An architecture for a load-balanced groups of multi-stage manycore processors shared dynamically among a set of software applications, with capabilities for destination task defined intra-application prioritization of inter-task communications (ITC), for architecture-based ITC performance isolation between the applications, as well as for prioritizing application task instances for execution on cores of manycore processors based at least in part on which of the task instances have available for them the input data, such as ITC data, that they need for executing.

An apparatus and method for providing ML processing for one or more ML applications operating on one or more Internet of Things (IoT) devices includes receiving a ML request from an IoT device. The ML request can be generated by a ML application operating on the IoT device and include input data collected by the first ML application. A ML model to perform ML processing of the input data included in the ML request is identified and provided to an ML core for ML processing along with the input data included in the first ML request. The ML core produces ML processing output data based on ML processing by the ML core of input data included in the ML request using the ML model. The ML processing output data can be transmitted to the IoT device.

Systems and methods for performing parallel computation are disclosed. The system can include: a task manager; and a plurality of cores coupled with the task manager and configured to respectively perform a set of parallel computation tasks based on instructions from the task manager, wherein each of the plurality of cores further comprises: a processing unit configured to generate a first output feature map corresponding to a first computation task among the set of parallel computation tasks; an interface configured to receive one or more instructions from the task manager to collect external output feature maps corresponding to the set of parallel computation tasks from other cores of the plurality of cores; a reduction unit configured to generate a reduced feature map based on the first output feature map and received external output feature maps.

A model coordination method for a first device is provided. The first device stores at least one model segment. The at least one model segment is configured to realize a part of functions of a preset model. The method includes: determining a first model segment from the at least one model segment stored in the first device, wherein when the first model segment is executed and a second model segment is executed by a second device, a part of or all the functions of the preset model are realized, the second model segment is one of at least one model segment stored in the second device, and the at least one model segment stored in the second device is configured to realize a part of the functions of the preset model. A model coordination apparatus is also provided.

A system, method and computer-readable media for managing a compute environment are disclosed. The method includes importing identity information from an identity manager into a module performs workload management and scheduling for a compute environment and, unless a conflict exists, modifying the behavior of the workload management and scheduling module to incorporate the imported identity information such that access to and use of the compute environment occurs according to the imported identity information. The compute environment may be a cluster or a grid wherein multiple compute environments communicate with multiple identity managers.

An information processing apparatus includes a memory and a processor couple to the memory and configured to generate one or more job groups by grouping multiple jobs of execution targets in descending order of priority, and perform a control for scheduling execution timings regarding the multiple jobs such that scheduling of respective jobs included in a specific job group including a job having a higher priority is implemented by priority over scheduling of respective jobs included in other job groups. The processor performs the control for scheduling the execution timings of the respective jobs included in the specific job group such that an execution completion time of all the jobs included in the specific job group satisfies a predetermined condition.

Technologies for allocating resources of managed nodes to workloads to balance multiple resource allocation objectives include an orchestrator server to receive resource allocation objective data indicative of multiple resource allocation objectives to be satisfied. The orchestrator server is additionally to determine an initial assignment of a set of workloads among the managed nodes and receive telemetry data from the managed nodes. The orchestrator server is further to determine, as a function of the telemetry data and the resource allocation objective data, an adjustment to the assignment of the workloads to increase an achievement of at least one of the resource allocation objectives without decreasing an achievement of another of the resource allocation objectives, and apply the adjustments to the assignments of the workloads among the managed nodes as the workloads are performed. Other embodiments are also described and claimed.

Methods, systems, and devices for pipeline fusion of a plurality of kernels. In some implementations, a first batch of a first kernel is executed on a first processing device to generate a first output of the first kernel based on an input. A first batch of a second kernel is executed on a second processing device to generate a first output of the second kernel based on the first output of the first kernel. A second batch of the first kernel is executed on the first processing device to generate a second output of the first kernel based on the input. The execution of the second batch of the first kernel overlaps at least partially in time with executing the first batch of the second kernel.

A credit regulation and monitoring module receives a command for an application that is to be executed. In response to the command, credit amount for execution of the command is calculated. Further, an outstanding credit amount is determined based on an outstanding credit table and the other commands being executed. It is determined whether the credit amount and the outstanding credit are below a threshold value. If so, the command is executed and an outstanding credit table is updated to reduce the amount of credit available according to the credit amount allocated to the command.

An integrated circuit includes a primary initiator domain (ID) circuit including having a processor core, a responder domain (RD) control circuit, and a reset controller. Secondary ID circuits, each include a processor core and a reset controller. RD circuitry is coupled to communicate with the primary ID circuit and the secondary ID circuits and includes RD resource circuits. The RD control circuit is configured to allocate each of the RD resource circuits to a first initiator domain consisting of the primary ID circuit or one of the secondary ID circuits, and when one of the secondary ID circuits enters a reset mode of operation, the RD resource circuit allocated to the one of the secondary ID circuits enters a reset while the remaining RD resource circuits are not affected by the reset.