Methods of communication between a remote resource and a data processing device, the system include storing in a transaction queue a message posted from the remote resource; sending a request to create a guest transaction queue, the guest transaction queue being accessible by both the data processing device and the remote resource; creating the guest transaction queue; reading, by the data processing device, the message from the remote resource; responding, from the data processing device to the remote resource by posting a message to the guest transaction queue; reading, by the remote resource, the message from the data processing device.

Systems and methods for a playback device outputting an audio alert from a network-enabled device include (i) while the playback device is playing back audio content, receiving an alert communication from the network-enabled device, the alert communication including (a) an audio notification identifier that identifies an audio notification and (b) a priority identifier that identifies a priority level of the audio notification; (ii) responsive to receiving the alert communication, adding the audio notification to a notification queue at a particular queue position, where the particular queue position of the audio notification in the notification queue is based on the priority level of the audio notification relative to other audio content in the notification queue; (iii) adjusting playback of the audio content for playing back the audio notification; and (iv) the playback device playing back the audio notification.

Methods and systems are provided for processing a stream of incoming messages sent from a specific input message source and validating each incoming message of that stream before sending them to a specific target system.

In one embodiment, an apparatus includes: a plurality of queues having a plurality of first entries to store receive information for a process; a master queue having a plurality of second entries to store wild card receive information, where redundant information of the plurality of second entries is to be included in a plurality of redundant entries of the plurality of queues; and a control circuit to match an incoming receive operation within one of the plurality of queues. Other embodiments are described and claimed.

A method, computer program product, and computer system for maintaining, at a computing device, one or more tuples in a software-level queue. The one or more tuples may be transported as a batch of the one or more tuples from the software-level queue to a first queue for processing at a hardware accelerator. After processing the one or more tuples, the one or more tuples may be transported from the first queue to a second queue at the hardware accelerator. The one or more tuples may be transported from the second queue to a next location.

The present disclosure provides modular electronic devices that are capable of managing task performance based on a particular context of computing resources currently available from the ad hoc combination of devices.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for batching inputs to machine learning models. One of the methods includes receiving a stream of requests, each request identifying a respective input for processing by a first machine learning model; adding the respective input from each request to a first queue of inputs for processing by the first machine learning model; determining, at a first time, that a count of inputs in the first queue as of the first time equals or exceeds a maximum batch size and, in response: generating a first batched input from the inputs in the queue as of the first time so that a count of inputs in the first batched input equals the maximum batch size, and providing the first batched input for processing by the first machine learning model.

Methods, systems, and media are provided for automatically determining a preferred queue size for an individual queue based on message traffic. Embodiments include referencing a plurality of queue data sets for one queue. One or more high-activity queue data sets are identified as having a large number of messages compared to other queue data sets in the plurality. Thereafter, a target size for a queue is determined based on an average message size generated using one or more of the high-activity queue data sets. The current size of the queue is adjusted to reflect the target size. In further aspects, the queue data sets may be collected over time intervals that are dynamically modified based on message traffic.

Computer implemented systems and methods intelligently distribute tasks received from clients among worker resources. One or more databases store information about worker resources and information about clients. A task assignment server, communicatively coupled to the database(s), receives a plurality of tasks that are to be performed for the clients, accesses the stored information about the worker resources, accesses the stored information about the clients, and assigns each of a majority of the tasks to one of the plurality of worker resources, in dependence on the information about the plurality of worker resources and in dependence on the information about the plurality of clients, so that the plurality of tasks are distributed among two or more of the plurality of worker resources. The system can also include a plurality of queues adapted to store information about tasks assigned to the worker resources associated with the queues.

In an embodiment, a method is provided. In an embodiment, the method provides determining that a message has been placed in a send buffer; and transferring the message to an application on a second virtual machine by bypassing use of an operating system to process the message by directly placing the message in an application memory space from which the application can retrieve the message.