Abstract: The subject technology performs a locking operation on a first set of keys by a first statement of a first transaction. The subject technology determines that a conflict occurred between the first statement and a second transaction. The subject technology determines that the second transaction has yet to complete after a predetermined period of time. The subject technology performs a deadlock detection process where the subject technology stores a key and value in a table indicating the first transaction and the second transaction, detects, based at least in part on a graph traversal of the table starting from the first transaction, a cycle between the first transaction and the second transaction, and determines that the first transaction is a youngest transaction in the detected cycle. The subject technology ceases execution of the first transaction in response to the first transaction being a youngest transaction in a detected cycle.

Abstract: A management system includes a storage unit that stores schedule information that indicates schedules of a plurality of tasks to be performed by the same flight vehicle. The schedule information includes types of the plurality of tasks, date/times of the plurality of tasks, and locations at which the plurality of tasks are to be performed. When the types, the date/times, and the locations that are included in the schedule information stored in the storage unit satisfy an integration condition, an integration unit integrates the schedules of the plurality of tasks. An output unit outputs integrated schedule information indicating the schedules of the integrated tasks.

Abstract: Techniques for solving asset synthesis by integrating asset synthesis instances into a historical, virtual, or predicted workflow within an organization. The integration facilitates improving a parameter of the synthesis, such as cost or time. The result is a system that improves productivity in an organization and improves accuracy of workflow completion prediction within the organization.

Abstract: A network device includes computing resources for utilization by processes hosted by the network device and a computing resources manager. The computing resources manager automatically instantiate a new instance of a first process of the processes upon termination of the first process; makes a determination that the network device has entered an out of computing resources state; and in response to the determination: performs an action set to increase a quantity of the computing resources that are available for allocation to the processes.

Abstract: A method and system for testing of a communication network utilizing a plurality of test agents in the communication network using a deterministic decentralized scheduling of the plurality of test agents to test a single network service. Determining an optimal time period for executing a test of the single network service by each of the plurality of test agents without requiring global knowledge of the system and without requiring centralized coordination of individual agent test schedules.

Abstract: One embodiment provides for a general-purpose graphics processing unit comprising a processing array including multiple compute blocks, each compute block including multiple processing clusters and a thread dispatch unit to dispatch threads of a workload to the multiple compute blocks based on a parallelism metric, wherein the thread dispatch unit, based on the parallelism metric, is to perform one of a first operation and a second operation, the first operation to distribute threads across the multiple compute blocks and the second operation is to concentrate threads within one of the multiple compute blocks.

Abstract: A method for providing virtual desktop services includes receiving a request for a session from a user; instantiating a virtual machine for the session; copying user data for the user from a data backup to a user volume attached to the virtual machine; and creating a delta disk associated with the user volume, wherein the delta disk records changes to the user data during the session. A system for providing virtual desktop services, includes a shared storage device having user data stored thereon; a host server configured to run one or more virtual machines, the host server having a local storage device; virtual machine having a user volume with a copy of the user data and a delta disk having changed user data.

Abstract: Two sets X2 and X1 of histograms of words, and a vocabulary V are accessed. Each of the two sets is representable as a sparse matrix, each row of which corresponds to a histogram. Each histogram is representable as a sparse vector, whose dimension is determined by a dimension of the vocabulary. Two phases compute distances between pairs of histograms. The first phase includes computations performed for each histogram and for each word in the vocabulary to obtain a dense, floating-point vector y. The second phase includes computing, for each histogram, a sparse-matrix, dense-vector multiplication between a matrix-representation of the set X1 of histograms and the vector y. The multiplication is performed to obtain distances between all histograms of the set X1 and each histogram X2[j]. Distances between all pairs of histograms are obtained, based on which distances between documents can subsequently be assessed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shaping compute load using virtual capacity. In one aspect, a method includes obtaining a load forecast that indicates forecasted future compute load for a cell, obtaining a power model that models a relationship between power usage and computational usage for the cell, obtaining a carbon intensity forecast that indicates a forecast of carbon intensity for a geographic area where the cell is located, determining a virtual capacity for the cell based on the load forecast, the power model, and the carbon intensity forecast, and providing the virtual capacity for the cell to the cell.

Abstract: Systems and methods are provided for dynamically reallocating resources during run-time execution of workloads in a distributed accelerator-as-a-service computing system to increase workload execution performance and resource utilization. A workload is executed in the distributed accelerator-as-a-service computing system using an initial set of resources allocated to the executing workload, wherein the allocated resources include accelerator resources (e.g., physical and/or virtual accelerator resources). The performance of the executing workload is monitored to detect a bottleneck condition which causes a decrease in the performance of the executing workload. In response to detecting the bottleneck condition, another set of resources is reallocated to the executing workload, which is determined to reduce or eliminate the bottleneck condition.

Abstract: Systems and methods for purposeful computing are disclosed that, among other things, include enabling an operating system for connected computing configured for identification, evaluation, selection, and/or use of suitable to user purposes' resources to produce outcomes optimized to such purposes' fulfillment. Such resources populate a distributed resource ecosphere and have associated attributes that inform regarding resource suitability.

Abstract: Systems, apparatuses, methods, and computer programs for overprovisioning resources are disclosed. Resource usage statistics may be gathered for a plurality of client virtual machines (“VMs”). Statistical characteristics of resource usage by the plurality of client VMs may be calculated. It may also be determined which of the plurality of client VMs requesting resources to allocate resources to, as well as an amount of the resources to allocate, in a given time slot based on the calculated statistical characteristics.

Abstract: Example resource management systems and methods are described. In one implementation, a resource manager is configured to manage data processing tasks associated with multiple data elements. An execution platform is coupled to the resource manager and includes multiple execution nodes configured to store data retrieved from multiple remote storage devices. Each execution node includes a cache and a processor, where the cache and processor are independent of the remote storage devices. A metadata manager is configured to access metadata associated with at least a portion of the multiple data elements.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for assigning a computing task. The method includes: segmenting, based on a computing resource required for a computing task of a graph, the graph into a subgraph set; determining, based on a computing resource required for a computing task of a subgraph in the subgraph set, whether a node in a node cluster is adapted to the subgraph in the subgraph set; assigning, in response to determining the node in the node cluster being adapted to the subgraph in the subgraph set, the computing task of the subgraph in the subgraph set to the node adapted to the subgraph in the subgraph set, to compute the subgraph; and synthesizing a computing result of the graph based on a computing result of each subgraph in the subgraph set.

Abstract: Systems and methods for minimally intrusive instruction pointer-aware processing resource activity profiling are disclosed. In one embodiment, a graphics processor includes a grouping of processing resources and control logic that is associated with the grouping of processing resources. The control logic is configured to sample a state of at least one processing resource of the grouping of processing resources and to determine activity data from the state with the activity data including at least one of stalls and reason counts for stalling activity, instruction types, pipeline utilization, thread utilization, and shader activity.

Abstract: A computational resource management apparatus is for managing a cluster system that executes a plurality of tasks. The computational resource management apparatus includes a condition specification unit that specifies a relationship between computational resources of the cluster system and computation time, a dependency relationship between tasks, and an execution time limit of each task, and a scheduling unit that determines, for each task, an execution sequence and computational resources to be allocated from among the computational resources of the cluster system, based on the relationship between the computational resources and computation time and the dependency relationship that are specified, such that the execution time limit is met.

Abstract: A data processing system includes one or more computer systems, each executing at least one hypervisor. Host bus adapters on the computer system are connectable to storage resources in at least one storage area network. The at least one hypervisor provides virtual instances of the host bus adapters as virtual host bus adapters, and a world-wide unique port number and a logical unit number are used to access a storage volume. A globally unique identifier is used to identify the storage volume. The system includes a management server comprising a management instance for evaluating a possibility of attaching storage resources to virtual machine instances generated by the hypervisor.

Abstract: Computational methods and systems that estimate time remaining and right size for usable capacities of resources used to run virtual objects of a distributed computing system are described. For each stream of metric data that represents usage of a resource of a distributed computing system, a model for forecasting metric data is determined and used to compute forecasted metric data in a forecast interval. A resource utilization metric is computed from the forecasted metric data and may be used to estimate a time remaining before the usable capacity of the resource is expected to be insufficient and the resource usable capacity is adjusted. The resource utilization metric may be used to determine the capacity remaining is insufficient. A right-size usable capacity for the resource is computed based on the resource utilization metric and the usable capacity of the resource is adjusted to at least the right-size usable capacity.

Abstract: A technique deploys a virtualization layer underneath an operating system executing on a node of a network environment to enable the virtualization layer to control the operating system is described. One or more executables (binaries) for the virtualization layer may be included in a kernel module loaded in memory of the node with a first privilege level (e.g., highest privilege level) needed to control the guest operating system. The kernel module may be configured to suspend the guest operating system and one or more hardware resources to a quiescent state. Furthermore, the kernel module is configured to (i) capture and save states of the hardware resource(s) and (ii) bootstrap the virtualization layer to create a virtual machine with an initial state that corresponds to a state of the system prior to deployment of the virtualization layer.

Abstract: Techniques for estimating runtimes of one or more machine learning tasks are provided. For example, one or more embodiments described herein can regard a system that can comprise a memory that stores computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an extraction component that can extract a parameter from a machine learning task. The parameter can define a performance characteristic of the machine learning task. Also, the computer executable components can comprise a model component that can generate a model based on the parameter. Further, the computer executable components can comprise an estimation component that can generate an estimated runtime of the machine learning task based on the model.

Abstract: A controller for controlling a memory device includes: a buffer including a plurality of segments; and a buffer manager suitable for deciding a segment attribute for each of the segments that represents one or more kinds of buffer allocation request for which the corresponding segment is allocable, deciding a priority allocation for each of the segments based on the segment attribute of the corresponding segment, and when a buffer allocation request is received, allocating one or more segments among the plurality of segments based on the segment attribute and the priorities of each of the non-allocated segments relative to the segment attributes.

Abstract: Certain aspects of the present disclosure provide techniques for generating a user experience for a software program product based on a knowledge engine. Techniques for generating the user experience include a UI builder tool providing a set of tabular UI views and receiving in each tabular UI view corresponding input data for generating a calculation graph, a completeness graph, and a client UI view. Based on the input data, the UI builder tool and knowledge engine can generate a set of artifact files. The knowledge engine can generate and/or execute the calculation and completeness graphs as defined in the corresponding artifact files. The UI builder tool can generate an instance of the client UI view. With the generated calculation graph(s), completeness graph(s), and an instance of the client UI view, the user experience can be provided to a computing device.

Abstract: A computing device, such as a personal computing device (e.g., laptop, smartphone, etc.) or server, is configured to utilize environmental factors in generating public/private key pairs to access restricted data or operations. The environmental factors can include location, time, barometric pressure, acceleration, temperature, humidity, and the like. An initial key pair may be used to encrypt data and enable other conventional security features. A key pair can be subsequently generated based on the same environmental factors as with the initial key pair generation and used to access the data or operations which have been restricted using the initial key pair.

Abstract: Embodiments for preemptive substitution of resources in a disaggregated computing environment. Failure patterns and mitigation actions are analyzed for specific failures of respective resources within the disaggregated computing environment. Responsive to determining a failure threshold has been reached for a first resource of a first type of the respective resources, a mitigation action is performed according to the analyzed failure patterns. A result of the mitigation action is determined and the result is used to improve the failure pattern analyzation.

Abstract: The technology includes methods, processes, and systems for virtualizing graphics processing unit (GPU) memory. Example embodiments of the technology include managing an amount of GPU memory used by one or more processes, such as Application Programming Interfaces (APIs), that directly or indirectly impact one or more other processes running on the same GPU. Managing and/or virtualizing the amount of GPU memory may ensure that an end user does not receive a GPU out-of-memory error because the API request is impacted by the processing of other API requests. A virtual machine with access to a GPU may be organized with one or more job slots that are configured to specify the number of processes that are able to run concurrently on a specific virtual machine. A process may be configured on each virtual machine running a software program or API and is used to schedule work based on GPU memory requirements.

Abstract: Embodiments are described for dynamically allocating and reallocating system resources between production work tasks and administrative tasks using policies. A resource monitor continuously monitors all resources in a computing system, and whether the resources are used for production work or administrative tasks. A policy can define resources needed to execute an administrative task and conditions which can be used to determine whether or not the administrative command is allocated the resources, even at the expense of a negative impact to production work.

Abstract: Techniques are disclosed for reducing power consumption on a power sensitive wireless device, such as for example a digital wireless camera operating on a battery. According to some techniques, power can be reduced when a portable device is in close proximity to the power sensitive wireless device, such as when a person is home and the recording of video on a digital wireless security camera can be disarmed. Some techniques include filtering mechanisms, which reduce unnecessary information being transmitted to the wireless network circuit of the power sensitive wireless device. Other techniques include modifying or adapting IEEE 802.11 standards to achieve power reducing results such as for example reducing the number of times to wake up to receive the beacons. Also, improved synchronization techniques are implemented such as for example improved synchronization accuracy allows reducing the duration of the wake time for receiving the beacons.

Abstract: The technology disclosed relates to buffer-based inter-node streaming of configuration data over a network fabric. In particular, the technology disclosed relates to a runtime processor configured to load and execute a first subset of configuration files in a set of configuration files on a first reconfigurable processor operatively coupled to a first processing node, load and execute a second subset of configuration files in the set of configuration files on a second reconfigurable processor operatively coupled to a second processing node, and use a first plurality of buffers operatively coupled to the first processing node, and a second plurality of buffers operatively coupled to the second processing node to stream data between the first reconfigurable processor and the second reconfigurable processor to load and execute the first subset of configuration files and the second subset of configuration files.

Abstract: Examples of device-driven management is described. A management service can generate a management console that includes a set of workflow objects to use in a workflow creation user interface. A management workflow can be retrieved from a network service and translated to be formatted into the workflow objects. A user can select the management workflow, and the management console can be updated to show graphical representations of the workflow objects. The management service can transmit a device-driven management workflow that includes a translated version of the management workflow.

Abstract: A method provides for controlling compliance remediation that includes performing compliance inspection runs by account nodes for multiple accounts. Inspection results of the inspection runs from each account node are aggregated by an account cognitive policy advisory (CPA) service. The inspection results from each account are aggregated. It is determined whether remediations are required by analyzing the inspection results combined with a current compliance mode of a server. Upon a determination that the current compliance mode of the server is a first mode, the account CPA service determines whether a policy fingerprint has changed. Upon a change to the policy fingerprint, compliance enforcement runs on the account nodes are temporarily suspended.

Abstract: An orchestrator platform may receive information identifying container attributes from a plurality of containers. The orchestrator platform may create aggregated information regarding the container attributes. The orchestrator platform may analyze the aggregated information to assign containers to container clusters. The orchestrator platform may analyze script information to assign scripts to script clusters. The orchestrator platform may match the script clusters and the container clusters. The orchestrator platform may generate information regarding a set of scripts for a container cluster based on the matching. The orchestrator platform may send the information regarding the set of scripts to a container to cause the container to obtain one or more scripts and execute the one or more scripts. The orchestrator platform may receive execution results. The orchestrator platform may determine whether a set of rules are satisfied.

Abstract: Methods, systems, and computer-readable media for dynamic regulation of parallelism for job scheduling are disclosed. A job scheduler sends a resource manager a request to execute a first set of compute jobs using a set of computing resources. The number of jobs corresponds to a first parallelism value. The job scheduler receives a response indicating that the number of computing resources was sufficient or insufficient to schedule the jobs. The job scheduler sends another request to execute another set of compute jobs whose number corresponds to a new parallelism value determined based at least in part on the response. If the number of computing resources was sufficient, the new parallelism value represents an increase over the first parallelism value. If the number of computing resources was insufficient, the new parallelism value represents a decrease from the first parallelism value.

Abstract: A method for selecting an action, includes reading, into a memory, a Partially Observed Markov Decision Process (POMDP) model, the POMDP model having top-k action IDs for each belief state, the top-k action IDs maximizing expected long-term cumulative rewards in each time-step, and k being an integer of two or more, in the execution-time process of the POMDP model, detecting a situation where an action identified by the best action ID among the top-k action IDs for a current belief state is unable to be selected due to a constraint, and selecting and executing an action identified by the second best action ID among the top-k action IDs for the current belief state in response to a detection of the situation. The top-k action IDs may be top-k alpha vectors, each of the top-k alpha vectors having an associated action, or identifiers of top-k actions associated with alpha vectors.

Abstract: Example resource management systems and methods are described. In one implementation, a resource manager is configured to receive a query to process database data. A plurality of virtual processors is operatively coupled to the resource manager. Each virtual processor comprises at least one CPU core and one storage device. The resource manager is configured to allocate computing resources from the plurality of virtual processors to process the database data in response to the query.

Abstract: A method includes generating an instance on a host computing device in response to a request to host a web application on the host computing device, and determining a resource usage profile associated with the instance. The resource usage profile indicates one or more specific resources on the host computing device to be utilized to host the web application. The method further includes selecting one of a stored plurality of resource models based at least in part on the resource usage profile, and modifying the instance on the host computing device in accordance with the selected one of the stored plurality of resource models. The instance is modified to host the web application.

Abstract: A network-based data store maintaining storage volumes for file systems at storage clients may implement dynamic storage volume scaling. A scaling event may be detected according to a specified scaling policy for a storage volume maintained at a network-based data store that is mounted at a storage client and configured for a file system. In a least some embodiments, the scaling policy for the storage volume may be received from the storage client. In response to detecting the storage event, storage maintaining the storage volume may be modified according to the scaling policy to scale the storage volume. An indication of the scaling event may be sent to the storage client in order to update the file system at the storage client so that the file system may utilize the scaled storage volume.

Abstract: A system including: a processor; and a memory storing computer program code that controls the processor to: collect real-time business process metrics; collect real-time cluster metrics for a plurality of application clusters indicative of a required allotment of infrastructure resources for a given business process level; estimate a predicted future business process level; based on the estimated predicted future business process level and the real-time cluster metrics, predict a future infrastructure resource requirement of each of the plurality of application clusters; compare the predicted future infrastructure resource requirement of each of the plurality of application clusters to a current dedication of each of the plurality of application clusters; automatically adjust, in real-time and based on the comparison, respective allotments of infrastructure resources for each of the plurality of application clusters; receive an actual business process; and process the business process across the plurality of

Abstract: A virtual disk is provided to a computing environment. The virtual disk includes identity information to enable identification of a virtual machine within the computing environment. A size of the virtual disk is increased within the computing environment to enable the virtual disk to act as a storage for the identity information and as a cache of other system data to operate the virtual machine. The virtual machine is booted within the computing environment. The virtual machine is configured to at least access the virtual disk that includes both identity information and caches other system data to operate the virtual machine. Related apparatus, systems, techniques and articles are also described.

Abstract: In some implementations, a computing device may configure a new device based on a current state of an old device, including settings, preferences, and other user data. The data may be transferred from the old device to the new device, and then relocated according to a manifest that details positions of the data on the old device. The destination device may be rebooted into a configuration mode to allow for the relocation of the transferred data, and then rebooted again to configure the destination device to provide access to the data in its respective relative locations on the destination device.

Abstract: Techniques for specifying and implementing a software application targeted for execution on a multiprocessor array (MPA). The MPA may include a plurality of processing elements, supporting memory, and a high bandwidth interconnection network (IN), communicatively coupling the plurality of processing elements and supporting memory. In some embodiments, software code may include first program instructions executable to perform a function. In some embodiments, the software code may also include one or more language constructs that are configurable to specify one or more one or more parameter inputs. In some embodiments, the one or more parameter inputs are configurable to specify a set of hardware resources usable to execute the software code. In some embodiments, the hardware resources include multiple processors and may include multiple supporting memories.

Abstract: A system and method for optimizing runtime environments for applications by running the applications in a plurality of runtime environments and iteratively selecting and creating new runtime environments based on a fitness score determined for the plurality of runtime environments.

Abstract: Embodiments of the application provide a resource configuration method, a mobile terminal and a storage medium. An operating system in an operating system space of a mobile terminal firstly receives a scenario data packet sent by a running target application program, the scenario data packet comprising an application type identifier and a scenario identifier of the target application program, then determines a performance improvement strategy according to the application type identifier and the scenario identifier, and adjusts allocation of a system resource for the target application program according to the performance improvement strategy.

Abstract: Technology is described for computationally intensive distributed computing systems and methods. A method for using object types to distribute processing may include determining object types for data objects. A mapping between the data objects and processing partitions may be determined using the object types. A processing partition may be associated with a processing application that processes data objects of a given object type. A hardware host in a distributed computing system may identify an application library having a plurality of processing applications that process a plurality of data objects associated with a plurality of object types. The hardware host may use the processing partition assigned to the hardware host to identify the processing application for the object type associated with the processing partition from the application library. The hardware host may launch an instance of the processing application to enable the hardware host to process the plurality of data objects.

Abstract: Remote provision of a drone resource is disclosed. A user equipment (UE) can generate a request for drone resources that can be employed to find an appropriate drone from a set of drones. The drone can be automatically provisioned to allow access to the drone resource in accord with the request. The set of drones can comprise different tiers of drones. A response can be generated indicating the state of provisioning a drone in accord with the request. The user equipment can make the request available to a drone allocation component via a communication framework that can comprise a wireless interface. Provisioning of the drone can similarly be accomplished via the communication framework. As such, the set of drones can be distributed and can be provisioned from a UE located remotely from the drone allocation component and/or the drones comprising the set of drones.

Abstract: A system includes an application server, a memory, and a processor. The application server runs one or more software threads. The memory stores snapshots of the system performance of the application server taken at periodic time intervals, a repository of previous stuck thread scenarios, and a plurality of thread healing scripts. The processor monitors server performance parameters, determines that a thread running on the application server is stuck, retrieves a set of snapshots of the system performance taken before the moment when it was determined that the thread is stuck, identifies from among the retrieved set of snapshots the oldest snapshot with a server performance parameter that exceeds a threshold, compares the server performance parameters in the identified oldest snapshot with the repository of previous stuck thread scenarios to identify a closest match, identifies a script for resolving the matched stuck thread scenario, and executes the identified script.

Abstract: Hardware accelerators are scored according to various metrics and attributes that characterize the accelerators. Examples of suitable accelerator scoring criteria include whether the software simulation of the accelerator is complete, whether hardware testing is complete, whether the accelerator is currently deployed, the number of times the accelerator has been deployed to a private cloud, the number of times the accelerator has been deployed to a public cloud, ratings by users, number of failures, number of executions, space utilization and efficiency, code metrics, power consumption, speed, and image characteristics, including space used, resources used, use of dedicated functions on a programmable device, etc. These accelerator scoring criteria are tracked for each accelerator in an accelerator scoring catalog.

Abstract: An event monitoring processor includes a processor and at least one memory. The memory stores a database of cohort definitions. Each cohort definition defines a respective cohort. The processor is configured to receive particulars of a member event initiated by a member of one of the cohorts, generate an additional cohort definition from the particulars of the member event, and save the additional cohort definition in the cohort definitions database. The processor is also configured to receive member data associated with the cohort member, select one of the cohorts in the cohort definitions database from a correlation between the member data and the cohort definitions, and save in a cohort member database a member record that identifies a correlation between the member event and an event defined in the selected one cohort.

Abstract: Included is a method for autonomous robotic refuse container replacement including: transmitting, by a processor of a first robotic refuse container, a request for replacement to a portion of processors of robotic refuse containers; receiving, by the processor of the first robotic refuse container, a return signal from a portion of processors of the robotic refuse containers; transmitting, by the processor of the first robotic refuse container, a confirmation for replacement to a processor of a second robotic refuse container in response to a return signal received from the processor of the second robotic refuse container; instructing, by the processor of the first robotic refuse container, the first robotic refuse container to navigate to a second location from a current location; and instructing, by the processor of the second robotic refuse container, the second robotic refuse container to navigate to the current location of the first robotic refuse container.

Abstract: In one example, a request may be received to create a digital worker to perform at least one automated task. The digital worker may be created in an organization upon receiving the request. Example digital worker may be a computer program to perform the at least one automated task. Credentials may be generated for the created digital worker. The credentials associated with the created digital worker may be updated in the organizations employee directory. The digital worker may be enabled to perform the at least one automated task upon updating the credentials in the organizations employee directory.

Abstract: Embodiments herein receive a request to reserve a fog computing resource for an end device, where the request includes a specified future time at which the fog computing resource will be used by the end device. It is determined that sufficient fog computing resources are available at the specified future time on a first fog node of a plurality of fog nodes. The fog computing resource of the first fog node is reserved for the specified future time, and an address corresponding to the first fog node is transmitted.