight data to obtain a feature value matrix and a weight value matrix; and inputting the feature value matrix and the weight value matrix into a plurality of three-dimensional systolic arrays for parallel computing to obtain a video data processing result. The present method can fully expand the degree of parallelism of computation and a four-dimensional systolic computation architecture is constructed by using multiple three-dimensional systolic arrays, so as to perform parallel computing on a three-dimensional feature value matrix and a three-dimensional weight value matrix, thereby shortening the computation time of three-dimensional convolution, and improving the video data processing efficiency.

Abstract: A distributed quantum computing simulation method and apparatus. The method includes: converting a quantum circuit to be simulated into a tensor network that is represented by an undirected graph, and segmenting the undirected graph into a plurality of sub-graphs by using a genetic algorithm that is based on operation resources of a distributed system; respectively performing, on sub-process nodes, tensor contraction and merging on the plurality of sub-graphs for connected tensors until only one tensor is left to finally obtain zero-order tensors of the plurality of sub-graphs at the same time; and acquiring and superposing the zero-order tensors of the plurality of sub-graphs from the sub-process nodes at the same time to determine a zero-order tensor of the undirected graph, and using the zero-order tensor of the undirected graph as a probability amplitude of a positive operator value measurement element, so as to perform quantum computing simulation.

Abstract: An image registration method and apparatus, an electronic apparatus, and a storage medium are provided. The image registration method comprises: extracting edge pixels of the binocular image, and determining high-confidence parallax points in the edge pixels and parallax; projecting each non-high-confidence parallax point to the triangular mesh in a direction parallel with a parallax dimension to obtain a triangular face; determining a parallax search range of parallax of each non-high-confidence parallax point, calculating a matching cost corresponding to all parallax in each parallax search range, and determining that parallax with the smallest matching cost is the parallax of the corresponding non-high-confidence parallax point; and determining a depth boundary point in the edge pixels, determining a parallax boundary point of each depth boundary point in a target direction, and setting parallax of pixels between the depth boundary point and the parallax boundary point to a target value.

Abstract: Provided are a method and apparatus for measuring the quantum decoherence degree, an electronic device and a computer-readable storage medium. The method includes: determining an initial quantum state and a point to be measured of a quantum system to be measured (S101); amplifying the amplitude of the quantum state of the point to be measured, and measuring a decoherence degree of the point to be measured (S102); and calculating a decoherence coefficient of the quantum system to be measured according to the decoherence degree (S103). According to the method for measuring the quantum decoherence degree, the amplitude of the quantum state of the point to be measured in the quantum system to be measured is amplified, and the probability of the point to be measured is obtained by means of measurement, so as to measure the decoherence degree of the point to be measured.