Exchange of Data Objects Between Task Routines Via Shared Memory Space

    公开(公告)号:US20210255843A1

    公开(公告)日:2021-08-19

    申请号:US17308355

    申请日:2021-05-05

    Abstract: An apparatus includes a processor to: based on data dependencies specified in a job flow definition, identify first and second tasks of the corresponding job flow to be performed sequentially, wherein the first task outputs a data object used as an input to the second; store, within a task queue, at least one message conveying at least an identifier of the first task, and an indication that the data object is to be exchanged through a shared memory space; within a task container, in response to storage of the at least one message within the task queue, sequentially execute first and second task routines to sequentially perform the first and second tasks, respectively, and instantiate the shared memory space to be accessible to the first and second task routines during their executions; and upon completion of the job flow, transmit an indication of completion to another device via a network.

    Automated Message-Based Job Flow Resource Management in Container-Supported Many Task Computing

    公开(公告)号:US20210200522A1

    公开(公告)日:2021-07-01

    申请号:US17139364

    申请日:2020-12-31

    Abstract: An apparatus includes at least one processor to retrieve a job flow definition defining a job flow as a set of tasks and dependencies thereamong, store a job performance request message to perform the job flow within a job queue, and in response to the storage of the job performance request message, execute instructions of a performance routine within a storage container to: based on the dependencies, derive an order of performance of the set of tasks that specifies a first task to perform; store, within a task queue, a first task routine execution request message requesting execution of a first task routine; and provide, to a resource allocation routine, an indication of a need for a first task container in which to execute the first task routine to perform the first task, wherein execution of the resource allocation routine causes dynamic allocation of containers based on availability of resources.

    COMMANDED MESSAGE-BASED JOB FLOW CANCELLATION IN CONTAINER-SUPPORTED MANY TASK COMPUTING

    公开(公告)号:US20210072963A1

    公开(公告)日:2021-03-11

    申请号:US17065843

    申请日:2020-10-08

    Abstract: An apparatus includes processor(s) to: receive, a request to cancel a performance of a job flow; store, within a task kill queue, a kill tasks request message; within a task container, in response to the storage of the kill tasks request message, cease execution of instructions of a task routine to cease performance of a task of a set of tasks of the job flow, and store, within a task queue, a task cancelation message indicating cancelation of execution of the task routine; within a performance container, execute instructions of a performance routine to cause the at least one processor to, in response to the storage of the task canceled message, store, within a job queue, a job cancelation message indicating cancelation of the job flow; and in response to the storage of the job cancelation message, transmit an indication of cancelation of the job flow to the requesting device.

    MANY TASK COMPUTING WITH MESSAGE PASSING INTERFACE

    公开(公告)号:US20200110589A1

    公开(公告)日:2020-04-09

    申请号:US16708179

    申请日:2019-12-09

    Abstract: An apparatus includes a processor to: receive a request to perform a set of tasks; analyze input data objects used as inputs and output data objects generated as outputs by the set of tasks to identify at least one dependency between tasks and at least one pair of tasks performable in parallel; determine an order of performance of the set of tasks; retrieve executable instructions of a corresponding set of task routines that define input interfaces and output interfaces for the input data objects and output data objects, respectively; generate a job flow definition defining the order of performance, each input interface and each output interface; use the job flow definition to perform the set of tasks; and transmit one of the output data objects to the requesting device as a result report serving as the output of the set of tasks.

    AUTOMATED EXCHANGES OF JOB FLOW OBJECTS BETWEEN FEDERATED AREA AND EXTERNAL STORAGE SPACE

    公开(公告)号:US20200097270A1

    公开(公告)日:2020-03-26

    申请号:US16699245

    申请日:2019-11-29

    Abstract: An apparatus includes a processor to: receive a job flow definition; retrieve the most recent versions of a set of task routines for the defined job flow; translate, into an intermediate representation, executable instructions of each task routine implementing an interface for data input and/or output during execution; translate executable instructions of the job flow definition that defines the interface for each task routine into an intermediate representation; compare each intermediate representation from a task routine to the corresponding intermediate representation from the job flow definition to determine if there is a match; and in response to there being a match for each comparison and to the executable instructions of the job flow definition being written in a secondary programming language, translate the executable instructions of the job flow definition into a primary programming language, and store the resulting translated form of the job flow definition in a federated area.

    MANY TASK COMPUTING WITH DISTRIBUTED FILE SYSTEM

    公开(公告)号:US20200026732A1

    公开(公告)日:2020-01-23

    申请号:US16587965

    申请日:2019-09-30

    Abstract: An apparatus includes a processor to: receive a request from a remote device to perform a job flow; retrieve a job flow definition defining the job flow and each of a set of task routines to perform tasks of the job flow from a set of storage devices where each is stored as an undivided object within one storage device; and in response to determining that a data set is stored as multiple data object blocks, generate a container containing the job flow definition and set of task routines to enable each storage device to perform the job flow using a locally stored data object block of the data set as input to generate a corresponding data object block of a result report, provide a copy of the container to each storage device, and transmit the result report assembled from the data object blocks thereof to the remote device.

    STAGED TRAINING OF NEURAL NETWORKS FOR IMPROVED TIME SERIES PREDICTION PERFORMANCE

    公开(公告)号:US20190384790A1

    公开(公告)日:2019-12-19

    申请号:US16556573

    申请日:2019-08-30

    Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.

    Generation of job flow objects in federated areas from data structure

    公开(公告)号:US10394890B2

    公开(公告)日:2019-08-27

    申请号:US16226828

    申请日:2018-12-20

    Abstract: An apparatus includes a processor to: receive a request to generate a DAG of a job flow of multiple tasks of an analysis based on data table(s) and formulae of a spreadsheet data structure; correlate each indication of data required as input or output to at least a subpart of a data table; identify data dependencies and determine an order of performance among the multiple tasks based on the formulae; generate, within the specified federated area, a job flow definition that specifies the order of performance of the multiple tasks; for each task of the multiple tasks, generate, within the specified federated area, a corresponding macro data structure of multiple macro data structures; and generate the requested visualization based on the job flow definition and the multiple macro data structures.

    Automated transfer of neural network definitions among federated areas

    公开(公告)号:US10360069B2

    公开(公告)日:2019-07-23

    申请号:US16039745

    申请日:2018-07-19

    Abstract: An apparatus includes a processor to: perform a testing job flow at least partly within a testing federated area to test a neural network defined by configuration data specifying hyperparameters and trained parameters thereof; and perform a transfer flow to transfer an object indicative of results of the testing from the testing federated area to another federated area, wherein: in response to the degree of accuracy falling below a predetermined minimum threshold, the processor is caused to transfer a specification of the degree of accuracy or a portion of inaccurate output to a training federated area in which the neural network was at least partly trained; and in response to the degree of accuracy exceeding a predetermined maximum threshold, the processor is caused to transfer a copy of the neural network configuration data to a usage federated area in which the neural network is to be made available for use.

Patent Agency Ranking