Abstract:
A mechanism is provided for scheduling application tasks. A scheduler receives a task that identifies a desired frequency and a desired maximum number of competing hardware threads. The scheduler determines whether a user preference designates either maximization of performance or minimization of energy consumption. Responsive to the user preference designating the performance, the scheduler determines whether there is an idle processor core in a plurality of processor cores available. Responsive to no idle processor being available, the scheduler identifies a subset of processor cores having a smallest load coefficient. From the subset of processor cores, the scheduler determines whether there is at least one processor core that matches desired parameters of the task. Responsive to at least one processor core matching the desired parameters of the task, the scheduler assigns the task to one of the at least one processor core that matches the desired parameters.
Abstract:
Ein Verfahren, ein System und ein Computerprogrammprodukt zum Verbessern der Leistungsfähigkeit einer digitalen Schaltung werden in den veranschaulichenden Ausführungsformen bereitgestellt. Eine tatsächliche Arbeitsfrequenz der digitalen Schaltung wird mithilfe einer Regelschleife in der digitalen Schaltung angepasst, wobei das Anpassen der tatsächlichen Frequenz als Reaktion auf eine Änderung bei einem Betriebszustand der digitalen Schaltung erfolgt. Eine Messung eines durch die digitale Schaltung aufgenommenen Stroms wird von einem Spannungsregler empfangen, welcher der digitalen Schaltung elektrische Leistung bereitstellt. Ein Überstrom-Zielstromwert wird empfangen. Eine Spannungsabgabe vom Spannungsregler an die digitale Schaltung wird so angepasst, dass der durch die digitale Schaltung aufgenommene Strom den Überstrom-Zielstromwert nicht überschreitet.
Abstract:
Ein Mechanismus zum Planen von Anwendungsaufgaben wird bereitgestellt. Ein Scheduler empfängt eine Aufgabe, die eine Sollfrequenz und eine maximale Sollzahl von konkurrierenden Hardware-Threads identifiziert. Der Scheduler ermittelt, ob eine Benutzereinstellung entweder eine Maximierung der Leistung oder eine Verringerung des Energieverbrauchs festlegt. Als Reaktion auf die Benutzereinstellung, die die Leistung festlegt, ermittelt der Scheduler, ob ein inaktiver Prozessorkern in einer Vielzahl von Prozessorkernen zur Verfügung steht. Als Reaktion darauf, dass kein inaktiver Prozessor zur Verfügung steht, identifiziert der Scheduler eine Teilmenge von Prozessorkernen, die einen niedrigsten Lastkoeffizienten aufweisen. Der Scheduler ermittelt anhand der Teilmenge von Prozessorkernen, ob mindestens ein Prozessorkern vorhanden ist, der mit den Sollparametern der Aufgabe übereinstimmt. Als Reaktion darauf, dass mindestens ein Prozessorkern mit den Sollparametern der Aufgabe übereinstimmt, weist der Scheduler die Aufgabe einem des mindestens einen Prozessorkerns zu, der mit den Sollparametern übereinstimmt.
Abstract:
A mechanism is provided for scheduling application tasks. A scheduler receives a task that identifies a desired frequency and a desired maximum number of competing hardware threads. The scheduler determines whether a user preference designates either maximization of performance or minimization of energy consumption. Responsive to the user preference designating the performance, the scheduler determines whether there is an idle processor core in a plurality of processor cores available. Responsive to no idle processor being available, the scheduler identifies a subset of processor cores having a smallest load coefficient. From the subset of processor cores, the scheduler determines whether there is at least one processor core that matches desired parameters of the task. Responsive to at least one processor core matching the desired parameters of the task, the scheduler assigns the task to one of the at least one processor core that matches the desired parameters.
Abstract:
A mechanism is provided for scheduling application tasks. A scheduler receives a task that identifies a desired frequency and a desired maximum number of competing hardware threads. The scheduler determines whether a user preference designates either maximization of performance or minimization of energy consumption. Responsive to the user preference designating the performance, the scheduler determines whether there is an idle processor core in a plurality of processor cores available. Responsive to no idle processor being available, the scheduler identifies a subset of processor cores having a smallest load coefficient. From the subset of processor cores, the scheduler determines whether there is at least one processor core that matches desired parameters of the task. Responsive to at least one processor core matching the desired parameters of the task, the scheduler assigns the task to one of the at least one processor core that matches the desired parameters.
Abstract:
A method and computer program product for dynamic power and performance calibration of a data processing system comprises executing a program 804 responsive to detecting an event 802, the program configured to generate data 806 indicative of the systemâ s power-performance characteristics or metrics which are measured under varying conditions of operation. The set of data is used to determine a performance or power limit on an operation of the system under present operation conditions, and a parameter of the system is calibrated 810 to operate the system within the performance limit. The program may cause the system to exhibit a behaviour approximating behaviour evident from initial power-performance data. A power-performance model may be created 808 using the set of data. Calibrating the system may include adjusting a planned workload on the system. The event may be a power-on self test event, a workload configuration event or a system configuration event.
Abstract:
A mechanism is provided for minimizing system power in the data processing system with fast convergence. A current aggregate system power value is determined using a current thermal threshold value. For each potential thermal threshold value in a set of potential thermal threshold values, a determination is made as to whether there is a potential thermal threshold value that results in a potential aggregate system power value that is lower than the current aggregate system power value. Responsive to identifying an optimal potential thermal threshold value from the set of potential thermal threshold values that results in minimum aggregate system power value that is lower than the current aggregate system power value, the optimal potential thermal threshold value is set as a new thermal threshold value.
Abstract:
A method for improving the performance of a digital circuit is provided in the illustrative embodiments. A real frequency of operation of the digital circuit is adjusted using a control loop in the digital circuit, the adjusting the real frequency being responsive to a change in an operating condition of the digital circuit. A measurement of a current drawn by the digital circuit is received from a voltage regulator supplying electrical power to the digital circuit. An over-current target current value is received. A voltage output from the voltage regulator to the digital circuit is adjusted such that the current drawn by the digital circuit does not exceed the over-current target current value.
Abstract:
A method, system, and computer program product for improving the performance of a digital circuit are provided in the illustrative embodiments. A real frequency of operation of the digital circuit is adjusted using a control loop in the digital circuit, the adjusting the real frequency being responsive to a change in an operating condition of the digital circuit. A measurement of a current drawn by the digital circuit is received from a voltage regulator supplying electrical power to the digital circuit. An over-current target current value is received. A voltage output from the voltage regulator to the digital circuit is adjusted such that the current drawn by the digital circuit does not exceed the over-current target current value.
Abstract:
A mechanism is provided for minimizing power consumption for operation of a fixed-frequency processing unit. A number of timeslots are counted in a time window where throttling is engaged to the fixed-frequency processing unit. The number of timeslots where throttling is engaged is divided by a total number of timeslots within the time window, thereby producing a performance loss (PLOSS) value. A determination is made as to whether determining whether the (PLOSS) value associated with the fixed-frequency processing unit is greater than an allowed performance loss (APLOSS) value. Responsive to the PLOSS value being less than or equal to the APLOSS value, a decrease in voltage supplied to the fixed-frequency processing unit is initiated.