An application control method includes: acquiring a multimedia resource, the multimedia resource being based on historical data of an account that is logged into a second application, the account being the same as an account that is logged into a first application; and acquiring an operation instruction for the first application, executing the operation instruction in the first application, and displaying the multimedia resource.

Execution systems for augmenting legacy user interfaces include a memory, one or more input/output device, and one or more processors coupled to the memory and the one or more input/output devices. The one or more processors are configured to load a workflow described according to a workflow structure, the workflow structure describing subprocesses of the workflow, routings between the subprocesses, and actions that make up the subprocesses; connect to a legacy user interface based on the workflow; receive a message from the legacy user interface; determine a subprocess for responding to the message based on the workflow; and perform one or more actions of the determined subprocess to respond to the message. In some embodiments, performing the one or more actions includes presenting information from the message to an operator, soliciting input from the operator, and sending a response to the legacy user interface based on the input.

The present application discloses a task allocation method and system based on a resource management platform. The method comprises: receiving an artificial intelligence model training and/or testing task and a name of data set required for processing the task; acquiring data set distribution information of a plurality of nodes; judging if the node has the required data sets according to names of the data sets in the node; and selecting a node with the size of the required data set meeting preset requirements for task allocation according to the size of the required data set in the node if the node has the required data set. It may be seen that, in the present application, the situation of data sets in a node is taken into account during task allocation, and the node with the size of the required data set meeting preset conditions is selected for task allocation, such that the node does not need to download the required data set or reduce the frequency of downloading data sets by a node, thereby improving the efficiency in processing tasks.

Described approaches provide for effectively and scalably using multiple GPUs to build and probe hash tables and materialize results of probes. Random memory accesses by the GPUs to build and/or probe a hash table may be distributed across GPUs and executed concurrently using global location identifiers. A global location identifier may be computed from data of an entry and identify a global location for an insertion and/or probe using the entry. The global location identifier may be used by a GPU to determine whether to perform an insertion or probe using an entry and/or where the insertion or probe is to be performed. To coordinate GPUs in materializing results of probing a hash table a global offset to the global output buffer may be maintained in memory accessible to each of the GPUs or the GPUs may compute global offsets using an exclusive sum of the local output buffer sizes.

Coordinated application processing. A method identifies processing engines available for coordinated application processing, distributes to the processing engines an application configured for execution to perform image processing, and distributes images to the processing engines. The images cover an image area that includes multiple different sub-areas, where the image processing proceeds across multiple cycles of image processing to process a respective set of images of each sub-area of the multiple different sub-areas, and where the distributing the images includes, for each sub-area of the multiple different sub-areas: selecting for that sub-area a respective processing engine of the processing engines to perform the image processing across the multiple cycles to process the respective set of images of that sub-area, and distributing, across the multiple cycles of the image processing, the images of the respective set of images of that sub-area to the respective processing engine selected for that sub-area.

A system and method is provided for timely and uniform real-time data packet transmission by a computing device. The system can include a shared packet memory buffer for storing data packets generated by a user application and a shared schedule memory buffer for storing packet identifiers and corresponding time slots for the data packets. Moreover, a kernel module is provided that operates in the kernel mode of the operating system directly above the network interface controller and can continuously poll the shared scheduled memory to access packet identifiers at corresponding time slots. Based on the packet identifiers in each time slot, the kernel module can pull the data packet having the packet identifier directly from the ring buffer and send each packet to the network interface controller for transmission as part of a media stream over a network to a media consuming device.

A distributed processing node includes a computing device that calculates gradient data of a loss function from an output result obtained by inputting learning data to a learning target model, an interconnect device that aggregates gradient data between the distributed processing node and other distributed processing nodes, a computing function unit that is provided in a bus device and performs processing of gradient data from the computing device, and a DMA controller that controls DMA transfer of gradient data between the computing device and the bus device and DMA transfer of gradient data between the bus device and the interconnect device.

A method, system and computer program product for managing a plurality of resources in a digital environment via a framework. The framework comprises an API an intermediary component for proxying communication between the API and the resources; and at least one isolated network segment comprising the plurality of resources associated with the digital environment. The method comprises receiving through the API, an input requesting a state of the digital environment, and characteristics associated with the plurality of resources The characteristics of at least one of the plurality of resources are provided to the intermediary component, which are used by the intermediary component, to configure at least one of the resources.

In one example, a system with a processor operable to cause operations to optimize resources based on user-specified parameters is disclosed. A provisioning request to provision resources from multiple resource pools is received. The provisioning request can include the user-specified parameters. The system may determine state data about the resource pools by using an API that interfaces with the resource pools. The system then determines the resource pools that can satisfy the provisioning request based upon the state data and how efficiently each of the resource pools satisfy the provisioning parameters. The system then provisions resources on a resource pool that has been determined to be capable of satisfying the provisioning request.

A method for managing storage and computational resources in a datacenter includes obtaining a power delivery limit for a rack power supply delivering power to the plurality of computing devices and measuring a resource telemetry for the first computing device and second computing device in the server rack. In response to measuring a power draw of the server rack above a power threshold value of the power delivery limit, the method includes allocating the second computing device of the server rack as a storage server to the first computing device. The method occurs at a server rack including a plurality of computing devices. A first computing device and a second computing device are in network communication with one another. Each of the first computing device and second computing device include a processor and a hardware storage device.