35 results about "Multiple dispatch" patented technology

A processor core having multiple parallel instruction execution slices and coupled to multiple dispatch queues by a dispatch routing network provides flexible and efficient use of internal resources. The dispatch routing network is controlled to dynamically vary the relationship between the slices and instruction streams according to execution requirements for the instruction streams and the availability of resources in the instruction execution slices. The instruction execution slices may be dynamically reconfigured as between single-instruction-multiple-data (SIMD) instruction execution and ordinary instruction execution on a per-instruction basis, permitting the mixture of those instruction types. Instructions having an operand width greater than the width of a single instruction execution slice may be processed by multiple instruction execution slices configured to act in concert for the particular instructions. When an instruction execution slice is busy processing a current instruction for one of the streams, another slice can be selected to proceed with execution.

In an embodiment, a processor includes a multi-level dispatch circuit configured to supply operations for execution by multiple parallel execution pipelines. The multi-level dispatch circuit may include multiple dispatch buffers, each of which is coupled to multiple reservation stations. Each reservation station may be coupled to a respective execution pipeline and may be configured to schedule instruction operations (ops) for execution in the respective execution pipeline. The sets of reservation stations coupled to each dispatch buffer may be non-overlapping. Thus, if a given op is to be executed in a given execution pipeline, the op may be sent to the dispatch buffer which is coupled to the reservation station that provides ops to the given execution pipeline.

A processor core having multiple parallel instruction execution slices and coupled to multiple dispatch queues by a dispatch routing network provides flexible and efficient use of internal resources. The configuration of the execution slices is selectable so that capabilities of the processor core can be adjusted according to execution requirements for the instruction streams. Two or more execution slices can be combined as super-slices to handle wider data, wider operands and / or vector operations, according to one or more mode control signal that also serves as a configuration control signal. The mode control signal is also used to partition clusters of the execution slices within the processor core according to whether single-threaded or multi-threaded operation is selected, and additionally according to a number of hardware threads that are active.

A method of operating a processor core having multiple parallel instruction execution slices and coupled to multiple dispatch queues by a dispatch routing network provides flexible and efficient use of internal resources. The configuration of the execution slices is selectable so that capabilities of the processor core can be adjusted according to execution requirements for the instruction streams. Two or more execution slices can be combined as super-slices to handle wider data, wider operands and / or vector operations, according to one or more mode control signal that also serves as a configuration control signal. The mode control signal is also used to partition clusters of the execution slices within the processor core according to whether single-threaded or multi-threaded operation is selected, and additionally according to a number of hardware threads that are active.

Disclosed herein are embodiments of an automated manufacturing system that is used to process multiple jobs in a product fabrication environment, where such processing comprises performing the same multiple consecutive process steps for each job and where each process step can be accomplished using one or more different available processing tools. The manufacturing system incorporates a unique run-time dispatch system. This dispatch system schedules the order in which jobs will be processed and further randomly assigns a particular combination of process steps and tools to each job in such a way that the processing tools are evenly distributed across the jobs. Ensuring even distribution of processing tools allows a statistical process control system to not only detect, for a given process step, product variability outside desired specifications, but also to efficiently de-convolve such product variability.

The present invention discloses a computer programmable autocontrol system and a control method thereof, where the system includes an application layer, a real-time dispatch layer and a real-time control layer, wherein the application layer is used for developing and coding programs, to implement remote communication and network man-machine interface interactive function; the real-time dispatch layer is used for real-time operation of programs of the application layer, and real-time dispatch of an operating instruction on the real-time control layer, to thereby operate hardware; the real-timecontrol layer is used for execution of the operating instruction, so as to complete control operation. According to the invention, a system platform with uniform combination of software and hardware is used, to integrate control modes, such as a PLC control mode, a machine-man control mode and so on into one system, which supplies functions such as logic, motion and processing; with this system, a user can upgrade or convert the control mode more flexibly and openly.

The invention relates to a method for monitoring and selectively recording the dispatching desks of a digital colony system, in particular to a method for monitoring and recording the dispatching desks of the digital colony system. The method provided by the invention is used for accessing the broadband wireless multimedia information and solves the defect that the hardware resources of the dispatching desks are wasted when the existing dispatching desks record the whole conversation monitoring course. The device for realizing the method comprises one to multiple dispatching desks, a colony dispatching server and multiple user terminals, wherein the dispatching desks for monitoring transmit monitoring request signaling to the colony dispatching server; the colony dispatching server transmits the voice data of a monitored user to the dispatching desks for monitoring; the dispatching desks for monitoring carry out the operation of starting the recording or stopping the recording; and after the monitoring ends, the data base of the dispatching desks for monitoring records the ending time of the conversation, records the conversation time and stores recoding files.

An embodiment of the invention provides an ability to configure the dispatch policy in an application or transaction server. For servlets and JSP's this is configured on a per-URL (Uniform Resource Locator) basis, RMI and EJB it is configured on a per-method basis. Available dispatch options include the ability to execute the request in the same thread that read the request or to enqueue it on a queue which feeds a pool of worker threads. Using this configuration one can control various quality of service parameters of the requests. Requests may be expedited by executing them directly in the thread which read them, thus skipping the queue. Alternatively, some requests may be throttled by assigning them to a queue which is tended by only a limited number of threads.