Abstract: A bare-metal server of a cloud storage management system comprises a system-on-chip (Soc) and a processor. The SoC receives a volume attaching request sent by a public cloud management component of the management system. The volume attaching request includes an identifier of a system volume storing a file for starting an operating system of a bare-metal server of the management system. The SoC stores the identifier of the system volume based on the volume attaching request. When the bare-metal server of the management system is started, the bare-metal server uses the identifier of the system volume to the system volume, and starts an operating system by means of the SoC accessing the system volume.

Abstract: An apparatus includes a processor and a memory that stores a deep Q reinforcement learning (DQN) algorithm configured to generate an action, based on a state. Each action includes a recommendation associated with a computational resource. Each state identifies at least a role within an enterprise. The processor receives information associated with a first user, including an identification of a first role assigned to the user and computational resource information associated with the user. The processor applies the DQN algorithm to a first state, which includes an identification of the first role, to generate a first action, which includes a recommendation associated with a first computational resource. In response to applying the DQN algorithm, the processor generates a reward value based on the alignment between the first recommendation and the computational resource information associated with the first user. The processor uses the reward value to update the DQN algorithm.

Abstract: In a system for automatic generation of event-driven, tuple-space based programs from a sequential specification, a hierarchical mapping solution can target different runtimes relying on event-driven tasks (EDTs). The solution uses loop types to encode short, transitive relations among EDTs that can be evaluated efficiently at runtime. Specifically, permutable loops translate immediately into conservative point-to-point synchronizations of distance one. A runtime-agnostic which can be used to target the transformed code to different runtimes.

Abstract: An aspect of the present disclosure facilitates resolving tickets in a multi-tenant environment. In one embodiment, a server receives a ticket for a tenant from a ticketing system and then determines a gross job representing a class of jobs suitable for resolution of the received ticket. The server then identifies a set of values for a set of system parameters characterizing the computing resources serving the tenant. The server selects a target job based on the combination of the determined gross job and the set of values for the set of system parameters. The selected target job is then executed to cause resolution of the ticket for the tenant. According to another aspect, the server performs the above noted actions automatically without manual intervention, in response to adding of the ticket into the ticketing system.

Abstract: An embodiment discloses an electronic device including: a first memory in which multiple applications are stored; a second memory; and at least one processor operatively connected to the first memory and the second memory. The processor(s) is configured to determine, based on a history of usage of the multiple applications for a first period of time, a priority of the multiple applications over multiple time intervals included in a second period of time. The processor(s) is further configured to preload a predetermined first number of applications into the second memory based on the priority if a designated condition being satisfied; and preload a first list of applications into the second memory if the designated condition is satisfied in a first time interval, and preload a second list of applications into the second memory if the designated condition is satisfied in a second time interval.

Abstract: Transparent memory management for over-subscribed accelerators is disclosed. A request from a remote initiator to execute a workload on a shared accelerator is received at a host system comprising the shared accelerator. A determination is made that there is insufficient physical memory of the accelerator to accommodate the request from the remote initiator. Responsive to determining that there is insufficient physical memory of the accelerator. An allocation of host system memory is requested for the remote initiator from the host system. A mapping between the remote initiator and the allocation of host system memory is then created.

Abstract: In some examples, a main thread of a plurality of execution threads executing on a plurality of processing cores of at least one hardware-based processor of a network device may receive a request for information associated with network routes that meet one or more criteria. Each of the plurality of execution threads may process a respective routing information partition to generate respective displayable information associated with a respective subset of the network routes that meets the one or more criteria. The main thread may generate consolidated displayable information associated with the network routes that meet the one or more criteria based on the respective displayable information generated by each of the plurality of execution threads. The main thread may output the consolidated displayable information associated with the network routes that meet the one or more criteria for display at a display device.

Abstract: An apparatus includes a first tensor compute cluster configured to receive first input feature tensors, a second tensor compute cluster configured to receive second input feature tensors more sparse than the first input feature tensors, and a vector accelerator. The apparatus also includes circuitry configured to partition an input feature map into a plurality of input feature tensors based on a compression criteria and assign each of the plurality of input feature tensors to one of the first tensor compute cluster, the second tensor compute cluster, or the vector accelerator based upon at least one of parameters including a sparsity and an optimization parameter.

Abstract: A system to facilitate infrastructure management is described. The system includes one or more processors and a non-transitory machine-readable medium storing instructions that, when executed, cause the one or more processors to execute an infrastructure management controller to receive a request to provide infrastructure management services and generate a mapping between at least one instance of the infrastructure management controller and one or more resource instances at one or more on-premise infrastructure controller instances to provide the cloud based infrastructure management services, wherein the request includes one or more configuration parameters.

Abstract: Graphics processing systems and methods are described. A graphics processing apparatus may comprise one or more graphics processing engines, a memory, a memory management unit (MMU) including a GPU second level page table and GPU dirty bit tracking, and a provisioning agent to receive a request from a virtual machine monitor (VMM) to provision a subcluster of graphics processing apparatuses, the subcluster including a plurality of graphics processing engines from a plurality of graphics processing apparatuses connected using a scale-up fabric, provision the scale-up fabric to route data within the subcluster of graphics processing apparatuses, and provision a plurality of resources on the graphics processing apparatus for the subcluster based on the request from the VMM.

Abstract: A computer system adapts processing of expressions by a command-line interface. An expression provided to the command-line interface is analyzed, wherein the command line interface includes pre-defined expression processing. One or more artificial intelligence agents are selected from a plurality of artificial intelligence agents based on the analysis of the expression. The expression is evaluated by the selected one or more artificial intelligence agents to determine processing modifications for the pre-defined expression processing. The expression is processed in accordance with the determined processing modifications and results are provided to the command-line interface. Embodiments of the present invention further include a method and program product for adapting processing of expressions by a shell in substantially the same manner described above.

Abstract: A gateway in a computing system for interfacing a host with a subsystem for acting as a work accelerator to the host, the gateway having: an accelerator interface for enabling the transfer of batches of data to the subsystem at pre-compiled data exchange synchronisation points attained by the subsystem; a data connection interface for receiving data to be processed from storage; and a gateway interface for connection to a third gateway. The gateway is configured to store a number of credits indicating at least one of: the availability of data for transfer to the subsystem at a pre-compiled data exchange synchronisation point; and the availability of storage for receiving data from the subsystem at a pre-compiled data exchange synchronisation point. The gateway uses these credits to control whether or not synchronisation barrier is passed by transmitting synchronisation requests upstream to the third gateway or simply acknowledging the requests received.

Abstract: A method includes obtaining, by a computing system executing a declarative code player, a processing widget defining multiple states and executing, by the computing system executing the declarative code player, the processing widget. Executing the processing widget comprises, for each current state of at least a subset of the states obtaining multiple state lifecycle declaration for the current state from a repository, the state lifecycle declaration is specified as declarative content, executing multiple library instructions according to the state lifecycle declaration to perform at least one operation of the current state, and transitioning, as defined by the current state, to a next state as defined in the processing widget.

Abstract: A method can include receiving scheduled tasks associated with subsystems of a wellsite system wherein the scheduled tasks are associated with achievement of desired states of the wellsite system; transmitting task information for at least a portion of the scheduled tasks to computing devices associated with the subsystems; receiving state information via the wellsite system; assessing the state information with respect to one or more of the desired states; based at least in part on the assessing, scheduling a task; and transmitting task information for the task to one or more of the computing devices associated with the subsystems.

Abstract: A storage system includes a plurality of storage devices coupled to at least one host through a network and configured to form a virtual network of virtual machines generated when the plurality of storage devices are coupled to the network, wherein each of the plurality of storage devices allocates memory resources to the virtual machines and shares device information for the plurality of storage devices through the virtual machines and wherein the host: selects from the plurality of storage devices a main storage device, and transmits a storage pool generation condition to the main storage device that identifies a number of storage pools and a capacity of each storage pool, wherein the main storage device generates at least one storage pool that satisfies the storage pool generation condition using the memory resources allocated to each of the virtual machines.

Abstract: This disclosure describes techniques that enable a parallel execution controller to execute partitioned segments of a data model in parallel and on different network resources. The resultant processed data from each partitioned segment may be combined to form an aggregated set of results data. The parallel execution controller may identify model attributes of a data model and determine whether the data model is partitionable, based on the model attributes. If the data model is partitionable, the parallel execution controller may partition the data model, initiate a parallel execution of the individual partitioned segments on available network resources, and combine the corresponding results data into an aggregated set of results data.

Abstract: Embodiments of the present disclosure relate to availability level-based service management. In an embodiment, a computer-implemented method is disclosed. According to the method, it is detected initiation of a request from a first microservice to a second microservice. The first and second microservices are comprised in a plurality of microservices of an application. The request comprises an expected availability level for the application. In response to a current availability level of the application being higher than or equal to the expected availability level and in response to determining that the execution of the second microservice is unavailable, the request is caused to be routed to a simulated microservice of the second microservice. The simulated microservice is configured to return to the first microservice a dummy response to the request. In other embodiments, a system and a computer program product are disclosed.

Abstract: Techniques for implementing event proxies in a Functions-as-a-Service (FaaS) infrastructure are provided. In one set of embodiments, a computer system implementing an event proxy can receive an event emitted by an event source, where the computer system is part of a first computing cloud including the FaaS infrastructure, and where the event source is a software service running in a second computing cloud that is distinct from the first computing cloud. The computer system can translate the event from a first format understood by the event source to a second format understood by a function scheduler of the FaaS infrastructure, where the function scheduler is configured to schedule execution of functions on hosts of the FaaS infrastructure. The computer system can then make the translated event available to the function scheduler.

Abstract: Disclosed herein are systems and methods for dynamic job performance in secure multiparty computation (SMPC). The method may comprise receiving an SMPC query that indicates a processing job to be performed on a data input. The method may split the data input to generate a plurality of partial data inputs, based on parameters and the query type of the SMPC query. The method may generate a plurality of jobs to perform on the plurality of partial data inputs and determine a combined result of the processing job. The method may adjust the amount of worker processes in a worker pool based on at least one of: required computation, time of day, date, financial costs, power consumption, and available network bandwidth.

Abstract: System and methods providing for categorizing individual virtual machines, as well as the associated application that they form by working in concert, into groups based on the feasibility of hosting the processes that occur on a virtual machine within a container, as well as the relative difficulty of doing so on a virtual machine and application level. The data used to create these scores is collected from the individual machines, at regular intervals through the use of an automated scoring engine that collects and aggregates the data. Said data is then analyzed by the system, that with the aid of passed in configuration data, is configured to generate the scores to allows for an educated and focused effort to migrate from hosting applications on virtual machines to hosting applications on containers.