2140results about "Multiple digital computer combinations" patented technology

An example operation may include one or more of storing a database of payment card data, receiving an identifier of a product from a digital wallet on a user device, identifying one or more payment cards stored within the digital wallet on the user device, determining the benefits that will be obtained by using each of the one or more payment cards to purchase the product via execution of an LLM on the identifier of the product and the database of payment card data; and displaying a chat message within a chat window on the user device with a description of the determined benefits that will be obtained.

The invention discloses a method and a device for realizing task splitting based on a multi-core processor and a related product. A device may be included as a processing device in a combined processing device, which may further include an interface device and a computing device. The computing device interacts with the processing device to jointly complete computing operation specified by a user. The combined processing device can further comprise a storage device, and the storage device is connected with the computing device and the processing device and used for storing data of the computing device and the processing device. The scheme disclosed by the invention provides a method for scheduling group matrix multiplication class operation task splitting on the multi-core processor, which can effectively reduce data memory access and improve processing efficiency.

A system and method for implementing a non-interactive and automatic way of facilitating user authentication with a proxy server is disclosed. At least, the technique disclosed includes determining a request to access a web server by a Hypertext Transfer Protocol (HTTP) agent on a client device, retrieving a proxy configuration file from a Uniform Resource Locator (URL) assigned to the client device, determining, using the proxy configuration file, a host name and a port number of a proxy server corresponding to the request, and routing, from the HTTP agent to the proxy server, the request using the host name and the port number of the proxy server, the proxy server configured to look up a user mapping table using a set of proxy connection information and uniquely identify a user of the client device based on the look up, the set of proxy connection information including a combination of a public Internet Protocol (IP) address of the client device, the host name of the proxy server, and the port number of the proxy server.

The invention relates to the field of satellite navigation anti-interference and the technical field of computers, and discloses a multi-processor core communication method and device, electronic equipment and a storage medium, and the method comprises the steps that a second processor core writes target information into a shared memory, and obtains a first idle channel number; the second processor obtains a first interrupt signal based on an interrupt trigger register corresponding to the first idle channel number; the first processor core reads target information in a shared memory according to the first interrupt signal; the first processor core processes the target information to obtain a processing result, and writes the processing result into the shared memory to obtain a second idle channel number; the first processor core obtains a second interrupt signal based on an interrupt trigger register corresponding to the second idle channel number; and the second processor core reads the processing result in the shared memory according to the second interrupt signal, and writes the processing result into the cache region. The multi-processor core communication method is suitable for different operating systems and is high in transportability.

Described are methods and systems for workload identity and access management. The method comprises: receiving a request from a client workload to access a service workload; authenticating the client workload based at least in part on identifying information determined from a compute environment of the client workload; retrieving an access policy based at least in part on the client workload identity; generating or retrieving an access credential to access the service workload based at least in part on the access policy; and communicating data between the workload and the service based at least in part on the access credential.

The invention discloses a consistency interconnection processing device, a data transmission method, equipment and a heterogeneous system, and relates to the technical field of data transmission, the consistency interconnection processing device installed on the equipment is utilized, the consistency interconnection processing device comprises a consistency interconnection port and a consistency interconnection controller, the consistency interconnection controller controls the consistency interconnection interface to establish a consistency interconnection communication link between the devices and distribute a cache space from the devices where the consistency interconnection interface is located, so that consistency interconnection between the devices is achieved; the consistency interconnection controller monitors the cache line state of the device where the consistency interconnection controller is located and the cache line states of other devices and records the global cache line state table, when the consistency interconnection transaction request is executed, the global cache line state table is inquired according to the target data information and then the target access position is determined, actual memory access detection does not need to be carried out, and the memory access efficiency is improved. Therefore, the number of times of executing the consistency access is reduced, the consistency maintenance overhead of the consistency interconnection between the devices is reduced, and the memory access performance of the consistency interconnection between the devices is improved.

The embodiment of the invention provides a read-write request processing method, a protocol conversion module, electronic equipment and a storage medium, and relates to the technical field of chips. The method comprises the steps that a protocol conversion module is arranged in a processor cluster, an original read-write request is converted into a first read-write request conforming to a CHI protocol through a first conversion module in the protocol conversion module, and a corresponding transmission channel is distributed to the first read-write request; and the request queue module orderly sends the received first read-write request, and the second conversion module recombines the first read-write request information to a second read-write request conforming to the CHI protocol, and allocates a corresponding channel for the second read-write request. According to the embodiment of the invention, the internal data channel (AXI or similar AXI) is directly converted into the CHI interface in the processor cluster, the internal circuit resources of the processor cluster are reused, the circuit area is saved, and the access path time delay is reduced.

The invention discloses a method and device for executing an operation task on a multi-core system and a related product. The device may be included as a processing device in a combined processing device, which may further include an interface device and a computing device. The computing device interacts with the processing device to jointly complete computing operation specified by a user. The combined processing device can further comprise a storage device, and the storage device is connected with the computing device and the processing device and used for storing data of the computing device and the processing device. According to the scheme, the method for executing the operation task on the multi-core system is provided, data memory access can be effectively reduced, and the processing efficiency is improved.

The invention relates to a heterogeneous GPU cluster scheduling optimization method and system based on resource affinity, and belongs to the field of computer resource scheduling. Comprising the steps of 1, according to an affinity historical library of historical jobs, matching the historical jobs with relatively high similarity through job characteristics, and estimating resource requirements; 2, for a new job, receiving the job, performing probe testing on each type of GPU, and obtaining and recording job performance data; 3, establishing an affinity evaluation model for each job by using historical information or test data, evaluating affinity values of the jobs under different resource configurations, and providing data support for resource allocation decisions; and 4, entering a scheduling optimization period cycle, constructing an allocation matrix according to a target function of an optimization problem, and allocating corresponding resources to each job. According to the method, accurate resource matching and data support are achieved, the dynamic adaptive capacity is guaranteed, and the system expandability is enhanced.

Methods and systems enable internal and external verification of computations performed by a code signing server according to hash-based signature techniques using unique state, and further for a code signing server to expose parts of a hash-based signature log without negating the security of the one-time signature key pairs generated by the code signing server. A signing module of a code signing server receives a signing request from a client computing system. The signing module configures the code signing server to generate a one-time signature key pair based on a Merkle tree state. The signing module configures the code signing server to issue a hash-based signature to the client computing system. The code signing server is configured to record the Merkle tree state and the issued HBS in an immutably ordered log at a logging server.

Systems and methods for expanding chat communication groups based on a chat context are provided. In an example, a chat and video conference provider establishes a first chat communication group for exchanging chat messages between a plurality of client devices and generates a chat summary for a subset of the chat messages within the first chat communication group. The chat and video conference provider determines a relevant user of the first chat communication group based on the chat summary and provides a recommendation for inviting the relevant user a second chat communication group. The chat and video conference provider establishes the second chat communication group and presents the chat summary in the second chat communication group in response to the relevant user joining the second chat communication group.

The invention relates to the technical field of intelligent monitoring, in particular to a multi-thread low-power-consumption intelligent monitoring system based on an AI processor. The method has the advantages that aiming at the problems of unbalanced computing power and power consumption, high multi-task processing delay and strong hardware dependence in the prior art, the NPU module of the RK3588 processor is combined with the INT8 quantitative model, so that the power consumption is lower than 10W under the 6TOPS computing power; a dynamic multi-thread scheduling mechanism is designed, parallel processing of more than eight paths of video streams is supported through binding of a priority queue and an NPU core, and end-to-end delay is compressed to be within 200 ms; a zero-copy video stream architecture is constructed, data transfer is eliminated through memory mapping, and preprocessing time consumption is reduced by 90%; an energy efficiency control module is integrated, the NPU voltage frequency is dynamically adjusted according to the load, and the energy efficiency ratio reaches 0.83 TOPS / W; space-time alignment of multi-model reasoning results is realized by adopting a frame ID synchronization technology, and the mismatching rate is lower than 0.1%.

A hybrid quantum-classical (HQC) computer system, which includes a classical computer and a quantum computer, solves linear systems. The HQC computer system splits the linear system to be solved into subsystems that are small enough to be solved by the quantum computer, under control of the classical computer. The classical computer synthesizes the outputs of the quantum computer to generate the complete solution to the linear system.

A system and method in a building or vehicle for an actuator operation in response to a sensor according to a control logic, the system comprising a router or a gateway communicating with a device associated with the sensor and a device associated with the actuator over in-building or in-vehicle networks, and an external Internet-connected control server associated with the control logic implementing a PID closed linear control loop and communicating with the router over external network for controlling the in-building or in-vehicle phenomenon. The sensor may be a microphone or a camera, and the system may include voice or image processing as part of the control logic. A redundancy is used by using multiple sensors or actuators, or by using multiple data paths over the building or vehicle internal or external communication. The networks may be wired or wireless, and may be BAN, PAN, LAN, WAN, or home networks.

The invention discloses a shared cache system applied to a real-time network terminal chip. The shared cache system comprises queue management, enqueue scheduling control, dequeue scheduling control, write bus control, read bus control, a data cache, a register module, an RXFIFO module and a TXFIFO module. According to the cache allocation strategy, the variable-length data is stored by using the fixed-length unit. The user can customize and configure the private space, the residual space is the shared space, and the storage utilization rate is high. The shared cache is mainly used for storing data packets sent by an external application layer through a host interface. And storing the received data packet, extracting frame information according to a network flow protocol, and directly discarding frames which do not meet the protocol. The shared cache is provided with a dynamic cache structure, the state of each queue can be updated in real time, frame loss is prevented, and the data stream processing capacity is improved. And meanwhile, complex hybrid scheduling of a real-time network is met. The whole shared cache is subjected to anti-radiation reinforcement, the scene requirement of space navigation application is met, and high reliability is achieved.

Dynamic selection of topologies for database data may be performed for performing queries. Different possible query plans for different assignments of topologies are determined for a query. One of the query plans is selected according to a cost-based model that assigns costs to different uses of the different topologies. The query is then performed using the selected query plan.

An example apparatus includes a vehicle with a network management controller. The vehicle having a multi-zone network including a plurality of network zones including a zone manager and arranged according to a network topology description. The network management controller includes a zone implementation circuit structured to interpret a zoned architecture communication scheme; a zone manager command circuit structured to interpret a zone manager command description for each of the at least one zone managers; and a zone execution circuit structured to provide the corresponding zone manager command description to each of the at least one zone managers; and where each of the at least one zone managers is responsive to the corresponding zone manager command description to control communications between end points of the corresponding network zone and end points of at least one other zone of the plurality of network zones.

There is disclosed a method of providing passive phishing remediation for an enterprise, including: displaying, to a user of a mobile device, an email; receiving from the user a one-click request to perform additional analysis of the email; providing the email to a phishing mitigation service; assigning the email a reputation score, generating a human-readable reputation display for the email, wherein the human-readable reputation display includes at least three grades comprising safe, unknown or unreliable, and unsafe or malicious; and providing the human-readable reputation display as a push notification to the mobile device.

The present application belongs to the technical field of servers. Disclosed are a server installation structure and a server system. The server installation structure comprises a server, two opposite side surfaces of the server being respectively connected to sliding rails; each sliding rail extends in a direction from an opening to the interior of a containing chamber, a first locking module and a second locking module being spaced apart on the sliding rail in the direction from the opening to the interior of the containing chamber, and the first locking module and the second locking module being both switched between a locked state and an unlocked state; the first locking module comprises a first elastic piece, a locking member and a first spring, and the second locking module comprises a second elastic piece; the first elastic piece is partially fixed to the sliding rail, a first gap being provided between the first elastic piece and the sliding rail; the locking member is rotationally connected to the sliding rail, one end of the first spring is connected to the first elastic piece, and the other end of the first spring is connected to the locking member; the second elastic piece is partially fixed to the sliding rail, an included angle being formed between part of the second elastic piece and the sliding rail, and a blocking member being arranged on the second elastic piece.

Systems and methods for a virtual layer-2 network are described herein. The method can include providing a virtual Layer 3 network in a virtualized cloud environment. The virtual Layer 3 network can be hosted by an underlying physical network. The method can include providing a virtual Layer 2 network in the virtualized cloud environment. The virtual Layer 2 network can be hosted by the underlying physical network.

The invention relates to an intelligent integrated circuit, an intelligent chip and an AI chip in an artificial intelligence hardware platform. The invention relates to the fields of deep neural networks, multilayer neural networks, convolutional neural networks and the like in an artificial intelligence general technology, in particular to an operation node, a layer cluster and an accelerator of a large language model. The large language model operation node comprises at least one calculation unit and a first storage unit which are located in the same design architecture, and the calculation unit is used for calculation; the first storage unit is used for residing static weight data in the operation process of the large language model; and the second storage unit is arranged outside the design structure and is used for storing KV cache data in the operation process of the large language model. According to the method, the problems of high power consumption and high delay caused by traditional external storage static weight data reading are effectively avoided, and compared with a traditional HBM scheme, the method has obvious advantages in performance power consumption and cost.

The embodiment of the invention relates to a communication method and device, a chip system and electronic equipment, and relates to the technical field of electronics. The method executes a plurality of tasks based on a first chip, the first chip comprises a first scheduler, a first AI accelerator and a first memory reader, and the method comprises the following steps: the first scheduler outputs a first trigger signal to the first AI accelerator based on a first scheduling subtask; the first AI accelerator responds to the first trigger signal based on the first calculation sub-task, performs AI calculation to obtain first data, and outputs a first completion signal to the first scheduler to indicate that the first calculation sub-task is completed, and the first data is data required by the second chip for performing AI calculation; the first scheduler outputs a second trigger signal to the first memory reader according to the first completion signal based on the first scheduling sub-task; and the first memory reader transmits the first data to the second chip in response to the second trigger signal based on the first transmission subtask. Therefore, the problem of relatively high time overhead can be solved.

The invention provides a dynamic latch, comprising an input terminal for inputting a first data; an output terminal for outputting a second data; a clock signal terminal for supplying a clock signal; a data transmission unit for transmitting the first data under control of the clock signal; and a data output unit for converting the first data into the second data. The data transmission unit and the data output unit are sequentially connected in series between the input terminal and the output terminal, and a node is provided between the data transmission unit and the data output unit. The dynamic latch further comprises a data retention unit electrically connected to the node. The retention time of data can be effectively extended, thereby improving data security and accuracy.

Methods and apparatus operative to quantify building metrics using artificial assessment of an environmental impact, such as climate change and / or carbon control practices. A design plan is represented using multiple dynamic components. Each dynamic component may include a parameter changeable via the user interactive interface. The dynamic components may be arranged in a user interactive interface to form a first set of boundaries, including a respective length and area, and defining at least a portion of a first unit. AI may determine a materials list, methods of construction, distance form a supply source to a job site, supply chain variables, and other variables that are included in an environmental impact analysis. The AI may assess whether a building described in the design plans complies with a relevant environmental impact objective, such, for example, objectives relating to carbon footprint and / or climate change.

The invention discloses a GPU Box hardware decoupling system based on a Retimer card and a PCIe Switch chip, and belongs to the technical field of computer hardware architecture and high-speed interconnection. According to the system, a Retimer card and a PCIe Switch chip are integrated in an independent GPU Box, and a decoupling link of a CPU server and a GPU acceleration card is constructed; the Retimer card realizes 30-meter long-distance PCIe signal transmission and breaks through physical distance limitation; the PCIe Switch chip pools GPU resources through a dynamic routing and MRIOV technology, supports flexible allocation of computing power by multiple servers, and realizes Peer-to-Peer direct connection communication between GPUs. Aiming at a large model reasoning scene, the system optimizes KV cache bandwidth allocation and video memory and memory cooperative scheduling, so that the 100B parameter model reasoning throughput is greatly improved; and meanwhile, the usability of the system is greatly improved through fault isolation and hot plug design. According to the method, the problems of physical binding of the CPU and the GPU, limited transmission distance, rigid resource allocation and the like in a traditional architecture are solved, and the method is suitable for large-scale AI calculation and distributed GPU cluster deployment.

One embodiment provides a multi-chiplet graphics processor comprising a plurality of chiplets, where a chiplet of the plurality of chiplets comprise a memory interface, processing resources configured to execute threads of a kernel, and thread dispatch circuitry to facilitate dispatch of threads of the kernel to the processing resources. The processing resources are configured to execute threads of a first kernel, receive dispatch of threads of a second kernel for execution before completion of the first kernel as threads of the first kernel retire, execute a first phase of the second kernel during completion of execution of the first kernel, via a thread of the first kernel, signal an event via an uncached write to a global memory, and execute a second phase of the second kernel based on detection of the event via an uncached read from the global memory.

A multi-function device is disclosed. A first port may be used to communicate with a host processor. A second port may be used to communicate with a storage device. A third port may be used to communicate with a computational storage unit. Circuit may be used to route a message from the host processor to at least one of the storage device or the computational storage unit.

The present application discloses an operation and maintenance task processing method, a storage medium, and an electronic device. The method comprises: acquiring text information, wherein the text information is used for using a natural language to describe an operation and maintenance task to be executed; performing semantic analysis on the text information to determine an operation and maintenance operation instruction corresponding to the operation and maintenance task; and calling a target interface to send the operation and maintenance operation instruction to a target cloud service, and acquiring a target operation and maintenance result, wherein the target interface is a cloud service interface corresponding to the operation and maintenance task, and the target operation and maintenance result is an operation and maintenance result obtained after the target cloud service executes the operation and maintenance operation instruction. The present application solves the technical problems of high learning costs, high operation difficulty and low efficiency in a method for using an operation and maintenance template to define operation and maintenance operation steps.

The present application relates to the technical field of servers, discloses a multi-node server architecture, and aims to solve the problems of how to reduce the amount of data cabling used and perform independent maintenance of nodes. The multi-node server architecture comprises a server chassis, a central processing unit node which is pluggably mounted in the server chassis, a data switch node which is pluggably mounted in the server chassis, a graphics processing unit node which is pluggably mounted in the server chassis, and a middle backplane module which is mounted in the server chassis. A first connector, a second connector, and a third connector which are in signal interconnection are arranged on the middle backplane module. The central processing unit node is insertedly engaged with the first connector, the data switch node is insertedly engaged with the second connector, and the graphics processing unit node is insertedly engaged with the third connector. According to the present application, the amount of data cabling used can be reduced as much as possible, independent disassembly, assembly, and maintenance operations of each node can be quickly and conveniently carried out, and the heat dissipation performance is ensured while flexible configuration of each node is achieved.

The invention relates to the technical field of mobile terminal data processing, in particular to a CPU-GPU dual-core collaborative execution method and system for a mobile terminal deep learning reasoning task. The method comprises the following steps: in an offline stage, performing structural analysis on a target deep learning model, and predicting execution time and data transmission overhead of each operator in combination with hardware characteristics; in the online stage, the two key modules of the task scheduler and the heterogeneous execution engine ensure efficient CPU and GPU cooperative execution through the innovative dynamic scheduling and resource management technology. The reasoning tasks are dynamically distributed to the CPU and the GPU, flexible cooperative scheduling is achieved, the calculation advantages of all processors are fully played, the overall utilization rate is remarkably improved, and the idle or bottleneck of a single calculation resource is avoided. For resource-limited scenes such as a mobile terminal, the system optimizes the memory use efficiency, improves the task execution concurrency and stability and realizes efficient reasoning performance through a double-buffer structure and a data multiplexing and concurrent execution strategy.