544 results about "Symmetric multiprocessor system" patented technology

System and method for submitting and performing computational tasks in a distributed heterogeneous networked environment. Embodiments may allow tasks to be submitted and run in parallel on a network of heterogeneous computers implementing a variety of operating environments. In one embodiment, a user on an originating node may advertise code on the network. Peer nodes that respond to the advertisement may receive the code. A job to be executed by the code may be split into separate tasks to distributed to the peer nodes that received the code. These tasks may be advertised on the network. Tasks may be assigned to peer nodes that respond to the task advertisements. The peer nodes may then work on the assigned tasks. Once a peer node's work on a task is completed, the peer node may return the results of the task to the originating node.

A system for generating software applications for a plurality of heterogeneous computing devices. Each computing device has different capabilities. The system outputs device-specific versions of a software application each tailored to the capabilities of the associated computing device in response to receiving device-independent modeling information characterizing the software application. The system includes a framework, a plurality of object types, a modeling tool, and a plurality of device-specific code generators. The framework defines common services on the computing devices. Each object type has a functional relationship to the common services provided by the framework. The modeling tool defines instances of the plurality of object types based on modeling information received as input, outputting a metadata structure describing the behavior and functionality of a software application. From the metadata, the code generators generate device-specific application code tailored to the capabilities of the associated devices.

A data transformation system includes clients, which initiate requests for transformation of data between first and second data formats. The system also includes peer transformation servers having data converters and graphs of available transformations between input and output data formats of such servers. The graph includes unidirectional edges, which extend between corresponding pairs of the formats. The servers collectively include one or more converters for each of the edges. The servers receive the requests and select plural intermediate transformations from the first format to plural intermediate formats, and a final transformation from an intermediate format to the second format. Each of the intermediate and final transformations is associated with a corresponding one of the edges. The servers initiate the converters corresponding to the selected transformations, in order to obtain and dispose the data in the second format. A communication network provides communication among the client and servers.

A method and apparatus is provided for breaking down computing tasks within a larger application and distributing such tasks across a network of heterogeneous computers for simultaneous execution. The heterogeneous computers may be connected across a wide or local area network. The invention supports mobile agents that are self-migrating and can transport state information and stack trace information as they move from one host to another, continuing execution where the mobile agents may have left off. The invention includes a server component for providing an execution environment for the agents, in addition to sub-components which handle real-time collaboration between the mobile agents as well as facilities monitoring during execution. Additional components provide realistic thread migration for the mobile agents. Real-time stack trace information is stored as the computing tasks are executed, and if over-utilization of the computing host occurs, execution of the computing task can be halted and the computing task can be transferred to another computing hosts where execution can be seamlessly resumed using the stored, real-time state information and stack trace information.

Systems and methods of the present disclosure are directed to providing centralized diagnostic services to a plurality of heterogeneous computing environments deployed at different data centers on different networks. In some embodiments, a centralized diagnostic tool establishes a connection to a server of a data center that deploys a computing environment with components. The centralized diagnostic tool validates automatically a component of the computing environment based on a corresponding configuration file received from the server for the component. The centralized diagnostic tool establishes a virtual device simulating a client application executing on a client device. The client application can be configured to communicate with the component. The centralized diagnostic tool automatically initiates a request using a predetermined protocol flow, and the virtual device transmits the request to the component. The virtual device receives a response to the request indicative of a status of the computing environment.

A method and system for managing a large number of servers and their server components distributed throughout a heterogeneous computing environment is provided. In one embodiment, an authenticated user, such as a IT system administrator, can securely and simultaneously control and configure multiple servers, supporting different operating systems, through a "virtual server." A virtual server is an abstract model representing a collection of actual target servers. To represent multiple physical servers as one virtual server, abstract system calls that extend execution of operating-system-specific system calls to multiple servers, regardless of their supported operating systems, are used. A virtual server is implemented by a virtual server client and a collection of virtual server agents associated with a collection of actual servers.

A computing method and system is presented that allows multiple heterogeneous computing systems containing file storage mechanisms to work together in a peer-to-peer fashion to provide a fault-tolerant decentralized highly available clustered file system. The file system can be used by multiple heterogeneous systems to store and retrieve files. The system automatically ensures fault tolerance by storing files in multiple locations and requires hardly any configuration for a computing device to join the clustered file system. Most importantly, there is no central authority regarding meta-data storage, ensuring no single point of failure.

System and method for submitting and performing computational tasks in a distributed heterogeneous networked environment. Embodiments may allow tasks to be submitted and run in parallel on a network of heterogeneous computers implementing a variety of operating environments. In one embodiment, a user on an originating node may advertise code on the network. Peer nodes that respond to the advertisement may receive the code. A job to be executed by the code may be split into separate tasks to distributed to the peer nodes that received the code. These tasks may be advertised on the network. Tasks may be assigned to peer nodes that respond to the task advertisements. The peer nodes may then work on the assigned tasks. Once a peer node's work on a task is completed, the peer node may return the results of the task to the originating node.

An architecture and system are described that provide a unified file access service within in a managed computing environment composed of diverse networks, computing devices, and storage devices. The service provides mechanisms for remotely accessing the file systems of any managed computer or disk snapshot, independently of the computer's current state (powered on, suspended or powered off), its location within the environment, its hardware type (virtual vs. physical), its operating system type, and its file system formats. The system isolates centralized FPAs from the details of clients, proxies and storage elements by providing a service that decomposes offloaded file system access into two steps. A FPA or a requester acting on behalf of the FPA first expresses the disk set or the computer containing the file systems it wishes to access, along with requirements and preferences about the access method. The service figures out an efficient data path satisfying the FPA's needs; and then automatically configures a set of storage and computing resources to provide the data path. The service then replies with information about the resources and instructions for using them. The FPA then accesses the requested file systems using the returned information.

A distributed system structure for a large-way, symmetric multiprocessor system using a bus-based cache-coherence protocol is provided. The distributed system structure contains an address switch, multiple memory subsystems, and multiple master devices, either processors, I / O agents, or coherent memory adapters, organized into a set of nodes supported by a node controller. The node controller receives transactions from a master device, communicates with a master device as another master device or as a slave device, and queues transactions received from a master device. Since the achievement of coherency is distributed in time and space, the node controller helps to maintain cache coherency. The node controller also implements an interrupt arbitration scheme designed to choose among multiple eligible interrupt distribution units without using dedicated sideband signals on the bus.

An architecture and system are described that provide a unified file access service within in a managed computing environment composed of diverse networks, computing devices, and storage devices. The service provides mechanisms for remotely accessing the file systems of any managed computer or disk snapshot, independently of the computer's current state (powered on, suspended or powered off), its location within the environment, its hardware type (virtual vs. physical), its operating system type, and its file system formats. The system isolates centralized FPAs from the details of clients, proxies and storage elements by providing a service that decomposes offloaded file system access into two steps. A FPA or a requester acting on behalf of the FPA first expresses the disk set or the computer containing the file systems it wishes to access, along with requirements and preferences about the access method. The service figures out an efficient data path satisfying the FPA's needs, and then automatically configures a set of storage and computing resources to provide the data path. The service then replies with information about the resources and instructions for using them. The FPA then accesses the requested file systems using the returned information.

A storage media management system operating in a heterogeneous computing environment having different servers, different operating systems, and different backup applications. The management system extracts backup information from each backup application and consolidates the information in a tracking database. A centralized interface to the tracking database permits centralized management of backup storage media, such as movement, retention, vaulting, reporting, utilization, and duplication.

A method, apparatus, and computer usable program code for logical partitioning and virtualization in heterogeneous computer architecture. In one illustrative embodiment, a portion of a first set of processors of a first type is allocated to a partition in a heterogeneous logically partitioned system and a portion of a second set of processors of a second type is allocated to the partition.

A method, computer program storage medium and system that implement evolutionary algorithms on heterogeneous computers; in which a central process resident in a central computer delegates subpopulations of individuals of similar fitness from a central pool to separate processes resident on peripheral computers where they evolve for a certain number of generations after which they return to the central pool before the delegation is repeated.

A system and method embodiments for optimally allocating compute kernels to different types of processors, such as CPUs and GPUs, in a heterogeneous computer system are disclosed. These include comparing a kernel profile of a compute kernel to respective processor profiles of a plurality of processors in a heterogeneous computer system, selecting at least one processor from the plurality of processors based upon the comparing, and scheduling the compute kernel for execution in the selected at least one processor.

Communication and Process Migration Protocols instituted in an independent layer of a virtual machine environment allow for heterogeneous or homogeneous process migration. The protocols manage message traffic for processes communicating in the virtual machine environment. The protocols manage message traffic for migrating processes so that no message traffic is lost during migration, and proper message order is maintained for the migrating process. In addition to correctness of migration operations, low overhead and high efficiency is achieved for supporting scalable, point-to-point communications.

A technique for compiling and running high-level program on heterogeneous computers may include partitioning a program code into two or more logical units, and compiling each of the logical units into one or more executable entities. At least some of the logical units are compiled into two or more executable entities, the two or more executable entities being different compilations of the same logical unit. The two or more executable entities are compatible to run on respective two or more platforms that have different architecture.

Various embodiments of methods and systems for controlling and / or managing thermal energy generation on a portable computing device that contains a heterogeneous multi-core processor are disclosed. Because individual cores in a heterogeneous processor may exhibit different processing efficiencies at a given temperature, thermal mitigation techniques that compare performance curves of the individual cores at their measured operating temperatures can be leveraged to manage thermal energy generation in the PCD by allocating and / or reallocating workloads among the individual cores based on the performance curve comparison.

A distributed system structure for a large-way, symmetric multiprocessor system using a bus-based cache-coherence protocol is provided. The distributed system structure contains an address switch, multiple memory subsystems, and multiple master devices, either processors, I / O agents, or coherent memory adapters, organized into a set of nodes supported by a node controller. The node controller receives transactions from a master device, communicates with a master device as another master device or as a slave device, and queues transactions received from a master device. Since the achievement of coherency is distributed in time and space, the node controller helps to maintain cache coherency. In order to reduce the delays in giving address bus grants, a bus arbiter for a bus connected to a processor and a particular port of the node controller parks the address bus towards the processor. A history of address bus grants is kept to determine whether any of the previous address bus grants could be used to satisfy an address bus request associated with a data bus request. If one of them qualifies, the data bus grant is given immediately, speeding up the data bus grant process by anywhere from one to many cycles depending on the requests for the address bus from the higher priority node controller.

In a symmetric multiprocessing system using processors (DP0–DP7) of different capabilities (instruction sets), a processor responds (S11) to a query regarding its capabilities (instruction set) with its “active” capability, which is the intersection of its native capability and a common capability across processors determined (S04) during a boot sequence (13). The querying application (29) can select (S12) a program variant optimized for the active capability of the selected processor. If the application is subsequently subjected to a blind transfer to another processor, it is more likely than it would otherwise be (if the processors responded with their native capabilities) that the previously selected program variant runs without encountering unimplemented instructions.

The invention provides a heterogeneous computing system based on CPU+GPU+FPGA architecture. The system comprises a CPU host unit, one or more GPU heterogeneous acceleration units and one or more FPGA heterogeneous acceleration units. The CPU host unit is in communication connection with the GPU heterogeneous acceleration units and the FPGA heterogeneous acceleration units. The CPU host unit is used for managing resources and allocating processing tasks to the GPU heterogeneous acceleration units and / or the FPGA heterogeneous acceleration units. The GPU heterogeneous acceleration units are used for carrying out parallel processing on tasks from the CPU host unit. The FPGA heterogeneous acceleration units are used for carrying out serial or parallel processing on the tasks from the CPU host unit. According to the heterogeneous computing system provided by the invention, the control advantages of the CPU, the parallel processing advantages of the GPU, the performance and power consumption ratio and flexible configuration advantages of the FPGA can be exerted fully, the heterogeneous computing system can adapt to different application scenes and can satisfy different kinds of task demands. The invention also provides a heterogeneous computing method based on the CPU+GPU+FPGA architecture.

A method is provided for query processing in a grid computing infrastructure. The method entails storing data in a data storage system accessible to a plurality of computing nodes. Computationally-expensive query operations are identified and query fragments are allocated to individual nodes according to computing capability. The query fragments are independently executed on individual nodes. The query fragment results are combined into a final query result.

A single chip, embedded symmetric multiprocessor (ESMP) having parallel multiprocessing architecture composed of identical processors includes a single program memory. Program access arbitration logic supplies an instruction to a single requesting central processing unit at a time. Shared memory access arbitration logic can supply data from separate simultaneously accessible memory banks or arbitrate among central processing units for access. The system may simulate an atomic read / modify / write instruction by prohibiting access to the one address by another central processing unit for a predetermined number of memory cycles following a read access to one of a predetermined set of addresses in said shared memory.

In one implementation, an apparatus includes a detector of capabilities of each of heterogeneous computing systems, the capabilities including a model, existence of a microphone, video controls, specifications of a camera, a processor speed, a bus speed, an amount of cache memory, an amount of non-cache memory, a telecom carrier and an operating system, a determiner of the minimum sufficiency of the capabilities of the each of the heterogeneous computing systems; the determiner being operably coupled to the detector, the determiner being operable to set a state in a memory location indicating an affirmative or a negative state of the minimum sufficiency of the capabilities of the each of the heterogeneous computing systems, and an initiator of a multimedia teleconference between the heterogeneous computing systems, the initiator being operably coupled to the determiner, the initiator being operable to initiate the multimedia teleconference in reference to the memory location indicating an affirmative or a negative state of the minimum sufficiency of the capabilities of the each of the heterogeneous computing systems.

A test signal multiplexer receives supplies external test signals to a selected debug master central processing unit in a symmetrical multiprocessor system and debug slave signals to debug slave central processing units. An executive master test access port controller responds to the external test signals and controls the test signal multiplexer. A control register loadable via the executive master test access port stores the debug slave signals. A test data output multiplexer connects the test data output line of the selected debug master central processor unit to an external test data output line. The external test signals includes a debug state signal supplied to each central processing unit. This selects either a normal mode or a debug mode at each central processor unit.

A shared memory system for symmetric multiprocessing systems including a plurality of physical memory locations in which the locations are either allocated to one node of a plurality of processing nodes, equally distributed among the processing nodes, or unequally distributed among the processing nodes. The memory locations are configured to be accessed by the plurality of processing nodes by mapping all memory locations into a plurality of address partitions within a hierarchy bus. The memory locations are addressed by a plurality of address aliases within the bus while the properties of the address partitions are employed to control transaction access generated in the processing nodes to memory locations allocated locally and globally within the processing nodes.

The invention relates to the technical field of storage, in particular to an NVMe (Non-Volatile Memory Express) data read-write method and NVMe equipment. The method comprises the following steps that: a transceiver receives an NVMe command which is written into an SQ (Submission Queue) by a host; when the SQ control module detects that the SQ changes in an SQ cache, the NVMe command in the SQ issent to an SSD (Solid State Drives) controller; the SSD controller executes the NVMe command and writes the generated NVMe command response into a CQ (Completion Queue) through a CQ control module; and the SSD controller notifies the host to read the CQ through trigger interruption to enable the host to process the NVMe command response in the CQ. Since the SQ and the CQ are both positioned in theNVMe equipment, the CPU (Central Processing Unit) can directly read the NVMe response command in the CQ or directly writes the NVMe command into the SQ so as to further lower the consumption of CPU resources. In addition, a way designed by the NVMe equipment can support CCIX (Cache Coherent Interconncet for Acceleration) on hardware, and therefore, the heterogeneous calculation of software memoryunification and an I / O operation can be realized.

An apparatus and method for provisioning software on a network of heterogeneous computers in a network. The provisioner receives a list of packages and deployment scope of the packages, then checks each node for installed applications and records dependency and potential application conflicts. In addition, the provisioner measures a plurality of network and node metrics. Based on the dependency information, conflict information, and metrics, one or more nodes are selected and software is provisioned and / or removed in accordance with the dependency and conflict information.

A normalization engine, system and method provide normalization of and access to data between heterogeneous data sources and heterogeneous computing devices. The engine includes connectors for heterogeneous data sources, and conduits for gathering a customized subset of data from the data sources, as required by a software application with which the conduit is compatible. Working together, the connector and conduit may gather large amounts of data from multiple data sources and prepare a subset of the data that includes only that data required by the application, which is particularly advantageous for mobile computing devices. Further, the conduit may process the subset data in various formats to provide normalized data in a single format, such as a JSON-formatted REST web service communication compatible with heterogeneous devices. As an intermediary, the normalization engine may further provide caching, authentication, discovery and targeted advertising to mobile computing and other computing devices.