A system and method for providing a digital real-time voltage droop detection and subsequent voltage droop reduction. A scheduler within a reservation station may store a weight value for each instruction corresponding to node capacitance switching activity for the instruction derived from pre-silicon power modeling analysis. For instructions picked with available source data, the corresponding weight values are summed together to produce a local current consumption value and this value is summed with any existing global current consumption values from corresponding schedulers of other processor cores yielding an activity event. The activity event is stored. Hashing functions within the scheduler are used to determine both a recent and an old activity average using the calculated activity event and stored older activity events. Instruction issue throttling occurs if either a difference between the old activity average and the recent activity average exceed a first threshold or the recent activity average exceeds a second threshold.

Voltage droop mitigation through instruction issue throttling

A system and method for efficient power transfer on a die. A semiconductor chip comprises on a die two or more computation units (CUs) utilizing at least two different voltage regulators and a power manager. The power manager reallocates power credits across the die when it detects an activity level of a given CU is below a given threshold. In response to receiving a corresponding number of donated power credits, each of the one or more selected CUs maintains a high activity level with a high performance P-state. When a corresponding workload increases, each CU maintains operation and an average power consumption corresponding to the high performance P-state by alternating between at least two different operational voltages. When the operational voltage drops during the alternation, the current drawn by the particular CU may exceed a given current limit. The power manager detects this current limit is exceeded and accordingly reallocates the power credits across the die.

Managing current and power in a computing system

A system and method for real-time power estimation. A core may be divided into units. Each unit is simulated to achieve a real power consumption characterization. The power consumption is sampled. Statistical analysis is performed that assumes the core has node capacitance switching behavior that is approximated by a stationary random process with a Poisson distribution. The statistical analysis determines the number of samples to take during a sample interval. The operational frequency, sample interval, and number of samples are used to determine the number of signals to sample. Signals are chosen that have a high correlation with the node capacitance switching behavior, such as clock enable signals on the last stage of a clock distribution system. Weights with tuned values are assigned to each sampled signal. Sampling occurs during every predetermined number of clock cycles. The weights of asserted sampled signals are summed in order to determine a repeatable power estimation value.

Sampling chip activity for real time power estimation

A computing system is associated with power consumption based on Power over Ethernet (PoE). Power consumption is compared to a threshold, and a signal is asserted that power consumption is to be limited based on the comparison to the threshold.

Power consumption limit associated with power over ethernet (poe) computing system

A system and method for efficient management of resources within a semiconductor chip for an optimal combination of power reduction and high performance. An intergrated circuit, such as a system on a chip (SOC), includes at least two processing units. The second processing unit includes a cache. The SOC includes a power management unit (PMU) that determines whether a first activity level for the first processing unit is above a first threshold and a second activity level for the second processing unit is below a second threshold. If this condition is true, then the PMU places a limit on a highest power-performance state (P-state) used by the second processing unit. The PMU sends an indication to flush the at least one cache within the second processing unit. The PMU changes a P-state used by the first processing unit to a higher performance P-state.

Method for soc performance and power optimization

A flip-flop circuit includes a differential stage coupled to a latch stage. The differential stage comprises cross-coupled dynamic logic and only provides a single output to the latch stage. During an evaluation phase, the state of a data input signal is sensed. Depending upon the state of the data input signal, either an output side or reference side of the differential stage is discharged. Also, during the evaluation phase, the latch stage write port is enabled while feedback is disabled, and the flip flop thereby samples and stores an output signal from the output side of the differential stage. Upon initiation of the next precharge phase, the latch stage write port is disabled and feedback is enabled, thereby retaining its present state. Only a single side of the differential stage is used to drive the latch stage and the differential stage may be implemented in an asymmetric fashion.

Asymmetric precharged flip flop

A processor ( 400 ) includes a clock source ( 402 ), a central processing unit (CPU) ( 408 ), and a clock generator ( 404 ). The clock source ( 402 ) includes an output for providing a periodic clock signal. The CPU ( 408 ) includes an input for receiving a CPU clock signal. The clock generator ( 404 ) includes a first input coupled to the output of the clock source ( 402 ), a second input for receiving a mode signal that indicates an output frequency, and an output coupled to the input of the CPU ( 408 ). The clock generator ( 404 ) provides the CPU clock signal using periodic pulse skipping such that the CPU clock signal has a number of transitions over a unit of time corresponding to the output frequency.

Techniques for integrated circuit clock management using pulse skipping

A compound logic flip-flop. The flip-flop includes a plurality of input stages, wherein each of the input stages is coupled to receive at least one input signal and a clock signal. Each of the plurality of input (i.e. ‘master’) stages is configured to perform a corresponding input logic function during a first phase of a clock cycle and to store a result of the corresponding input logic function. The flip-flop further includes an output (i.e. ‘slave’) stage coupled to receive the clock signal and the results of the input logic functions from each of the plurality of input stages. The output stage is configured, during a second phase of the clock cycle, to logically combine the results of the input logic functions by performing an output logic function and provide an output signal based on a result of the output logic function.

Compound logic flip-flop having a plurality of input stages

An integrated circuit ( 1600 ) includes a debug module ( 1602 ) and a clock generator ( 1610 ). The debug module ( 1602 ) is configured to receive a test pattern and provide a mode signal based on the test pattern. The clock generator ( 1610 ) includes a first clock input configured to receive a first clock signal, a second clock input configured to receive a second clock signal, and a mode input configured to receive the mode signal. The first and second clock signals are out of phase and have the same clock frequency. The clock generator ( 1610 ) is configured to provide a generated clock signal whose effective frequency is based on the first and second clock signals and the mode signal.

Techniques for integrated circuit clock signal manipulation to facilitate functional and speed test

A semiconductor device includes a primary voltage rail, a secondary voltage rail, a plurality of transistors coupled between the primary and secondary voltage rails, and control logic operable to enable a first subset of the plurality of transistors to couple the primary voltage rail to the secondary voltage rail. During a steady state condition, the first subset comprises less than all of the plurality of transistors.

Daniel W. Bailey

Papers

Asymmetric precharged flip flop

Techniques for integrated circuit clock management using pulse skipping

Compound logic flip-flop having a plurality of input stages

Techniques for integrated circuit clock signal manipulation to facilitate functional and speed test

Variable-width power gating module