摘要:
Methods and systems for improving resource utilization when remoting three dimensional graphics commands generated by an application executing on a local computing machine include intercepting, by an agent executing on a local computing machine, a first call to a drawing library, the first call generated by an application requesting information from the drawing library. The agent transmits a first frame, generated by the application, to a remote computing machine. Upon failing to receive a notification indicating the first frame was rendered, a return of the first call to the requesting application is prevented. The agent receives a notification, generated by the remote computing machine, indicating the first frame was rendered, and permits the return of the first call to the requesting application.
摘要:
A utility program executing on a mobile communication device decides whether to launch an application remotely as a Webapp or whether to launch the application locally on the mobile communication device. The decision is based at least in part on an estimate of how much of a resource the application would consume were the application to be launched and executed on the mobile communication device. Examples of resources include battery capacity, memory capacity, and processing power capacity. If the total amount of a resource consumed by currently executing applications and the application to be launched would exceed a threshold amount, then the utility uses a browser on the mobile communication device to launch the application remotely as a Webapp, otherwise the utility program causes the application to be launched locally. The utility program has a graphical user interface (GUI) whereby utility program operation can be configured and customized.
摘要:
A method of integrating an on-demand compute environment into a local compute environment comprises: receiving a request to integrate the on-demand compute environment with the local compute environment; in response to the request, routing local workload information comprising at least one of policy requirements for submitted jobs and resource configuration information from the local compute environment to the on-demand compute environment; and creating a customized environment in the on-demand compute environment for processing submitted jobs in the on-demand compute-environment, based at least on the local workload information, that (1) mirrors the local compute environment with respect to at least one of rigid resource attributes and flexible resource attributes and that (2) complies with the policy requirements associated with the local compute environment.
摘要:
A novel personal electronic device includes a processor having first (embedded) and second (non-embedded) cores including associated operating systems and functions. In one aspect, the first core performs relatively limited functions, while the second core performs relatively broader functions under control of the first core. Often the second core requires more power than the first core and is selectively operated by the first core to minimize overall power consumption. Protocols for functions to be performed by the second core may be provided directly to the second core and processed by the second core. In another aspect, a display controller is designed to interface with both cores. In another aspect, the operating systems work with one another. In another aspect, the first core employs a thermal control program. Advantages of the invention include a broad array of functions performed by a relatively small personal electronics device.
摘要:
Disclosed are systems, methods and computer-readable media for controlling and managing the identification and provisioning of resources within an on-demand center as well as the transfer of workload to the provisioned resources. One aspect involves creating a virtual private cluster within the on-demand center for the particular workload from a local environment. A method of managing resources between a local compute environment and an on-demand environment comprises detecting an event associated with a local compute environment and based on the detected event, identifying information about the local environment, establishing communication with an on-demand compute environment and transmitting the information about the local environment to the on-demand compute environment, provisioning resources within the on-demand compute environment to substantially duplicate the local environment and transferring workload from the local-environment to the on-demand compute environment. The event may be a threshold or a triggering event within or outside of the local environment. The transfer of workload and provisioning of the on-demand center may also be related to a profile of the workload or an analysis of backlog workload. Another aspect relates to transferring webserver traffic from a webserver to an on-demand center such that web traffic is served by the on-demand center.
摘要:
A programmatic interface to allow external functions to be registered and called in parallel from within a database management system is described for coordinating a computation at multiple nodes. In one embodiment, each node executes a process configured for starting a program to perform the computation in response to a command received from a database system. In response to receiving a query at the database system, multiple commands are transmitted to the processes for concurrently performing the computation at each said corresponding process. Results are received from each of the processes and execution of the statement is completed based on the results received.
摘要:
A management processor (32) of a main processor unit (100) transmits a request for task switching that includes information related to a task performed after the switching, from a main processor communication unit (62) to a graphic processor communication unit (72) of a graphic processor unit (100). A memory controller (70) of the graphic processor unit (100) reads image-related data related to a task before the change from a graphic memory (10), and saves the read data in a main memory (50). The memory controller (70) reads the data related to the task after the change from the main memory (50), which stores previously saved image-related data. The memory controller (70) restores the read data to the graphic memory (10). The graphic processor communication unit (72) transmits an acceptance permit signal indicating that the graphic processor unit (100) is ready for task switching to the main processor communication unit (62). After acknowledging the acceptance permit signal, the main processor unit (200) switches between tasks in the management processor (32).
摘要:
A plurality of sub-processors (30) and a management processor (32) process the first task. A graphic processor unit (100) executes image processing corresponding to the first task processed by the management processor (32). One of the sub-processors (30) performs a second task different from the first task. An image process related to the first task and originated in the sub-processor is accepted by the graphic processor unit (100) and associated first rendering data is transferred to the graphic processor unit (100). Meanwhile, when the need arises in the one of the sub-processors (30) for a second image process related to the second task, the one of the sub-processor (30) saves second rendering data for the second image process in a main memory (50). Subsequently, when the graphic processor unit (100) starts the second image process corresponding to the second task, the second rendering data is transferred from the main memory (50) to a graphic memory (10).
摘要:
An inexpensive network service without time constraints is provided to an information terminal through delegation thereof. A method for delegating information processing includes the steps of: establishing a wireless link between a first information terminal (10) and a second information terminal (20) located nearby; providing, from the second information terminal, an information processing delegation certificate to the first information terminal via the wireless link, and requesting the first information terminal for the delegation of desired information processing, such as information transmission processing or information reception processing; the first information terminal moving to the neighborhood of access service equipment for a wide-area network (40); establishing a wireless link between the first information terminal and access service equipment; performing, at the first information terminal, information processing with the wide-area network via the access service equipment, based on the request; the first information terminal moving back to the neighborhood of the second information terminal, where the wireless link is re-established between the two terminals; and the first information terminal reporting to the second information terminal the results of the requested information processing.