132 results about "Resource contention" patented technology

Computer processors and methods of operation of computer processors that include a plurality of pipelined hardware threads of execution, each thread including a plurality of computer program instructions; an instruction decoder that determines dependencies and latencies among instructions of a thread; and an instruction dispatcher that arbitrates, in the presence of resource contention and in accordance with the dependencies and latencies, priorities for dispatch of instructions from the plurality of threads of execution.

Monitoring is performed to detect a hang condition. A timer is set to detect a hang based on a core hang limit. If a thread hangs for the duration of the core hang limit, then a core hang is detected. If the thread is performing an external memory transaction, then the timer is increased to a longer memory hang limit. If the thread is waiting for a shared resource, then the timer may be increased to the longer memory hang limit if another thread or, more particularly, the thread blocking the resource has a pending memory transaction. Responsive to detecting a hang condition, instructions dispatched to the plurality of execution units may be flushed, or the processor may be reset and restored to a previously known good, checkpointed architected state.

A method for determining where in time to schedule a project in a computerized system for scheduling multiple projects operates in conjunction with a database composed of schedules for individual projects with resources assigned to some tasks. A user specifies the resources to be used for a new project, the loading caused by projects whose dates are already determined, the earliest possible start times for the new project, and the maximum amount of expansion in flow time (start to finish time) allowed for the new project, with considering inter-project resource contention. The new project is delayed only long enough to allow contention for the selected resources to be resolved, while not violating the flow time expansion restriction.

Under a resource manager, unexpected blocking is prevented without calling a handler for resolving a resource contention, by assigning a priority level depending on the program that has requested for a reservation of a resource as well as by assigning a special priority level which permits a reservation of a resource without any conditions in the case of a program which is urgently needed such as an EAS module.

In a computer system an object of this invention is to reduce physical resource contentions during the parallel migration of volumes. The computer system of this invention has the host computers, the storage systems and the storage management server. When parallelly migrating two or more volumes of data in the storage systems to the same number of other volumes, the storage management server selects volumes having few physical conflicts of the controllers or storage devices in the storage systems and executes the parallel migration operation.

A digital cable network architecture and services method includes a cable medium and a plurality of hosts that include a receiver. A policy file store contains policy files having at least one of a service provider section, a consumer section, and a manufacturer section that can be updated by at least one of the service provider, a consumer and a receiver manufacturer, respectively. A service provider that is associated with the policy file store provides digital cable services over the cable medium to the hosts and downloads monitor applications and policy files to the hosts over the cable medium. The MAs use the service provider section, the consumer section, and/or the manufacturer section of the policy file to alter resource contention, alter service provisioning at levels below a channel level, and/or alter fraudulent receiver identification calculations.

A performance prediction simulator gives effect to the resource contention among multiple resources in a simulated system by adjusting event durations appropriately. A resource topology tree defining the resource configuration of the system is input to the simulator. The simulator includes an evaluation engine that determines the amount of resource used during each simulation interval of the simulation and records the resource usage in a resource contention timeline, which can be displayed to a user. The amount of resource used during a simulation is also used to adjust the event duration calculations of the hardware models associated with each event.

The embodiment of the invention provides a GPU cluster deep learning task parallelization method, a GPU cluster deep learning task parallelization device and electronic equipment, and relates to the technical field of internet. The method comprises the following steps: firstly, analyzing the similarity between a to-be-processed deep learning task and each computing node of a GPU cluster; determining a target computing node of the to-be-processed deep learning task in the GPU cluster, reducing the possibility of computing node resource contention, and improving the utilization rate and the execution efficiency of deep learning task system resources; according to the number of GPUs required by the to-be-processed deep learning task, obtaining a to-be-processed deep learning task; dividing the to-be-processed deep learning task into a plurality of target sub-tasks, analyzing the interference level and the communication cost of the target subtask; determining the target GPU of the target sub-task in the target computing node, and avoiding unbalanced resource allocation on the GPU in the computing node. The high parallelization of the deep learning task is realized. The resource utilization rate of the GPU cluster is improved. Meanwhile, the execution efficiency of the deep learning task is improved.

A digital cable network architecture includes hosts that include a receiver with a hash function generator that calculates hash values based on a hash function and data from memory blocks in the receiver. A policy file store contains policy files having a service provider section, a consumer section, and/or a manufacturer section that can be updated by the service provider, a consumer and/or a receiver manufacturer. A service provider downloads monitor applications (MAs) and policy files to the hosts over the cable medium. The MAs access the service provider section, the consumer section, and/or the manufacturer section of the policy file to alter resource contention, service provisioning, and/or alter fraudulent receiver identification calculations. The hash function of the receiver outputs the hash values to the MA, which compares the hash values to expected hash values to identify fraudulent access.

The invention discloses a distributed system for avoiding global resource disorder, which comprises main control equipment and service equipment, wherein the main control equipment transmits resource operating information to the service equipment according to service requests, and the service equipment utilizes a preset resource-occupying marker to judge whether a target resource is available and utilizes a preset buffer linked list to restore services stopped because of resource contention. The invention also correspondingly discloses the service equipment for avoiding global resource disorder and a method for applying the distributed system. The distributed system, the service equipment and the application method thereof can simply avoid the synchronous disorder of global resources while avoiding cross-module resource release, and can automatically restore the services.

To facilitate both minimal allocations and adaptive allocations, two sets of storage group policies are defined—one policy setting minimal allocation values for storage group access to storage resources and one policy setting maximal allocation values for storage group access to storage. In addition, a set of priority weights is specified that is used to balance access to storage tiers across storage groups. Upon existence of contention for storage resources, minimum allocation values for storage groups are determined based on the priority weights for the storage groups, resulting in threshold values being set to enable at least partial access to storage resources for all storage groups without requiring priority weighting of the activity density distributions of the competing storage groups. Allocations other than the minimal allocations are provided based on relative activity density distribution of storage extents between groups.

Techniques are disclosed relating to resource contention resolution in a pre-memory environment. Prior to system memory being accessible, a resource control processing element controls access to a hardware resource by a plurality of processing elements by granting received requests from the processing elements for access to the resource. The resource control processing element may prioritize requests based on a determined amount of utilization of the hardware resource by individual ones of the processing elements. In one embodiment, processing elements request for information from a bus controller (e.g., an SMBus controller) that is usable to initialize system memory. The resource control processing element may respond to the requests by retrieving the requested information from the controller and providing that information to the processing element or by retrieving the requested information from a cache and providing that information to the processing element.

The invention discloses a cluster resource scheduling method and system. The cluster resource scheduling method comprises the steps: carrying out the resource scheduling of a task in real time based on the priority of the task; acquiring total resource information and task execution information of the cluster in real time, and traversing real-time resource occupation data of each task being executed; and judging whether the resource occupation data is abnormal in real time according to the abnormal standard, and optimizing the resource scheduling of the task in real time according to the judgment result, so that the conditions of abnormal scheduling, resource contention and the like of the YARN under a high-load condition are reduced, and the cluster operation capability and reliability are further improved. The cluster resource scheduling system disclosed adopts the scheduling method, thus effectively improving the cluster operation capability and reliability, and solving the problemsof resource contention, scheduling abnormality and the like in a service peak period.

The invention discloses a method and an apparatus for resource contention based on an access priority. The method comprises the steps of establishing or re-establishing a user group, by a serving base station, based on an interference environment of user equipments within a cell; receiving, by the user equipment, an uplink schedule grant from a serving base station, the uplink schedule grant comprising an access priority of the user equipment on an unlicensed frequency band; configuring, by the user equipment, an uplink frame structure for uplink transmission of the unlicensed frequency band based on the access priority; blind-detecting other reserved signals of other user equipments within a user group on the unlicensed frequency band based on the uplink frame structure; performing channel clearance assessment to the unlicensed frequency band based on the uplink frame structure; if the user equipment fails to blind-detect the other reserved signals and a result of the channel clearance assessment is idle, transmitting a first reserved signal on the unlicensed frequency band and performing uplink data transmission of the user equipment; and if the user equipment blind-detects the other reserved signals or a result of the channel clearance assessment is busy, stopping contending for the unlicensed frequency band.