Abstract: Described is a controller that provides in-situ state retention using a closed loop global retention clamp. The controller addresses di/dt and reliability constraints using an adaptive scheme where steps with smaller current are quickly changed whereas steps with larger current are changed slowly. The loop controller of a voltage regulator is modified for controlling not only retention Vmin during a low power state (e.g., C1LP), but also to control fast wake up the low power state (e.g., from C1LP and from C6).

Abstract: Prior knowledge of access pattern is leveraged to improve energy dissipation for general matrix operations. This improves memory access energy for a multitude of applications such as image processing, deep neural networks, and scientific computing workloads, for example. In some embodiments, prior knowledge of access pattern allows for burst read and/or write operations. As such, burst mode solution can provide energy savings in both READ (RD) and WRITE (WR) operations. For machine learning or inference, the weight values are known ahead in time (e.g., inference operation), and so the unused bytes in the cache line are exploited to store a sparsity map that is used for disabling read from either upper or lower half of the cache line, thus saving dynamic capacitance.

Abstract: A controller of a processor core may select telemetry data generated by a plurality of sensors of the processor core at a first time interval of a plurality of time intervals. The controller may transform the telemetry data based at least in part on a model. The controller may detect a change at the first time interval based on the transformed telemetry data. The controller may determine an event based on the change. The controller may initiate an action during the first time interval based on the event.

Abstract: A distributed and scalable all-digital LDO (D-DLDO) voltage regulator allowing rapid scaling across technology nodes. The distributed DLDO includes many tillable DLDO units regulating a single supply voltage with a shared power distribution network (PDN). The D-DLDO includes an all-digital proportional-integral-derivative (PID) controller that receives a first code indicative of a voltage behavior on a power supply rail. A droop detector is provided to compare the first code with a threshold to determine a droop event, wherein information about the droop event is provided to the PID controller, wherein the PID controller generates a second code according to the first code and the information about the droop event. The DLDO includes a plurality of power gates that receive the second code.

Abstract: Described is a level-shifter that can save area between voltage domains with limited voltage differential, and further save power by steering current between two power supply rails. The level-shifter comprises: an input to receive a first signal between a first reference rail and a second reference rail; an output to provide a second signal the first reference rail and a third reference rail, wherein in a voltage level of the third reference rail is higher than a voltage level of the second reference rail, and wherein a voltage level of the first reference is lower than the voltage level of the second reference rail and the third reference rail; and a circuitry coupled to the input and the output, wherein the circuitry is to steer current from the third reference rail to the second reference rail.

Abstract: An apparatus is provided which comprises: a plurality of devices coupled to an input power supply rail and an output power supply rail; a first circuitry coupled to the plurality of devices, wherein the first circuitry is to turn on or off one or more devices of the plurality according to a control; and a second circuitry coupled to the first circuitry, wherein the second circuitry comprises an all-digital proportional-derivative mechanism to generate the control according to a digital representation of voltage on the output power supply rail.

Abstract: Described is a controller that provides in-situ state retention using a closed loop global retention clamp. The controller addresses di/dt and reliability constraints using an adaptive scheme where steps with smaller current are quickly changed whereas steps with larger current are changed slowly. The loop controller of a voltage regulator is modified for controlling not only retention Vmin during a low power state (e.g., C1LP), but also to control fast wake up the low power state (e.g., from C1LP and from C6).

Abstract: A detection circuit includes a tunable delay circuit that generates a delayed signal and that receives a supply voltage. The detection circuit includes a control circuit that adjusts a delay provided by the tunable delay circuit to the delayed signal. The detection circuit includes a time-to-digital converter circuit that converts the delay provided by the tunable delay circuit to the delayed signal to a digital code and adjusts the digital code based on changes in the supply voltage. The control circuit causes the tunable delay circuit to maintain the delay provided to the delayed signal constant in response to the digital code reaching an alignment value. The detection circuit may continuously monitor timing margin of a data signal relative to a clock signal and update the digital code in every clock cycle. The detection circuit may be a security sensor that detects changes in the supply voltage.

Abstract: An all-digital voltage monitor (ADVM) generates a multi-bit output code that changes in proportion to a voltage being monitored, by leveraging the voltage impact on a gate delay. ADVM utilizes a simple delay chain, which receives a clock-cycle-long pulse every clock cycle, such that the monitored supply voltage is sampled for one full cycle every cycle. The outputs of all delay cells of the delay chain collectively represents a current voltage state as a digital thermometer code. In AVDM, a voltage droop event thus results in a decrease in the output code from a nominal value, while an overshoot results in an increase in the output code.

Abstract: Systems, apparatuses and methods include technology that determines, with a first processing engine of a plurality of processing engines, a first partial similarity measurement based on a first portion of a query vector and a first portion of a first candidate vector. The technology determines, with a second processing engine of the plurality of processing engines, a total similarity measurement based on the query vector and a second candidate vector. The technology determines, with the first processing engine, whether to compare a second portion of the query vector to a second portion of the first candidate vector based on the first partial similarity measurement and the total similarity measurement.

Abstract: An all-digital voltage monitor (ADVM) generates a multi-bit output code that changes in proportion to a voltage being monitored, by leveraging the voltage impact on a gate delay. ADVM utilizes a simple delay chain, which receives a clock-cycle-long pulse every clock cycle, such that the monitored supply voltage is sampled for one full cycle every cycle. The outputs of all delay cells of the delay chain collectively represents a current voltage state as a digital thermometer code. In AVDM, a voltage droop event thus results in a decrease in the output code from a nominal value, while an overshoot results in an increase in the output code.

Abstract: A distributed and scalable all-digital LDO (D-DLDO) voltage regulator allowing rapid scaling across technology nodes. The distributed DLDO includes many tillable DLDO units regulating a single supply voltage with a shared power distribution network (PDN). The D-DLDO includes an all-digital proportional-integral-derivative (PID) controller that receives a first code indicative of a voltage behavior on a power supply rail. A droop detector is provided to compare the first code with a threshold to determine a droop event, wherein information about the droop event is provided to the PID controller, wherein the PID controller generates a second code according to the first code and the information about the droop event. The DLDO includes a plurality of power gates that receive the second code.

Abstract: Prior knowledge of access pattern is leveraged to improve energy dissipation for general matrix operations. This improves memory access energy for a multitude of applications such as image processing, deep neural networks, and scientific computing workloads, for example. In some embodiments, prior knowledge of access pattern allows for burst read and/or write operations. As such, burst mode solution can provide energy savings in both READ (RD) and WRITE (WR) operations. For machine learning or inference, the weight values are known ahead in time (e.g., inference operation), and so the unused bytes in the cache line are exploited to store a sparsity map that is used for disabling read from either upper or lower half of the cache line, thus saving dynamic capacitance.

Abstract: An apparatus is provided which comprises: a first device coupled to a first power supply rail; a second device coupled in series with the first device, wherein the second device is coupled to a second power supply rail; and a third device coupled to the first and second power supply rails, wherein the first device is controllable by a first input, wherein the second device is controllable by a second input, wherein the third device is controllable by a third input, and wherein the first input is an analog bias between a high power supply level and a ground supply level.

Abstract: Described is a level-shifter that can save area between voltage domains with limited voltage differential, and further save power by steering current between two power supply rails. The level-shifter comprises: an input to receive a first signal between a first reference rail and a second reference rail; an output to provide a second signal the first reference rail and a third reference rail, wherein in a voltage level of the third reference rail is higher than a voltage level of the second reference rail, and wherein a voltage level of the first reference is lower than the voltage level of the second reference rail and the third reference rail; and a circuitry coupled to the input and the output, wherein the circuitry is to steer current from the third reference rail to the second reference rail.

Abstract: A minimum delay error apparatus such as a minimum delay error detection, prediction, correction, repair, prevention, and/or avoidance apparatus includes a minimum delay path replica circuit. The minimum delay path replica circuit can detect or predict, and subsequently can correct or avoid, minimum delay errors in data paths of digital circuits using pulsed latches.

Abstract: An all-digital voltage monitor (ADVM) generates a multi-bit output code that changes in proportion to a voltage being monitored, by leveraging the voltage impact on a gate delay. ADVM utilizes a simple delay chain, which receives a clock-cycle-long pulse every clock cycle, such that the monitored supply voltage is sampled for one full cycle every cycle. The outputs of all delay cells of the delay chain collectively represents a current voltage state as a digital thermometer code. In AVDM, a voltage droop event thus results in a decrease in the output code from a nominal value, while an overshoot results in an increase in the output code.

Abstract: Described is a level-shifter that can save area between voltage domains with limited voltage differential, and further save power by steering current between two power supply rails. The level-shifter comprises: an input to receive a first signal between a first reference rail and a second reference rail; an output to provide a second signal the first reference rail and a third reference rail, wherein in a voltage level of the third reference rail is higher than a voltage level of the second reference rail, and wherein a voltage level of the first reference is lower than the voltage level of the second reference rail and the third reference rail; and a circuitry coupled to the input and the output, wherein the circuitry is to steer current from the third reference rail to the second reference rail.

Abstract: A system, article, and method provide temporal-domain feature extraction for automatic speech recognition.

Abstract: An apparatus is provided which comprises: a plurality of devices coupled to an input power supply rail and an output power supply rail; a first circuitry coupled to the plurality of devices, wherein the first circuitry is to turn on or off one or more devices of the plurality according to a control; and a second circuitry coupled to the first circuitry, wherein the second circuitry comprises an all-digital proportional-derivative mechanism to generate the control according to a digital representation of voltage on the output power supply rail.