Qualcomm Incorporated

Jeffrey Gemar

Matthew Levi Severson

Vijayakumar Ashok Dibbad

Wei Yu Chen

Bohuslav Rychlik

Stephen A Molloy

George Patsilaras

Dipti Ranjan Pal

Boris Andreev

Tauseef Kazi

Vinod Chamarty

Aravind Bhaskara

Olivier Alavoine

Simon Booth

Mohammad Tamjidi

Tao Shen

Edoardo Regini

Yucong Tao

Wenbiao Wang

Renatas Jakushokas

Sejoong Lee

Engin Ipek

Saurabh Patodia

Chang Yong Yang

Prajakt Kulkarni

Ramaprasath Vilangudipitchai

Andrew Edmund Turner

Rajat Mittal

Ronald Alton

Ali Taha

Haw-Jing Lo

Suresh Sugumar

Rexford Alan Hill

Michael Hawjing Lo

Shih-Hsin Jason Hu

Jason Edward Podaima

Madan Krishnappa

Lipeng Cao

Kyle Ernewein

Abinash Roy

Amy Derbyshire

Philippe Martin

Tao Xue

Mahadevamurty Nemani

Haoping Xu

Lai Xu

Francisco Perez

John Daniels

Nikhil Ashok Bhelave

Hamza Omar

Goran Goran

Can Hankendi

Fahad Ali

Ambudhar Tripathi

Mark Kempfert

Noman Ahmed

Alex Miler

Methods for thermal cooling implemented by a processor of a thermal cooling system may include receiving a power profile input associated with a power consuming unit cooled by a coolant within the thermal cooling system, estimating a peak Tj of the power consuming unit during an upcoming interval based on the power profile input, a coolant temperature regulation point, and a coolant flow rate, and changing at least one of the coolant temperature regulation point or the coolant flow rate in response to the estimated peak Tj varying from a predesignated Tj limit by a predetermined threshold.

Thermal cooling regulation based on power profile

Power limiting in a processor-based system based on allocating power budgets for different sub-systems based on multiple time-based power limits is disclosed. The processor-based system has multiple power consuming sub-systems (e.g., non-processing unit (PU) and PU sub-systems) that demand and consume power from a power source of the processor-based system. To limit overall power consumption of the processor-based system over different time-based power limits, the processor-based system includes a power limiter circuit. The power limiter circuit is configured to manage multiple, different time-based (e.g., time constant) power limits for the processor-based system and to allocate corresponding power limit budgets to constrain power consumption of different sub-systems based on the multiple time-based power limits. The power limiter circuit can be configured to constrain power consumption of a PU sub-system to a total PU sub-system power limit budget based on the multiple time-based power limits.

Power limiting in a processor-based system based on allocating power budgets for different sub-systems based on multiple time-based power limits

Various embodiments include methods performed by a processor for managing voltage droop margins of a power distribution network (PDN). Various embodiments may include receiving, by a processor from a first client powered by a shared power rail within the PDN, a first requested performance corner, receiving, by the processor from a second client powered by the shared power rail, a second requested performance corner, determining by the processor a first peak current value based on the first requested performance corner, determining by the processor a second peak current value based on the second requested performance corner, determining by the processor a system voltage droop margin based on the first peak current value, the second peak current value, and an impedance value of the PDN, and adjusting a voltage of the shared power rail based on the system voltage droop margin.

Energy efficient Vmin architecture for shared power rails

Providing content-aware cache replacement and insertion policies in processor-based devices is disclosed. In some aspects, a processor-based device comprises a cache memory device and a cache controller circuit of the cache memory device. The cache controller circuit is configured to determine a plurality of content costs for each of a plurality of cached data values in the cache memory device, based on a plurality of bit values of each of the plurality of cached data values. The cache controller circuit is configured to identify, based on the plurality of content costs, a cached data value of the plurality of cached data values associated with a lowest content cost as a target cached data value. The cache controller circuit is also configured to evict the target cached data value from the cache memory device.

Providing content-aware cache replacement and insertion policies in processor-based devices

The energy consumed by data transfer in a computing device may be reduced by transferring data that has been encoded in a manner that reduces the number of one '1' data values, the number of signal level transitions, or both. A data destination component of the computing device may receive data encoded in such a manner from a data source component of the computing device over a data communication interconnect, such as an off-chip interconnect. The data may be encoded using minimum Hamming weight encoding, which reduces the number of one '1' data values. The received data may be decoded using minimum Hamming weight decoding. For other computing devices, the data may be encoded using maximum Hamming weight encoding, which increases the number of one &#x201c;1&#x201d; data values while reducing the number of zero &#x201c;0&#x201d; values, if reducing the number of zero values reduces energy consumption.

Data re-encoding for energy-efficient data transfer in a computing device

In some aspects, the present disclosure provides a method for power management. The method includes receiving, by a power management unit (PMU), signaling indicative of a first plurality of latency durations from a first plurality of clients, each of the first plurality of latency durations corresponding to one of the first plurality of clients, wherein each of the first plurality of clients is configured to utilize a first shared resource for communication of data. In certain aspects, the method also includes selecting, by the PMU, a first latency duration from the first plurality of latency durations based on a determination that the first latency duration is the shortest latency duration of the first plurality of latency durations, and transitioning, by the PMU, the first shared resource from an active state to the first idle state.

Active power management

Systems and methods are disclosed method for controlling instantaneous current changes in parallel processors with arrays of parallel computing elements, such as neural processors. An exemplary method comprises monitoring the array of computing elements and determining a transition from a first activity level of the array to a second activity level of the array, such as an idle-to-active or active-to-idle transition. Once a transition is determined, the array is selectively controlled to minimize the instantaneous current change from the transition from the first activity level to the second activity level.

Systems and methods for controlling instantaneous current changes in parallel processors

In certain aspects, an apparatus includes a first power chain, a second power chain, and an enable circuit having an output coupled to an input of the first power chain. The apparatus also includes a multiplexer having a first input coupled to an output of the first power chain, a second input coupled to the output of the enable circuit, and an output coupled to an input of the second power chain, wherein the multiplexer is configured to receive a select signal, and couple the first input or the second input to the output of the multiplexer based on the select signal.

Dynamic power switch control scheme

Various aspects include methods for managing memory subsystems on a computing device. Various aspect methods may include determining a period of time to force a memory subsystem on the computing device into a low power mode, inhibiting memory access requests to the memory subsystem during the determined period of time, forcing the memory subsystem into the low power mode for the determined period of time, and executing the memory access requests to the memory subsystem inhibited during the determined period of time in response to expiration of the determined period of time.

Forced idling of memory subsystems

An apparatus includes a first circuit and a second circuit sharing an instruction stream. A voltage controller circuit is configured to provide an operation voltage and at least one low-power voltage to the second circuit independent of a supply voltage of the first circuit in response to a sequence of the instruction stream. In another aspect, a method of operating a power management function is presented. The method includes providing an instruction stream for a first circuit and a second circuit and providing selectively an operation voltage and at least one low-power voltage to the second circuit independent of a supply voltage of the first circuit in response to a sequence of the instruction stream.

Processor power management responsive to a sequence of an instruction stream

Data retention circuitry, such as at least one integrated circuit (IC), is disclosed herein for power multiplexing with flip-flops having a retention feature. In an example aspect, an IC includes a first power rail and a second power rail. The IC further includes a flip-flop and power multiplexing circuitry. The flip flop includes a master portion and a slave portion. The master portion is coupled to the first power rail for a regular operational mode and for a retention operational mode. The power multiplexing circuitry is configured to couple the slave portion to the first power rail for the regular operational mode and to the second power rail for the retention operational mode.

Power multiplexing with flip-flops

A method for operating an electronic apparatus is provided. The method includes receiving a token, activating a power switch for powering up a core in response to the receiving the token, and outputting the token based on a state of powering up the core. The outputting of the received token is delayed until the state of powering up the core is reached. In one aspect, an electronic apparatus includes a power switch configured to power up to a core is provided. A power-switch control circuit is configured to receive a token, activate the power switch for powering up the core in response to receiving the token, output the received token based on a state of powering up the core. The outputting of the received token is delayed until the state of powering up the core is reached. A plurality of the power-switch control circuits is configured as a ring.

Token-based power-switch control circuits

Provided are apparatus and methods for testing an integrated circuit. In an exemplary method for testing an integrated circuit, a test controller and a power manager are integrated into a main power domain of the integrated circuit. The test controller can be Joint Test Action Group-compatible. An isolation signal is generated using the power manager. The isolation signal can comprise at least one of a freeze signal configured to isolate an input-output port of the integrated circuit, and a clamp signal configured to isolate a functional module of the integrated circuit. The isolation signal can be stored in a boundary scan register controlled with the test controller. The main power domain is isolated from a power-collapsible domain of the integrated circuit with the isolation signal. Power of the power-collapsible domain is collapsed. When power is collapsed, the power-collapsible domain is tested using the test controller and the power manager. The testing of the power-collapsible domain can comprise testing a power supply current. When power to the power-collapsible domain is collapsed, a level shifter output can be held constant to an output level based on a pre-collapse input from the power-collapsible domain.

Integrated circuit testing with power collapsed

In examples, apparatus and methods are provided for an integrated circuit. The integrated circuit includes a first integrated circuit portion having a main power domain and a second integrated circuit portion having a collapsible power domain. The integrated circuit also has a level shifter having an input coupled to the second circuit portion and an output coupled to the first integrated circuit portion. The level shifter is configured to hold constant the level shifter output when power to the collapsible power domain is collapsed. A quiescent drain current measurement circuit can be coupled to test at least a part of the second integrated circuit portion. A boundary scan register can be coupled between the level shifter output and the first integrated circuit portion. The integrated circuit can also include a power management circuit.

Growing community of inventors

San Diego, CA, United States of America

Jeffrey Gemar