Abstract: A computer-implemented method optimizes a neural network. One or more processors define layers in a neural network based on neuron locations relative to incoming initial inputs and original outgoing final outputs of the neural network, where a first defined layer is closer to the incoming initial inputs than a second defined layer, and where the second defined layer is closer to the original outgoing final outputs than the first defined layer. The processor(s) define parameter criticalities for parameter weights stored in a memory used by the neural network, and associate defined layers in the neural network with different memory banks based on the parameter criticalities for the parameter weights. The processor(s) store parameter weights used by neurons in the first defined layer in the first memory bank and parameter weights used by neurons in the second defined layer in the second memory bank.

Abstract: Embodiments of the present invention include a system, computer-implemented method, and a computer program product. A non-limiting example of the method includes a processor utilizing a model having a plurality of parameters. The processor compares a current value of a model parameter to a prior value of the model parameter. Based at least in part on comparing the current value of the model parameter to the prior value of the model parameter, a determination is made that the model being utilized by the processor has changed. The current value of the model parameter is transmitted by the processor.

Abstract: An aspect includes optimizing an application workflow. The optimizing includes characterizing the application workflow by determining at least one baseline metric related to an operational control knob of an embedded system processor. The application workflow performs a real-time computational task encountered by at least one mobile embedded system of a wirelessly connected cluster of systems supported by a server system. The optimizing of the application workflow further includes performing an optimization operation on the at least one baseline metric of the application workflow while satisfying at least one runtime constraint. An annotated workflow that is the result of performing the optimization operation is output.

Abstract: A computer program product includes a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to perform a method that includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations. A second base station may be selected, by the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: A central processing unit system includes: a pipeline configured to receive an instruction; and a register file partitioned into one or more subarrays where (i) the register file includes one or more computation elements and (ii) the one or more computation elements are directly connected to one or more subarrays.

Abstract: A computer-implemented method includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations, where each base station is configured to provide connections to a plurality of mobile devices. Responsive to the first base station being overloaded, a second base station may be selected, by a computer processor of the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: A computer-implemented method optimizes a neural network. One or more processors define layers in a neural network based on neuron locations relative to incoming initial inputs and original outgoing final outputs of the neural network, where a first defined layer is closer to the incoming initial inputs than a second defined layer, and where the second defined layer is closer to the original outgoing final outputs than the first defined layer. The processor(s) define parameter criticalities for parameter weights stored in a memory used by the neural network, and associate defined layers in the neural network with different memory banks based on the parameter criticalities for the parameter weights. The processor(s) store parameter weights used by neurons in the first defined layer in the first memory bank and parameter weights used by neurons in the second defined layer in the second memory bank.

Abstract: Embodiments of the present invention include a system, computer-implemented method, and a computer program product. A non-limiting example of the method includes a processor utilizing a model having a plurality of parameters. The processor compares a current value of a model parameter to a prior value of the model parameter. Based at least in part on comparing the current value of the model parameter to the prior value of the model parameter, a determination is made that the model being utilized by the processor has changed. The current value of the model parameter is transmitted by the processor.

Abstract: A computer-implemented method includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations, where each base station is configured to provide connections to a plurality of mobile devices. Responsive to the first base station being overloaded, a second base station may be selected, by a computer processor of the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: A computer program product includes a computer readable storage medium having program instructions embodied therewith. The program instructions are executable by a processor to cause the processor to perform a method that includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations. A second base station may be selected, by the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: Embodiments relate to clustering execution in a processing system. An aspect includes accessing a control flow graph that defines a data dependency and an execution sequence of a plurality of tasks of an application that executes on a plurality of system components. The execution sequence of the tasks in the control flow graph is modified as a clustered control flow graph that clusters active and idle phases of a system component while maintaining the data dependency. The clustered control flow graph is sent to an operating system, where the operating system utilizes the clustered control flow graph for scheduling the tasks.

Abstract: Embodiments relate to clustering execution in a processing system. An aspect includes accessing a control flow graph that defines a data dependency and an execution sequence of a plurality of tasks of an application that executes on a plurality of system components. The execution sequence of the tasks in the control flow graph is modified as a clustered control flow graph that clusters active and idle phases of a system component while maintaining the data dependency. The clustered control flow graph is sent to an operating system, where the operating system utilizes the clustered control flow graph for scheduling the tasks.

Abstract: An aspect includes optimizing an application workflow. The optimizing includes characterizing the application workflow by determining at least one baseline metric related to an operational control knob of an embedded system processor. The application workflow performs a real-time computational task encountered by at least one mobile embedded system of a wirelessly connected cluster of systems supported by a server system. The optimizing of the application workflow further includes performing an optimization operation on the at least one baseline metric of the application workflow while satisfying at least one runtime constraint. An annotated workflow that is the result of performing the optimization operation is output.

Abstract: Embodiments relate to storing data in memory. An aspect includes applying a power savings technique to at least a subset of a processor. Pending work items scheduled to be executed by the processor are monitored. The pending work items are grouped based on the power savings technique. The grouping includes delaying a scheduled execution time of at least one of the pending work items to increase an overall number of clock cycles that the power savings technique is applied to the processor. It is determined that an execution criteria has been met. The pending work items are executed based on the execution criteria being met and the grouping.

Abstract: Embodiments relate to storing data in memory. An aspect includes applying a power savings technique to at least a subset of a processor. Pending work items scheduled to be executed by the processor are monitored. The pending work items are grouped based on the power savings technique. The grouping includes delaying a scheduled execution time of at least one of the pending work items to increase an overall number of clock cycles that the power savings technique is applied to the processor. It is determined that an execution criteria has been met. The pending work items are executed based on the execution criteria being met and the grouping.

Abstract: A computer-implemented method includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations, where each base station is configured to provide connections to a plurality of mobile devices. Responsive to the first base station being overloaded, a second base station may be selected, by a computer processor of the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: A computer-implemented method includes determining, by a first base station, that the first base station is overloaded with connections from mobile devices. Responsive to the first base station being overloaded, a status update may be received, by the first base station, from each of a plurality of base stations, where each base station is configured to provide connections to a plurality of mobile devices. Responsive to the first base station being overloaded, a second base station may be selected, by a computer processor of the first base station, from among the plurality of base stations. Responsive to the first base station being overloaded, the second base station may be instructed, by the first base station, to relocate from a first position to a new position closer to the first base station. The plurality of base stations automatically relocate to load-balance connections from the plurality of mobile devices.

Abstract: An aspect includes optimizing an application workflow. The optimizing includes characterizing the application workflow by determining at least one baseline metric related to an operational control knob of an embedded system processor. The application workflow performs a real-time computational task encountered by at least one mobile embedded system of a wirelessly connected cluster of systems supported by a server system. The optimizing of the application workflow further includes performing an optimization operation on the at least one baseline metric of the application workflow while satisfying at least one runtime constraint. An annotated workflow that is the result of performing the optimization operation is output.

Abstract: Embodiments relate to clustering execution in a processing system. An aspect includes accessing a control flow graph that defines a data dependency and an execution sequence of a plurality of tasks of an application that executes on a plurality of system components. The execution sequence of the tasks in the control flow graph is modified as a clustered control flow graph that clusters active and idle phases of a system component while maintaining the data dependency. The clustered control flow graph is sent to an operating system, where the operating system utilizes the clustered control flow graph for scheduling the tasks.

Abstract: Embodiments relate to clustering execution in a processing system. An aspect includes accessing a control flow graph that defines a data dependency and an execution sequence of a plurality of tasks of an application that executes on a plurality of system components. The execution sequence of the tasks in the control flow graph is modified as a clustered control flow graph that clusters active and idle phases of a system component while maintaining the data dependency. The clustered control flow graph is sent to an operating system, where the operating system utilizes the clustered control flow graph for scheduling the tasks.