WO2022039747A1 - Power ratios for power adjustments - Google Patents

Power ratios for power adjustments Download PDF

Info

Publication number
WO2022039747A1
WO2022039747A1 PCT/US2020/047207 US2020047207W WO2022039747A1 WO 2022039747 A1 WO2022039747 A1 WO 2022039747A1 US 2020047207 W US2020047207 W US 2020047207W WO 2022039747 A1 WO2022039747 A1 WO 2022039747A1
Authority
WO
WIPO (PCT)
Prior art keywords
power
electronic device
thermal environment
power ratio
processor
Prior art date
Application number
PCT/US2020/047207
Other languages
French (fr)
Inventor
Peter Siyuan ZHANG
Fangyong Dai
Lan Wang
Qijun Steve CHEN
Jon Gregory LLOYD
Original Assignee
Hewlett-Packard Development Company, L.P.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hewlett-Packard Development Company, L.P. filed Critical Hewlett-Packard Development Company, L.P.
Priority to PCT/US2020/047207 priority Critical patent/WO2022039747A1/en
Publication of WO2022039747A1 publication Critical patent/WO2022039747A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16Constructional details or arrangements
    • G06F1/20Cooling means
    • G06F1/206Cooling means comprising thermal management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/16Constructional details or arrangements
    • G06F1/20Cooling means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206Monitoring of events, devices or parameters that trigger a change in power modality
    • G06F1/3215Monitoring of peripheral devices
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234Power saving characterised by the action undertaken
    • G06F1/324Power saving characterised by the action undertaken by lowering clock frequency
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234Power saving characterised by the action undertaken
    • G06F1/3296Power saving characterised by the action undertaken by lowering the supply or operating voltage

Definitions

  • FIG. 1 is a block diagram illustrating an example of an electronic device that may be utilized for power adjustment based on a measured power ratio
  • FIG. 2 is a block diagram illustrating another example of an electronic device that may be utilized for power adjustment based on a measured power ratio
  • FIG. 3 is a block diagram illustrating an example of a computer- readable medium for power adjustment based on a measured power ratio
  • FIG. 4 is a flow diagram illustrating an example of a method for power adjustment based on a measured power ratio.
  • An electronic device may be a device that includes electronic circuitry.
  • an electronic device may include integrated circuitry (e.g., transistors, digital logic, semiconductor technology, etc.).
  • Examples of electronic devices include computing devices, laptop computers, desktop computers, smartphones, tablet devices, wireless communication devices, game consoles, smart appliances, printing devices, vehicles with electronic components, aircraft, drones, robots, smart appliances, etc.
  • the examples described herein provide for classifying the thermal environment and/or surroundings of an electronic device based on a ratio of the processor power and the cooling device power of the electronic device.
  • the processor may be central processing unit (CPU) and/or a graphics processing unit (GPU).
  • the cooling device may include an active cooling component (e.g., a fan, refrigerated heat exchanger, liquid cooling pump, etc.) that uses power (e.g., electrical power) to perform cooling of the processor and/or other components of the electronic device.
  • an active cooling component e.g., a fan, refrigerated heat exchanger, liquid cooling pump, etc.
  • the thermal environment classification may be used to adjust a performance parameter of the electronic device.
  • the electronic device may be optimized in response to changes with its surroundings.
  • the performance parameter e.g., processor power limit, cooling device power limit
  • the thermal environment includes conditions external to the electronic device that affect heat transfer from the electronic device.
  • the thermal environment may include external conditions that affect conduction, convection and/or radiation of heat from the electronic device.
  • conditions that may be included in the thermal environment include the surrounding air temperature (also referred to as ambient air temperature or ambient temperature), radiant temperature (e.g., infrared radiation, solar radiation, etc.), air velocity (e.g., ventilation of the electronic device), humidity, and/or contact surface temperature (e.g., temperature of contacting objects, surface temperature).
  • surrounding air temperature also referred to as ambient air temperature or ambient temperature
  • radiant temperature e.g., infrared radiation, solar radiation, etc.
  • air velocity e.g., ventilation of the electronic device
  • humidity e.g., humidity
  • contact surface temperature e.g., temperature of contacting objects, surface temperature
  • the current thermal environment of the electronic device may be characterized based on a measured power ratio of processor power use to cooling device power use. This measured power ratio may be compared to a reference power ratio.
  • the reference power ratio may be a power ratio for the processor and the cooling device of the electronic device determined in a reference thermal environment. For instance, the reference power ratio may be determined by measuring the processor power and cooling device power while the electronic device is in a controlled environment.
  • heat transfer conditions e.g., the air temperature, radiant temperature, humidity, contact surface temperature, etc.
  • the reference thermal environment includes calibrated external conditions that affect heat transfer from the electronic device.
  • a processor power limit when the thermal environment is favorable for heat transfer (e.g., a cold ambient temperature may facilitate heat transfer from the electronic device), a processor power limit may be increased.
  • the processor power limit when there is an unfavorable thermal environment for heat transfer (e.g., a hot ambient temperature may inhibit heat transfer from the electronic device), the processor power limit may be decreased.
  • the power limit for the cooling device may be decreased in a favorable thermal environment and the power limit for the cooling device may be increased in an unfavorable thermal environment to avoid overheating the electronic device.
  • the measured power ratio of processor power and cooling device power may be determined in different thermal environments. This measured ratio may then be compared to a reference power ratio (also referred to as a default power ratio or baseline power ratio) to characterize the current thermal environment of the electronic device.
  • the electronic device may include a power monitor to measure power use (e.g., energy inflow) of the processor and/or cooling device.
  • the power monitor may include circuitry to measure power (e.g., electrical power) supplied to the processor and/or the cooling device.
  • the power monitor may provide power data to the controller.
  • the processor and/or cooling device may provide power data directly to the controller.
  • the power data may be read at a certain frequency (e.g., every 60 seconds) by the controller, which calculates the measured power ratio based on the power data.
  • the controller may compare the measured power ratio with the reference power ratio.
  • the controller may classify the thermal environment of the electronic device based on the measured power data.
  • the controller may trigger a power adjustment based on the current thermal environment classification. For example, if a change in the thermal environment classification is detected, the controller may notify the electronic device of the change or may wait for the next power data measurement cycle for confirmation of the change in the thermal environment classification. Once the electronic device receives a power adjustment command from controller, the electronic device may modify a processor power limit or cooling device power limit setting accordingly to optimize performance of the electronic device.
  • These examples may improve performance of the electronic device beyond a design target. These examples may also enable the electronic device to modify performance of the electronic device if the thermal environment is unfavorable to heat transfer to mitigate overheating.
  • FIG. 1 is a block diagram illustrating an example of an electronic device 102 that may be utilized for power adjustment based on a measured power ratio 110.
  • Examples of the electronic device 102 may include computing devices, laptop computers, desktop computers, smartphones, tablet devices, wireless communication devices, game consoles, smart appliances, printing devices, vehicles with electronic components, aircraft, drones, robots, smart appliances, etc.
  • the electronic device 102 may include a processor 104 and/or a memory (not shown).
  • the processor 104 may be any of a central processing unit (CPU), a semiconductor-based microprocessor, graphics processing unit (GPU), field-programmable gate array (FPGA), an applicationspecific integrated circuit (ASIC), and/or other hardware device suitable for retrieval and execution of instructions stored in the memory.
  • the processor 104 may fetch, decode, and/or execute instructions stored in the memory. While a single processor 104 is shown in FIG. 1 , in other examples, the processor 104 may include multiple processors (e.g., a CPU and a GPU).
  • the memory may be any electronic, magnetic, optical, and/or other physical storage device that contains or stores electronic information (e.g., instructions and/or data).
  • the memory may be, for example, Random Access Memory (RAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), magnetoresistive random-access memory (MRAM), phase change RAM (PCRAM), non-volatile random-access memory (NVRAM), memristor, flash memory, a storage device, and/or an optical disc, etc.
  • the memory may be a non-transitory tangible computer-readable storage medium, where the term “non-transitory” does not encompass transitory propagating signals.
  • the processor 104 may be in electronic communication with the memory.
  • a processor 104 and/or memory of the electronic device 102 may be combined with or separate from a processor (e.g., CPU) and/or memory of a host device.
  • the electronic device 102 may include different sets of memory.
  • the electronic device 102 may store certain information (e.g., instructions executed by the processor 104) in a first memory.
  • the electronic device 102 may store other information (e.g., instructions executed by a controller 108) in a second memory.
  • the electronic device 102 may include a controller 108.
  • the controller 108 may include a semiconductor-based processor (e.g., microprocessor), field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), and/or other hardware device suitable for retrieval and execution of instructions stored in memory.
  • the processor of the controller 108 may fetch, decode, and/or execute instructions stored in memory.
  • the controller 108 may be separate from the processor 104 of the electronic device 102.
  • the controller 108 may be an embedded controller or other discrete controller of the electronic device 102.
  • the controller 108 may be combined with the processor 104.
  • the processor 104 may implement the operations (or a subset of the operations) performed by the controller 108 as described herein.
  • the electronic device 102 may include a cooling device 106.
  • the cooling device 106 may be an active device that uses electrical power to perform cooling of the electronic device 102.
  • Some examples of the cooling device 106 include a fan, a refrigerator (e.g., components of a refrigeration system), a pump for a liquid-cooling, etc.
  • the controller 108 may determine a measured power ratio 110 of processor power to cooling device power.
  • power refers to electrical power provided to or consumed by a component of the electronic device 102. In some examples, power may be measured in watts (W).
  • the processor power may be the amount of electrical power being supplied to and/or consumed by the processor 104.
  • the processor 104 may use 30W.
  • the cooling device power may be the amount of electrical power being supplied to and/or consumed by the cooling device 106.
  • the cooling device 106 may use 10W to remove the heat generated by the processor 104 and/or the other components of the electronic device 102.
  • the thermal capability of the electronic device 102 may change based on the surroundings in which the electronic device 102 is located. These surroundings are referred to as the thermal environment of the electronic device 102.
  • the cooling device 106 may dissipate much more heat in a cold winter environment than a hot summer environment.
  • the cooling device 106 may dissipate more heat in windy outdoor air than in a closed room.
  • the heat removal capability of the cooling device 106 may be greatly reduced if the electronic device 102 is sitting on a pillow, a couch or other enclosed area that restricts airflow as opposed to a hard surface.
  • Capturing variation of the thermal environment in real time may allow the electronic device 102 to optimize thermal parameters. With favorable thermal environments, performance of the electronic device 102 may be increased to capture extra thermal headroom for those thermal environments. Likewise, if an unfavorable thermal environment is detected, the electronic device 102 may decrease its performance to reflect lower thermal capability of those thermal environments to avoid overheating.
  • the processor 104 when the processor 104 increases demand for power, the processor 104 may generate more heat, resulting in a temperature rise. In response, the cooling device 106 may consume more power to remove the heat generated by the processor 104. Likewise, once power demand by the processor 104 drops, the heat generated by the processor 104 also drops. In response, cooling device 106 may decrease power consumption due to the reduced heal load.
  • the measured power ratio 110 reflects how much processor power can be removed by single unit (e.g., watt) of power spent on cooling by the cooling device 106. Therefore, the measured power ratio 110 may reflect variations in the capability of the cooling device 106 to remove heat generated by the processor 104.
  • the measured power ratio 110 may be defined as where Rmeasured is the measured power ratio 110, Pprocessor is the power used by the processor 104 and P C ooling is the power used by the cooling device 106. Therefore, in an example, the measured power ratio 110 may be determined by dividing the processor power by the cooling device power. In an example means 10W of processor power is removed with 1W of cooling device power. In another example, means 1W of processor power is removed with 10W of cooling device power.
  • the measured power ratio 110 may remain within a relatively small range. However, if there is a dramatic change in the measured power ratio 110, then this may indicate that there has been a change in the thermal environment. In this case, the performance of the electronic device 102 may be adjusted to account for the change in thermal environment.
  • the controller 108 may measure the processor power and/or the cooling device power directly.
  • the controller 108 may include circuitry to determine the power used by the processor 104 and/or the cooling device 106.
  • the controller 108 may measure the voltage and current provided to the processor 104 and/or cooling device 106. From these measurements, the power may be determined by multiplying the voltage by the current.
  • the controller 108 may receive the processor power and/or the cooling device power from another component (referred to herein as a power monitor) that measures the processor power and/or the cooling device power.
  • a power monitor another component that measures the processor power and/or the cooling device power.
  • the controller 108 may receive a signal indicating the processor power and/or the cooling device.
  • the operating system, BIOS and/or other component of the electronic device 102 may measure the processor power.
  • the controller 108 may receive a signal that informs the controller 108 of the current state of the processor power.
  • the controller 108 may determine the processor power from the received signal.
  • the controller 108 may determine the cooling device power based on a setting of the cooling device 106. For example, the controller 108 may set or may receive a speed of the cooling device 106. In the case that the cooling device 106 is a fan, the controller 108 may set or may receive the fan speed (e.g., rotation speed). The fan speed may correspond to a certain power use by the fan. In other words, the controller 108 may know how much power is used to cause the fan to rotate at a certain speed.
  • the controller 108 may compare the measured power ratio 110 to a reference power ratio 112.
  • the reference power ratio 112 may be a power ratio for the processor 104 and the cooling device 106 determined in a reference thermal environment. This controlled environment may be referred to as a reference thermal environment.
  • the reference power ratio 112 may be calibrated for a certain ambient temperature (e.g., 25 degrees Celsius (C)) and static airflow.
  • the reference power ratio 112 may be determined by measuring the processor power and the cooling device power in the reference thermal environment.
  • the reference thermal environment may simulate a setting for the electronic device 102. For instance, the reference thermal environment may simulate the temperature and/or airflow experienced by the electronic device 102 in an office setting.
  • the reference power ratio 112 may be determined using an electronic device with similar or equivalent properties as the electronic device 102. In other words, the reference power ratio 112 may be determined for one electronic device and the resulting reference power ratio 112 may be configured in the controller 108 of another electronic device 102. In some cases, the reference power ratio 112 may be determined for a particular electronic device model or range of models that share similar characteristics.
  • the controller 108 may compare the measured power ratio 110 to the reference power ratio 112. For example, a change in the thermal environment may result in a change in the measured power ratio 110.
  • the bias e.g., amount of deviation
  • the bias from the measured power ratio 110 to the reference power ratio 112 may indicate a change in the thermal environment.
  • the bias from the measured power ratio 110 to the reference power ratio 112 may be expressed in terms of a threshold amount greater than or less than the reference power ratio 112.
  • the controller 108 may determine whether the measured power ratio 110 is a threshold amount greater than the reference power ratio 112 or a threshold amount less than the reference power ratio 112.
  • a -10C cold winter setting may increase the thermal capability of the cooling device 106.
  • more processor power can be removed per unit of cooling device power in a “cold winter” environment as compared to the reference thermal environment.
  • This “cold winter” thermal environment can be detected when the measured power ratio 110 is a threshold amount greater than the reference power ratio 112. For example, if the measured power ratio 110 is 3 times greater than the reference power ratio 112, then this may indicate a “cold winter” thermal environment.
  • the electronic device 102 may be placed on a pillow.
  • less processor power can be removed per unit of cooling device power in the “enclosed” environment of the pillow as compared to the reference thermal environment.
  • This “enclosed” thermal environment can be detected when the measured power ratio 110 is a threshold amount less than the reference power ratio 112. For example, if the measured power ratio 110 is 0.3 times less than the reference power ratio 112, then this may indicate an “enclosed” thermal environment.
  • the controller 108 may determine a power adjustment 114 for the electronic device 102 based on the comparison of the measured power ratio 110 to the reference power ratio 112.
  • the power adjustment 114 may include increasing or decreasing a processor power limit.
  • the power adjustment 114 may include increasing a processor power limit in response to determining that the measured power ratio 110 is a threshold amount greater than the reference power ratio 112.
  • the thermal environment may assist heat transfer by the cooling device 106, resulting in thermal overhead for the cooling device 106. Therefore, the performance of the processor 104 may be increased to allow for the use of more power. In other words, the processor 104 may use more power without increasing the power supplied to the cooling device 106.
  • the power adjustment 114 may include decreasing a processor power limit in response to determining that the measured power ratio 110 is a threshold amount less than the reference power ratio 112.
  • the thermal environment may inhibit heat transfer by the cooling device 106. Therefore, the power supplied to the processor 104 may be reduced to avoid overheating of the electronic device 102.
  • the power adjustment 114 may include increasing or decreasing a cooling device power limit.
  • the power adjustment 114 may include decreasing a cooling device power limit in response to determining that the measured power ratio 110 is a threshold amount greater than the reference power ratio 112.
  • the thermal environment may assist heat transfer by the cooling device 106. Therefore, the cooling device 106 may use less power to remove heat generated by the processor 104.
  • the power adjustment 114 may include increasing a cooling device power limit in response to determining that the measured power ratio 110 is a threshold amount less than the reference power ratio 112.
  • the thermal environment may inhibit heat transfer by the cooling device 106. Therefore, the cooling device 106 may use more power to remove heat generated by the processor 104.
  • the controller 108 may instruct the electronic device 102 to perform the power adjustment 114. For instance, the controller 108 may instruct the electronic device 102 to increase or decrease a power limit by a certain amount.
  • the controller 108 may inform the electronic device 102 of the change in the thermal environment, and the electronic device 102 may implement the power adjustment 114. For instance, the controller 108 may inform the electronic device 102 about the amount of bias between the measured power ratio 110 and the reference power ratio 112. The electronic device 102 may then determine how to change a power limit based on this bias.
  • FIG. 2 is a block diagram illustrating another example of an electronic device 202 that may be utilized for power adjustment based on a measured power ratio 210.
  • the electronic device 202 may be implemented in accordance with the electronic device 102 described in FIG. 1.
  • the electronic device 202 may include a processor 204, cooling device 206, and controller 208 as described in FIG. 1 .
  • the electronic device 202 may include a power monitor 216 to measure power data for the processor 204 and/or the cooling device 206.
  • the power monitor 216 may include circuitry to measure power use of the processor 204 and/or the cooling device 206.
  • the power monitor 216 may include circuitry to measure power supplied to and/or consumed by the processor 204 and/or the cooling device 206.
  • a first resistor (not shown) may be coupled between a power supply and an input to the processor 204.
  • the power monitor 216 may measure the voltage and current across the first resistor for determining the processor power.
  • a second resistor (not shown) may be coupled between a power supply and an input to the cooling device 206. The power monitor 216 may measure the voltage and current across the second resistor for determining the cooling device power.
  • the power monitor 216 may send the power data to the controller 208.
  • the power monitor 216 may be referred to as an energy estimation engine (E3 IC).
  • the power monitor 216 may communicate the power data to the controller 208 on an Inter-Integrated Circuit (I2C) bus or other communication channel.
  • I2C Inter-Integrated Circuit
  • the controller 208 may determine the measured power ratio 210 of processor power to cooling device power. This may be accomplished as described in FIG. 1. In some examples, the controller 208 may determine the measured power ratio 210 using the power data provided by the power monitor 216.
  • the controller 208 may determine a current thermal environment classification 218 of the electronic device 202 based on a comparison of the measured power ratio 210 to a reference power ratio 212.
  • the reference power ratio 212 may be determined as described in FIG. 1 .
  • the controller 208 may select the current thermal environment classification 218 from a thermal environment classification list 220.
  • the thermal environment classification list 220 may include multiple thermal environment classifications that are related to the reference power ratio 212.
  • a given thermal environment classification may be associated with a certain amount of bias from the reference power ratio 212.
  • a first thermal environment classification may be selected when the fraction (or quotient) of the measured power ratio 210 ( Rmeasured ) and the reference power ratio 212 For example, if t hen the contro
  • the first threshold (A) may be calibrated to correspond to a certain thermal environment (e.g., an enclosed environment).
  • a second thermal environment classification may be selected when the fraction is greater than or equal to the first threshold (A) and less than a second threshold (B). For example, if , then the controller 208 may select the second thermal environment classification as the current thermal environment classification 218.
  • the thermal environment classification list 220 may include a number of thermal environment classifications. An example thermal environment classification list 220 with five thermal environment classifications is illustrated in Table-1 .
  • “Office Environment” is the reference thermal environment at which the reference power ratio 212 is determined.
  • X is the fraction seen in the example of Table-1
  • the multiple thermal environment classifications of the thermal environment classification list 220 may be calibrated to relate the reference power ratio 212 to different thermal surroundings (e.g., Enclosed Environment, Hot Summer Weather, Office Environment, Windy Open Air, Cold Winter, etc.).
  • the thermal environment classification list 220 may be calibrated to relate the reference power ratio 212 to a first thermal environment, to a second thermal environment, and so forth.
  • the thermal environment classifications may be decided by the level of bias between the measured power ratio 210 and reference power ratio 212 (as determined from the fraction , f or example).
  • the controller 208 may send a power adjustment command 224 based on the current thermal environment classification 218.
  • the power adjustment command 224 may instruct the electronic device 202 to adjust a processor power limit or a cooling device limit.
  • the power adjustment commands in Table-1 are examples of a power adjustment command 224 for adjusting the processor power limit.
  • the controller 208 may send the power adjustment command 224 in response to a thermal environment classification change. For example, the controller 208 may determine the current thermal environment classification 218 at a first time (ti) based on the measured power ratio 210 and the reference power ratio 212. At a later time (t2), the controller 208 may recalculate the measured power ratio 210 and current thermal environment classification 218. If the current thermal environment classification 218 at t2 differs from the previous thermal environment classification at ti, then the controller 208 may detect this thermal environment classification change. If the controller 208 detects a thermal environment classification change, then the controller 208 may send a power adjustment command 224. Otherwise, if there is no detected thermal environment classification change, then the controller 208 may forgo sending a power adjustment command 224.
  • the power adjustment command 224 may include a command to increase a processor power limit in response to a change to the current thermal environment classification 218 that is colder than a previous thermal environment classification. For instance, if the current thermal environment classification 218 changes from a warmer classification to a colder classification (e.g., from “Office Environment” to “Cold Winter”), then the power adjustment command 224 may instruct the electronic device 202 to increase the processor power limit to utilize the thermal headroom resulting from the change in thermal environment.
  • the power adjustment command 224 may include a command to decrease a processor power limit in response to a change to the current thermal environment classification that is warmer than a previous thermal environment classification. For instance, if the current thermal environment classification 218 changes from a colder classification to a warmer classification (e.g., from “Office Environment” to “Hot Summer Weather”), then the power adjustment command 224 may instruct the electronic device 202 to decrease the processor power limit to avoid overheating.
  • a colder classification to a warmer classification e.g., from “Office Environment” to “Hot Summer Weather”
  • the controller 208 may determine the measured power ratio 210 and current thermal environment classification 218 at a certain frequency (e.g., every 60 seconds). By calculating the measured power ratio 210 and comparing the measured power ratio 210 with the reference power ratio 212, the controller 208 may classify the current thermal environment with data from the past duration. In some examples, if a thermal environment classification change is detected, the controller 208 may send the power adjustment command 224. In other examples, the controller 208 may wait a certain number of cycles for re-confirmation of the thermal environment classification change before sending the power adjustment command 224.
  • the electronic device 202 may modify the processor power limit and/or cooling device power limit accordingly.
  • the controller 208 may aggregate (e.g., combine, supplement, etc.) the measured power ratio 210 with other sensor data to improve the classification of the thermal environment.
  • the electronic device 202 may include a motion sensor (e.g., inertial motion sensor, accelerometer, etc.) that provides motion data to the controller 208.
  • the controller 208 may determine whether the electronic device 202 is in a certain location (e.g., in a bag, on a table, on a lap, etc.) based on the motion data.
  • the electronic device 202 may further perform machine learning operations on the motion data to classify the motion data.
  • the motion data may be used in combination with the measured power ratio 210 to determine the current thermal environment classification 218.
  • FIG. 3 is a block diagram illustrating an example of a computer- readable medium 322 for power adjustment based on a measured power ratio.
  • the computer-readable medium 322 may be a non-transitory, tangible computer-readable medium 322.
  • the computer-readable medium 322 may be, for example, RAM, EEPROM, a storage device, an optical disc, and the like.
  • the computer-readable medium 322 may be volatile and/or non-volatile memory, such as DRAM, EEPROM, MRAM, PCRAM, memristor, flash memory, and the like.
  • the computer-readable medium 322 described in FIG. 3 may be an example of memory for an electronic device 102 described in FIG. 1 or memory for an electronic device 202 described in FIG. 2.
  • code e.g., data and/or executable code or instructions
  • of the computer-readable medium 322 may be transferred and/or loaded to memory or memories of the electronic device 102 or electronic device 202.
  • the computer-readable medium 322 may include code (e.g., data and/or executable code or instructions).
  • the computer-readable medium 322 may include measured power ratio instructions 326, thermal environment classification instructions 328, thermal environment classification change instructions 330, and/or power adjustment command instructions 332.
  • the measured power ratio instructions 326 may be instructions that when executed cause a controller of the electronic device to determine a measured power ratio of processor power to cooling device power.
  • the controller may receive power data for the processor power and the cooling device power.
  • the controller may determine the measured power ratio by dividing the processor power by the cooling device power. In some examples, this may be accomplished as described in FIGS. 1-2.
  • the thermal environment classification instructions 328 may be instructions that when executed cause the controller of the electronic device to determine a current thermal environment classification of the electronic device based on a comparison of the measured power ratio to a reference power ratio. For example, the controller may select the current thermal environment classification from a thermal environment classification list comprising multiple thermal environment classifications.
  • the reference power ratio may be a power ratio for the processor and the cooling device determined in a reference thermal environment. In some examples, this may be accomplished as described in FIGS. 1-2.
  • the thermal environment classification change instructions 330 may be instructions that when executed cause the controller of the electronic device to detect a thermal environment classification change based on the current thermal environment classification. For example, the controller may determine whether the current thermal environment classification differs from the previous thermal environment classification. In some examples, this may be accomplished as described in FIGS. 1-2.
  • the power adjustment command instructions 332 may be instructions that when executed cause the controller of the electronic device to send a power adjustment command in response to the thermal environment classification change.
  • the power adjustment command may be a command to increase a processor power limit in response to a change to the current thermal environment classification that is colder than a previous thermal environment classification.
  • the power adjustment command may be a command to decrease a processor power limit in response to a change to the current thermal environment classification that is warmer than a previous thermal environment classification. In some examples, this may be accomplished as described in FIGS. 1-2.
  • FIG. 4 is a flow diagram illustrating an example of a method 400 for power adjustment based on a measured power ratio.
  • the method 400 and/or an element or elements of the method 400 may be performed by an electronic device.
  • an element or elements of the method 400 may be performed by the electronic device 102 described in FIG. 1 , the controller 108 described in FIG. 1 , the electronic device 202 described in FIG. 2, and/or the controller 208 described in FIG. 2, any of which may be referred to generally as an “electronic device” in FIG. 4.
  • the electronic device may determine 402 a measured power ratio.
  • the electronic device e.g., controller
  • the electronic device may determine the measured power ratio of processor power to cooling device power.
  • the measured power ratio may be determined by dividing the processor power by the cooling device power.
  • the electronic device may determine 404 a current thermal environment classification of the electronic device.
  • the current thermal environment classification may be based on a comparison of the measured power ratio to a reference power ratio.
  • the reference power ratio may be a power ratio for the processor and the cooling device of the electronic device determined in a reference thermal environment.
  • the electronic device may select the current thermal environment classification from a thermal environment classification list comprising multiple thermal environment classifications. The multiple thermal environment classifications may be calibrated to relate the reference power ratio to different thermal surroundings.
  • the electronic device may determine 406 whether the thermal environment classification has changed. For example, the electronic device may determine whether the current thermal environment classification differs from a previous thermal environment classification. If the thermal environment classification has not changed, then the electronic device may continue to determine 402 the measured power ratio for a subsequent time period.
  • the electronic device may send 408 a power adjustment command based on the current thermal environment classification.
  • the power adjustment command may instruct the electronic device to adjust a processor power limit or a cooling device limit.
  • the power adjustment command may include a command to increase a processor power limit.
  • the power adjustment command may include a command to decrease a processor power limit.
  • the term “and/or” may mean an item or items.
  • the phrase “A, B, and/or C” may mean any of: A (without B and C), B (without A and C), C (without A and B), A and B (but not C), B and C (but not A), A and C (but not B), or all of A, B, and C.
  • the disclosure is not limited to the examples. Variations of the examples described herein may be within the scope of the disclosure. For example, operations, functions, aspects, or elements of the examples described herein may be omitted or combined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Cooling Or The Like Of Semiconductors Or Solid State Devices (AREA)

Abstract

Examples of electronic devices are described herein. In some examples, an electronic device includes a processor, a cooling device to provide thermal cooling to the processor, and a controller. In some examples, the controller is to determine a measured power ratio of processor power to cooling device power. In some examples, the controller is to compare the measured power ratio to a reference power ratio. In some examples, the controller is to determine a power adjustment for the electronic device based on the comparison of the measured power ratio to the reference power ratio.

Description

POWER RATIOS FOR POWER ADJUSTMENTS
BACKGROUND
[0001] Electronic technology has advanced to become virtually ubiquitous in society and has been used to improve many activities in society. For example, electronic devices are used to perform a variety of tasks, including work activities, communication, research, and entertainment. Different varieties of electronic circuits may be utilized to provide different varieties of electronic technology.
BRIEF DESCRIPTION OF THE DRAWINGS
[0002] Various examples will be described below by referring to the following figures.
[0003] FIG. 1 is a block diagram illustrating an example of an electronic device that may be utilized for power adjustment based on a measured power ratio;
[0004] FIG. 2 is a block diagram illustrating another example of an electronic device that may be utilized for power adjustment based on a measured power ratio;
[0005] FIG. 3 is a block diagram illustrating an example of a computer- readable medium for power adjustment based on a measured power ratio; and [0006] FIG. 4 is a flow diagram illustrating an example of a method for power adjustment based on a measured power ratio.
[0007] Throughout the drawings, identical or similar reference numbers may designate similar, but not necessarily identical, elements. The figures are not necessarily to scale, and the size of some parts may be exaggerated to more clearly illustrate the example shown. Moreover, the drawings provide examples in accordance with the description; however, the description is not limited to the examples provided in the drawings.
DETAILED DESCRIPTION
[0008] An electronic device may be a device that includes electronic circuitry. For instance, an electronic device may include integrated circuitry (e.g., transistors, digital logic, semiconductor technology, etc.). Examples of electronic devices include computing devices, laptop computers, desktop computers, smartphones, tablet devices, wireless communication devices, game consoles, smart appliances, printing devices, vehicles with electronic components, aircraft, drones, robots, smart appliances, etc.
[0009] The examples described herein provide for classifying the thermal environment and/or surroundings of an electronic device based on a ratio of the processor power and the cooling device power of the electronic device. In some examples, the processor may be central processing unit (CPU) and/or a graphics processing unit (GPU). In some examples, the cooling device may include an active cooling component (e.g., a fan, refrigerated heat exchanger, liquid cooling pump, etc.) that uses power (e.g., electrical power) to perform cooling of the processor and/or other components of the electronic device.
[0010] In some examples, the thermal environment classification may be used to adjust a performance parameter of the electronic device. For instance, the electronic device may be optimized in response to changes with its surroundings. In some examples, the performance parameter (e.g., processor power limit, cooling device power limit) may be optimized in response to changes in the thermal environment. In some examples, the thermal environment includes conditions external to the electronic device that affect heat transfer from the electronic device. For example, the thermal environment may include external conditions that affect conduction, convection and/or radiation of heat from the electronic device. Some examples of conditions that may be included in the thermal environment include the surrounding air temperature (also referred to as ambient air temperature or ambient temperature), radiant temperature (e.g., infrared radiation, solar radiation, etc.), air velocity (e.g., ventilation of the electronic device), humidity, and/or contact surface temperature (e.g., temperature of contacting objects, surface temperature).
[0011] The current thermal environment of the electronic device may be characterized based on a measured power ratio of processor power use to cooling device power use. This measured power ratio may be compared to a reference power ratio. In some examples, the reference power ratio may be a power ratio for the processor and the cooling device of the electronic device determined in a reference thermal environment. For instance, the reference power ratio may be determined by measuring the processor power and cooling device power while the electronic device is in a controlled environment. In some examples, heat transfer conditions (e.g., the air temperature, radiant temperature, humidity, contact surface temperature, etc.) may be calibrated (e.g., set, adjusted, determined, etc.) for the reference thermal environment. Therefore, the reference thermal environment includes calibrated external conditions that affect heat transfer from the electronic device.
[0012] In an example, when the thermal environment is favorable for heat transfer (e.g., a cold ambient temperature may facilitate heat transfer from the electronic device), a processor power limit may be increased. In another example, when there is an unfavorable thermal environment for heat transfer (e.g., a hot ambient temperature may inhibit heat transfer from the electronic device), the processor power limit may be decreased. In yet another example, the power limit for the cooling device may be decreased in a favorable thermal environment and the power limit for the cooling device may be increased in an unfavorable thermal environment to avoid overheating the electronic device.
[0013] In some examples, the measured power ratio of processor power and cooling device power may be determined in different thermal environments. This measured ratio may then be compared to a reference power ratio (also referred to as a default power ratio or baseline power ratio) to characterize the current thermal environment of the electronic device. [0014] In some examples, the electronic device may include a power monitor to measure power use (e.g., energy inflow) of the processor and/or cooling device. In some examples, the power monitor may include circuitry to measure power (e.g., electrical power) supplied to the processor and/or the cooling device. The power monitor may provide power data to the controller. In other examples, the processor and/or cooling device may provide power data directly to the controller. In some examples, the power data may be read at a certain frequency (e.g., every 60 seconds) by the controller, which calculates the measured power ratio based on the power data.
[0015] In some examples, the controller may compare the measured power ratio with the reference power ratio. The controller may classify the thermal environment of the electronic device based on the measured power data.
[0016] In some examples, the controller may trigger a power adjustment based on the current thermal environment classification. For example, if a change in the thermal environment classification is detected, the controller may notify the electronic device of the change or may wait for the next power data measurement cycle for confirmation of the change in the thermal environment classification. Once the electronic device receives a power adjustment command from controller, the electronic device may modify a processor power limit or cooling device power limit setting accordingly to optimize performance of the electronic device.
[0017] These examples may improve performance of the electronic device beyond a design target. These examples may also enable the electronic device to modify performance of the electronic device if the thermal environment is unfavorable to heat transfer to mitigate overheating.
[0018] FIG. 1 is a block diagram illustrating an example of an electronic device 102 that may be utilized for power adjustment based on a measured power ratio 110. Examples of the electronic device 102 may include computing devices, laptop computers, desktop computers, smartphones, tablet devices, wireless communication devices, game consoles, smart appliances, printing devices, vehicles with electronic components, aircraft, drones, robots, smart appliances, etc. [0019] In some examples, the electronic device 102 may include a processor 104 and/or a memory (not shown). The processor 104 may be any of a central processing unit (CPU), a semiconductor-based microprocessor, graphics processing unit (GPU), field-programmable gate array (FPGA), an applicationspecific integrated circuit (ASIC), and/or other hardware device suitable for retrieval and execution of instructions stored in the memory. The processor 104 may fetch, decode, and/or execute instructions stored in the memory. While a single processor 104 is shown in FIG. 1 , in other examples, the processor 104 may include multiple processors (e.g., a CPU and a GPU).
[0020] The memory may be any electronic, magnetic, optical, and/or other physical storage device that contains or stores electronic information (e.g., instructions and/or data). The memory may be, for example, Random Access Memory (RAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), magnetoresistive random-access memory (MRAM), phase change RAM (PCRAM), non-volatile random-access memory (NVRAM), memristor, flash memory, a storage device, and/or an optical disc, etc. In some examples, the memory may be a non-transitory tangible computer-readable storage medium, where the term “non-transitory” does not encompass transitory propagating signals. The processor 104 may be in electronic communication with the memory. In some examples, a processor 104 and/or memory of the electronic device 102 may be combined with or separate from a processor (e.g., CPU) and/or memory of a host device.
[0021] In some examples, the electronic device 102 may include different sets of memory. For example, the electronic device 102 may store certain information (e.g., instructions executed by the processor 104) in a first memory. The electronic device 102 may store other information (e.g., instructions executed by a controller 108) in a second memory.
[0022] In some examples, the electronic device 102 may include a controller 108. In some examples, the controller 108 may include a semiconductor-based processor (e.g., microprocessor), field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), and/or other hardware device suitable for retrieval and execution of instructions stored in memory. The processor of the controller 108 may fetch, decode, and/or execute instructions stored in memory.
[0023] In some examples, the controller 108 may be separate from the processor 104 of the electronic device 102. For example, the controller 108 may be an embedded controller or other discrete controller of the electronic device 102. In other examples, the controller 108 may be combined with the processor 104. For instance, the processor 104 may implement the operations (or a subset of the operations) performed by the controller 108 as described herein.
[0024] The electronic device 102 may include a cooling device 106. In some examples, the cooling device 106 may be an active device that uses electrical power to perform cooling of the electronic device 102. Some examples of the cooling device 106 include a fan, a refrigerator (e.g., components of a refrigeration system), a pump for a liquid-cooling, etc.
[0025] The controller 108 may determine a measured power ratio 110 of processor power to cooling device power. As used herein, power refers to electrical power provided to or consumed by a component of the electronic device 102. In some examples, power may be measured in watts (W).
[0026] In some examples, the processor power may be the amount of electrical power being supplied to and/or consumed by the processor 104. For example, while performing computing operations, the processor 104 may use 30W.
[0027] In some examples, the cooling device power may be the amount of electrical power being supplied to and/or consumed by the cooling device 106. For example, while cooling the processor 104 and/or other components of the electronic device 102, the cooling device 106 may use 10W to remove the heat generated by the processor 104 and/or the other components of the electronic device 102.
[0028] It should be noted that the thermal capability of the electronic device 102 may change based on the surroundings in which the electronic device 102 is located. These surroundings are referred to as the thermal environment of the electronic device 102. In an example, the cooling device 106 may dissipate much more heat in a cold winter environment than a hot summer environment. In another example, the cooling device 106 may dissipate more heat in windy outdoor air than in a closed room. In yet another example, the heat removal capability of the cooling device 106 may be greatly reduced if the electronic device 102 is sitting on a pillow, a couch or other enclosed area that restricts airflow as opposed to a hard surface.
[0029] Capturing variation of the thermal environment in real time may allow the electronic device 102 to optimize thermal parameters. With favorable thermal environments, performance of the electronic device 102 may be increased to capture extra thermal headroom for those thermal environments. Likewise, if an unfavorable thermal environment is detected, the electronic device 102 may decrease its performance to reflect lower thermal capability of those thermal environments to avoid overheating.
[0030] In an example, when the processor 104 increases demand for power, the processor 104 may generate more heat, resulting in a temperature rise. In response, the cooling device 106 may consume more power to remove the heat generated by the processor 104. Likewise, once power demand by the processor 104 drops, the heat generated by the processor 104 also drops. In response, cooling device 106 may decrease power consumption due to the reduced heal load.
[0031] The measured power ratio 110 reflects how much processor power can be removed by single unit (e.g., watt) of power spent on cooling by the cooling device 106. Therefore, the measured power ratio 110 may reflect variations in the capability of the cooling device 106 to remove heat generated by the processor 104. In an example, the measured power ratio 110 may be defined as
Figure imgf000009_0001
where Rmeasured is the measured power ratio 110, Pprocessor is the power used by the processor 104 and PCooling is the power used by the cooling device 106. Therefore, in an example, the measured power ratio 110 may be determined by dividing the processor power by the cooling device power. In an example means 10W of processor power is removed with 1W
Figure imgf000010_0001
of cooling device power. In another example, means 1W of
Figure imgf000010_0002
processor power is removed with 10W of cooling device power.
[0032] If the thermal environment remains approximately constant (e.g., the electronic device 102 remains on a desk in an air conditioned office), the measured power ratio 110 may remain within a relatively small range. However, if there is a dramatic change in the measured power ratio 110, then this may indicate that there has been a change in the thermal environment. In this case, the performance of the electronic device 102 may be adjusted to account for the change in thermal environment.
[0033] In some examples, the controller 108 may measure the processor power and/or the cooling device power directly. For instance, the controller 108 may include circuitry to determine the power used by the processor 104 and/or the cooling device 106. In an example, the controller 108 may measure the voltage and current provided to the processor 104 and/or cooling device 106. From these measurements, the power may be determined by multiplying the voltage by the current.
[0034] In another example, the controller 108 may receive the processor power and/or the cooling device power from another component (referred to herein as a power monitor) that measures the processor power and/or the cooling device power. An example of an approach using a power monitor is described in FIG. 2.
[0035] In another example, the controller 108 may receive a signal indicating the processor power and/or the cooling device. For instance, the operating system, BIOS and/or other component of the electronic device 102 may measure the processor power. The controller 108 may receive a signal that informs the controller 108 of the current state of the processor power. The controller 108 may determine the processor power from the received signal.
[0036] In yet another example, the controller 108 may determine the cooling device power based on a setting of the cooling device 106. For example, the controller 108 may set or may receive a speed of the cooling device 106. In the case that the cooling device 106 is a fan, the controller 108 may set or may receive the fan speed (e.g., rotation speed). The fan speed may correspond to a certain power use by the fan. In other words, the controller 108 may know how much power is used to cause the fan to rotate at a certain speed.
[0037] The controller 108 may compare the measured power ratio 110 to a reference power ratio 112. In some examples, the reference power ratio 112 may be a power ratio for the processor 104 and the cooling device 106 determined in a reference thermal environment. This controlled environment may be referred to as a reference thermal environment. For example, the reference power ratio 112 may be calibrated for a certain ambient temperature (e.g., 25 degrees Celsius (C)) and static airflow. The reference power ratio 112 may be determined by measuring the processor power and the cooling device power in the reference thermal environment. In some examples, the reference thermal environment may simulate a setting for the electronic device 102. For instance, the reference thermal environment may simulate the temperature and/or airflow experienced by the electronic device 102 in an office setting.
[0038] It should be noted that the reference power ratio 112 may be determined using an electronic device with similar or equivalent properties as the electronic device 102. In other words, the reference power ratio 112 may be determined for one electronic device and the resulting reference power ratio 112 may be configured in the controller 108 of another electronic device 102. In some cases, the reference power ratio 112 may be determined for a particular electronic device model or range of models that share similar characteristics.
[0039] The controller 108 may compare the measured power ratio 110 to the reference power ratio 112. For example, a change in the thermal environment may result in a change in the measured power ratio 110. The bias (e.g., amount of deviation) from the measured power ratio 110 to the reference power ratio 112 may indicate a change in the thermal environment.
[0040] In some examples, the bias from the measured power ratio 110 to the reference power ratio 112 may be expressed in terms of a threshold amount greater than or less than the reference power ratio 112. For example, the controller 108 may determine whether the measured power ratio 110 is a threshold amount greater than the reference power ratio 112 or a threshold amount less than the reference power ratio 112.
[0041] In an example, a -10C cold winter setting may increase the thermal capability of the cooling device 106. In this case, more processor power can be removed per unit of cooling device power in a “cold winter” environment as compared to the reference thermal environment. This “cold winter” thermal environment can be detected when the measured power ratio 110 is a threshold amount greater than the reference power ratio 112. For example, if the measured power ratio 110 is 3 times greater than the reference power ratio 112, then this may indicate a “cold winter” thermal environment.
[0042] In another example, the electronic device 102 may be placed on a pillow. In this case, less processor power can be removed per unit of cooling device power in the “enclosed” environment of the pillow as compared to the reference thermal environment. This “enclosed” thermal environment can be detected when the measured power ratio 110 is a threshold amount less than the reference power ratio 112. For example, if the measured power ratio 110 is 0.3 times less than the reference power ratio 112, then this may indicate an “enclosed” thermal environment.
[0043] The controller 108 may determine a power adjustment 114 for the electronic device 102 based on the comparison of the measured power ratio 110 to the reference power ratio 112. In some examples, the power adjustment 114 may include increasing or decreasing a processor power limit. For example, the power adjustment 114 may include increasing a processor power limit in response to determining that the measured power ratio 110 is a threshold amount greater than the reference power ratio 112. In this case, the thermal environment may assist heat transfer by the cooling device 106, resulting in thermal overhead for the cooling device 106. Therefore, the performance of the processor 104 may be increased to allow for the use of more power. In other words, the processor 104 may use more power without increasing the power supplied to the cooling device 106. [0044] In another example, the power adjustment 114 may include decreasing a processor power limit in response to determining that the measured power ratio 110 is a threshold amount less than the reference power ratio 112. In this case, the thermal environment may inhibit heat transfer by the cooling device 106. Therefore, the power supplied to the processor 104 may be reduced to avoid overheating of the electronic device 102.
[0045] In other examples, the power adjustment 114 may include increasing or decreasing a cooling device power limit. For example, the power adjustment 114 may include decreasing a cooling device power limit in response to determining that the measured power ratio 110 is a threshold amount greater than the reference power ratio 112. In this case, the thermal environment may assist heat transfer by the cooling device 106. Therefore, the cooling device 106 may use less power to remove heat generated by the processor 104.
[0046] In another example, the power adjustment 114 may include increasing a cooling device power limit in response to determining that the measured power ratio 110 is a threshold amount less than the reference power ratio 112. In this case, the thermal environment may inhibit heat transfer by the cooling device 106. Therefore, the cooling device 106 may use more power to remove heat generated by the processor 104.
[0047] In some examples, the controller 108 may instruct the electronic device 102 to perform the power adjustment 114. For instance, the controller 108 may instruct the electronic device 102 to increase or decrease a power limit by a certain amount.
[0048] In other examples, the controller 108 may inform the electronic device 102 of the change in the thermal environment, and the electronic device 102 may implement the power adjustment 114. For instance, the controller 108 may inform the electronic device 102 about the amount of bias between the measured power ratio 110 and the reference power ratio 112. The electronic device 102 may then determine how to change a power limit based on this bias.
[0049] FIG. 2 is a block diagram illustrating another example of an electronic device 202 that may be utilized for power adjustment based on a measured power ratio 210. The electronic device 202 may be implemented in accordance with the electronic device 102 described in FIG. 1. For example, the electronic device 202 may include a processor 204, cooling device 206, and controller 208 as described in FIG. 1 .
[0050] In some examples, the electronic device 202 may include a power monitor 216 to measure power data for the processor 204 and/or the cooling device 206. The power monitor 216 may include circuitry to measure power use of the processor 204 and/or the cooling device 206. For example, the power monitor 216 may include circuitry to measure power supplied to and/or consumed by the processor 204 and/or the cooling device 206.
[0051] In some examples, a first resistor (not shown) may be coupled between a power supply and an input to the processor 204. The power monitor 216 may measure the voltage and current across the first resistor for determining the processor power. In some examples, a second resistor (not shown) may be coupled between a power supply and an input to the cooling device 206. The power monitor 216 may measure the voltage and current across the second resistor for determining the cooling device power.
[0052] The power monitor 216 may send the power data to the controller 208. In some examples, the power monitor 216 may be referred to as an energy estimation engine (E3 IC). In some examples, the power monitor 216 may communicate the power data to the controller 208 on an Inter-Integrated Circuit (I2C) bus or other communication channel.
[0053] The controller 208 may determine the measured power ratio 210 of processor power to cooling device power. This may be accomplished as described in FIG. 1. In some examples, the controller 208 may determine the measured power ratio 210 using the power data provided by the power monitor 216.
[0054] The controller 208 may determine a current thermal environment classification 218 of the electronic device 202 based on a comparison of the measured power ratio 210 to a reference power ratio 212. In some examples, the reference power ratio 212 may be determined as described in FIG. 1 .
[0055] The controller 208 may select the current thermal environment classification 218 from a thermal environment classification list 220. In some examples, the thermal environment classification list 220 may include multiple thermal environment classifications that are related to the reference power ratio 212. A given thermal environment classification may be associated with a certain amount of bias from the reference power ratio 212. For example, a first thermal environment classification may be selected when the fraction (or quotient) of the measured power ratio 210 ( Rmeasured ) and the reference power ratio 212 For example, if then the contro||er 208 may select the first thermal
Figure imgf000015_0003
environment classification as the current thermal environment classification 218. In some examples, the first threshold (A) may be calibrated to correspond to a certain thermal environment (e.g., an enclosed environment).
[0056] In another example, a second thermal environment classification may be selected when the fraction is greater than or equal to the first
Figure imgf000015_0001
threshold (A) and less than a second threshold (B). For example, if , then the controller 208 may select the second thermal
Figure imgf000015_0002
environment classification as the current thermal environment classification 218. [0057] The thermal environment classification list 220 may include a number of thermal environment classifications. An example thermal environment classification list 220 with five thermal environment classifications is illustrated in Table-1 .
Figure imgf000016_0006
Table-1
[0058] In Table-1 , “Office Environment” is the reference thermal environment at which the reference power ratio 212 is determined. X is the fraction
Figure imgf000016_0001
seen in the example of Table-1 , the multiple thermal
Figure imgf000016_0003
environment classifications of the thermal environment classification list 220 may be calibrated to relate the reference power ratio 212 to different thermal surroundings (e.g., Enclosed Environment, Hot Summer Weather, Office Environment, Windy Open Air, Cold Winter, etc.). For example, the thermal
Figure imgf000016_0004
Figure imgf000016_0005
environment classification list 220 may be calibrated to relate the reference power ratio 212 to a first thermal environment, to a second thermal environment, and so forth. The thermal environment classifications may be decided by the level of bias between the measured power ratio 210 and reference power ratio 212 (as determined from the fraction , for example).
Figure imgf000016_0002
[0059] The controller 208 may send a power adjustment command 224 based on the current thermal environment classification 218. In some examples, the power adjustment command 224 may instruct the electronic device 202 to adjust a processor power limit or a cooling device limit. The power adjustment commands in Table-1 are examples of a power adjustment command 224 for adjusting the processor power limit.
[0060] In some examples, the controller 208 may send the power adjustment command 224 in response to a thermal environment classification change. For example, the controller 208 may determine the current thermal environment classification 218 at a first time (ti) based on the measured power ratio 210 and the reference power ratio 212. At a later time (t2), the controller 208 may recalculate the measured power ratio 210 and current thermal environment classification 218. If the current thermal environment classification 218 at t2 differs from the previous thermal environment classification at ti, then the controller 208 may detect this thermal environment classification change. If the controller 208 detects a thermal environment classification change, then the controller 208 may send a power adjustment command 224. Otherwise, if there is no detected thermal environment classification change, then the controller 208 may forgo sending a power adjustment command 224.
[0061] In an example, the power adjustment command 224 may include a command to increase a processor power limit in response to a change to the current thermal environment classification 218 that is colder than a previous thermal environment classification. For instance, if the current thermal environment classification 218 changes from a warmer classification to a colder classification (e.g., from “Office Environment” to “Cold Winter”), then the power adjustment command 224 may instruct the electronic device 202 to increase the processor power limit to utilize the thermal headroom resulting from the change in thermal environment.
[0062] In another example, the power adjustment command 224 may include a command to decrease a processor power limit in response to a change to the current thermal environment classification that is warmer than a previous thermal environment classification. For instance, if the current thermal environment classification 218 changes from a colder classification to a warmer classification (e.g., from “Office Environment” to “Hot Summer Weather”), then the power adjustment command 224 may instruct the electronic device 202 to decrease the processor power limit to avoid overheating.
[0063] In some examples, the controller 208 may determine the measured power ratio 210 and current thermal environment classification 218 at a certain frequency (e.g., every 60 seconds). By calculating the measured power ratio 210 and comparing the measured power ratio 210 with the reference power ratio 212, the controller 208 may classify the current thermal environment with data from the past duration. In some examples, if a thermal environment classification change is detected, the controller 208 may send the power adjustment command 224. In other examples, the controller 208 may wait a certain number of cycles for re-confirmation of the thermal environment classification change before sending the power adjustment command 224.
[0064] Once the electronic device 202 (e.g., the operating system, BIOS, etc.) receives the power adjustment command 224, the electronic device 202 may modify the processor power limit and/or cooling device power limit accordingly.
[0065] In some examples, the controller 208 may aggregate (e.g., combine, supplement, etc.) the measured power ratio 210 with other sensor data to improve the classification of the thermal environment. For example, the electronic device 202 may include a motion sensor (e.g., inertial motion sensor, accelerometer, etc.) that provides motion data to the controller 208. The controller 208 may determine whether the electronic device 202 is in a certain location (e.g., in a bag, on a table, on a lap, etc.) based on the motion data. In some examples, the electronic device 202 may further perform machine learning operations on the motion data to classify the motion data. The motion data may be used in combination with the measured power ratio 210 to determine the current thermal environment classification 218.
[0066] FIG. 3 is a block diagram illustrating an example of a computer- readable medium 322 for power adjustment based on a measured power ratio. The computer-readable medium 322 may be a non-transitory, tangible computer-readable medium 322. The computer-readable medium 322 may be, for example, RAM, EEPROM, a storage device, an optical disc, and the like. In some examples, the computer-readable medium 322 may be volatile and/or non-volatile memory, such as DRAM, EEPROM, MRAM, PCRAM, memristor, flash memory, and the like. In some examples, the computer-readable medium 322 described in FIG. 3 may be an example of memory for an electronic device 102 described in FIG. 1 or memory for an electronic device 202 described in FIG. 2. In some examples, code (e.g., data and/or executable code or instructions) of the computer-readable medium 322 may be transferred and/or loaded to memory or memories of the electronic device 102 or electronic device 202.
[0067] The computer-readable medium 322 may include code (e.g., data and/or executable code or instructions). For example, the computer-readable medium 322 may include measured power ratio instructions 326, thermal environment classification instructions 328, thermal environment classification change instructions 330, and/or power adjustment command instructions 332.
[0068] In some examples, the measured power ratio instructions 326 may be instructions that when executed cause a controller of the electronic device to determine a measured power ratio of processor power to cooling device power. For example, the controller may receive power data for the processor power and the cooling device power. The controller may determine the measured power ratio by dividing the processor power by the cooling device power. In some examples, this may be accomplished as described in FIGS. 1-2.
[0069] In some examples, the thermal environment classification instructions 328 may be instructions that when executed cause the controller of the electronic device to determine a current thermal environment classification of the electronic device based on a comparison of the measured power ratio to a reference power ratio. For example, the controller may select the current thermal environment classification from a thermal environment classification list comprising multiple thermal environment classifications. The reference power ratio may be a power ratio for the processor and the cooling device determined in a reference thermal environment. In some examples, this may be accomplished as described in FIGS. 1-2. [0070] In some examples, the thermal environment classification change instructions 330 may be instructions that when executed cause the controller of the electronic device to detect a thermal environment classification change based on the current thermal environment classification. For example, the controller may determine whether the current thermal environment classification differs from the previous thermal environment classification. In some examples, this may be accomplished as described in FIGS. 1-2.
[0071] In some examples, the power adjustment command instructions 332 may be instructions that when executed cause the controller of the electronic device to send a power adjustment command in response to the thermal environment classification change. For example, the power adjustment command may be a command to increase a processor power limit in response to a change to the current thermal environment classification that is colder than a previous thermal environment classification. In another example, the power adjustment command may be a command to decrease a processor power limit in response to a change to the current thermal environment classification that is warmer than a previous thermal environment classification. In some examples, this may be accomplished as described in FIGS. 1-2.
[0072] FIG. 4 is a flow diagram illustrating an example of a method 400 for power adjustment based on a measured power ratio. The method 400 and/or an element or elements of the method 400 may be performed by an electronic device. For example, an element or elements of the method 400 may be performed by the electronic device 102 described in FIG. 1 , the controller 108 described in FIG. 1 , the electronic device 202 described in FIG. 2, and/or the controller 208 described in FIG. 2, any of which may be referred to generally as an “electronic device” in FIG. 4.
[0073] The electronic device may determine 402 a measured power ratio. For example, the electronic device (e.g., controller) may determine the measured power ratio of processor power to cooling device power. In some examples, the measured power ratio may be determined by dividing the processor power by the cooling device power. [0074] The electronic device may determine 404 a current thermal environment classification of the electronic device. For example, the current thermal environment classification may be based on a comparison of the measured power ratio to a reference power ratio. In some examples, the reference power ratio may be a power ratio for the processor and the cooling device of the electronic device determined in a reference thermal environment. The electronic device may select the current thermal environment classification from a thermal environment classification list comprising multiple thermal environment classifications. The multiple thermal environment classifications may be calibrated to relate the reference power ratio to different thermal surroundings.
[0075] The electronic device may determine 406 whether the thermal environment classification has changed. For example, the electronic device may determine whether the current thermal environment classification differs from a previous thermal environment classification. If the thermal environment classification has not changed, then the electronic device may continue to determine 402 the measured power ratio for a subsequent time period.
[0076] If the electronic device determines 406 that the thermal environment classification has changed, then the electronic device may send 408 a power adjustment command based on the current thermal environment classification. For example, the power adjustment command may instruct the electronic device to adjust a processor power limit or a cooling device limit. In the case that the current thermal environment classification is colder than the previous thermal environment classification, then the power adjustment command may include a command to increase a processor power limit. In the case that the current thermal environment classification is warmer than the previous thermal environment classification, then the power adjustment command may include a command to decrease a processor power limit.
[0077] As used herein, the term “and/or” may mean an item or items. For example, the phrase “A, B, and/or C” may mean any of: A (without B and C), B (without A and C), C (without A and B), A and B (but not C), B and C (but not A), A and C (but not B), or all of A, B, and C. [0078] While various examples are described herein, the disclosure is not limited to the examples. Variations of the examples described herein may be within the scope of the disclosure. For example, operations, functions, aspects, or elements of the examples described herein may be omitted or combined.

Claims

1 . An electronic device, comprising: a processor; a cooling device to provide thermal cooling to the processor; and a controller to: determine a measured power ratio of processor power to cooling device power; compare the measured power ratio to a reference power ratio; and determine a power adjustment for the electronic device based on the comparison of the measured power ratio to the reference power ratio.
2. The electronic device of claim 1 , further comprising a power monitor to measure power data for the processor and the cooling device, and to send the power data to the controller.
3. The electronic device of claim 1 , wherein the measured power ratio is determined by dividing the processor power by the cooling device power.
4. The electronic device of claim 1 , wherein the reference power ratio comprises a power ratio for the processor and the cooling device of the electronic device determined in a reference thermal environment.
5. The electronic device of claim 1 , wherein the power adjustment comprises decreasing a cooling device power limit in response to determining that the measured power ratio is a threshold amount greater than the reference power ratio.
6. The electronic device of claim 1 , wherein the power adjustment comprises increasing a processor power limit in response to determining that the measured power ratio is a threshold amount greater than the reference power ratio.
7. The electronic device of claim 1 , wherein the power adjustment comprises increasing a cooling device power limit in response to determining that the measured power ratio is a threshold amount less than the reference power ratio.
8. The electronic device of claim 1 , wherein the power adjustment comprises decreasing a processor power limit in response to determining that the measured power ratio is a threshold amount less than the reference power ratio.
9. An electronic device, the electronic device to: determine a measured power ratio of processor power to cooling device power; determine a current thermal environment classification of the electronic device based on a comparison of the measured power ratio to a reference power ratio; and send a power adjustment command based on the current thermal environment classification.
10. The electronic device of claim 9, wherein the controller is to select the current thermal environment classification from a thermal environment classification list comprising multiple thermal environment classifications.
11 . The electronic device of claim 10, wherein the thermal environment classification list is calibrated to relate the reference power ratio to a first thermal environment and to a second thermal environment.
12. The electronic device of claim 9, wherein the power adjustment command is to instruct the electronic device to adjust a processor power limit or a cooling device limit.
13. A non-transitory tangible computer-readable medium comprising instructions when executed cause a controller of an electronic device to: determine a measured power ratio of processor power to cooling device power; determine a current thermal environment classification of the electronic device based on a comparison of the measured power ratio to a reference power ratio; detect a thermal environment classification change based on the current thermal environment classification; and send a power adjustment command in response to the thermal environment classification change.
14. The computer-readable medium of claim 13, wherein the power adjustment command comprises a command to increase a processor power limit in response to a change to the current thermal environment classification that is colder than a previous thermal environment classification.
15. The computer-readable medium of claim 13, wherein the power adjustment command comprises a command to decrease a processor power limit in response to a change to the current thermal environment classification that is warmer than a previous thermal environment classification.
PCT/US2020/047207 2020-08-20 2020-08-20 Power ratios for power adjustments WO2022039747A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/US2020/047207 WO2022039747A1 (en) 2020-08-20 2020-08-20 Power ratios for power adjustments

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/US2020/047207 WO2022039747A1 (en) 2020-08-20 2020-08-20 Power ratios for power adjustments

Publications (1)

Publication Number Publication Date
WO2022039747A1 true WO2022039747A1 (en) 2022-02-24

Family

ID=80323034

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2020/047207 WO2022039747A1 (en) 2020-08-20 2020-08-20 Power ratios for power adjustments

Country Status (1)

Country Link
WO (1) WO2022039747A1 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6182232B1 (en) * 1999-01-29 2001-01-30 Micron Electronics, Inc. Power and thermal management based on a power supply output
US20070250729A1 (en) * 1994-06-20 2007-10-25 Thomas C D Thermal and power management for computer systems
US10278304B2 (en) * 2014-02-27 2019-04-30 International Business Machines Corporation Fan control of a computer system based on power ratio
US20190155348A1 (en) * 2016-04-29 2019-05-23 Hewlett Packard Enterprise Development L.P. Fan control
US20190249678A1 (en) * 2018-02-13 2019-08-15 Quanta Computer Inc. Management of multiple fan modules
CN111103943A (en) * 2018-10-25 2020-05-05 中国信息通信研究院 Method and device for determining liquid cooling energy efficiency ratio of liquid cooling system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070250729A1 (en) * 1994-06-20 2007-10-25 Thomas C D Thermal and power management for computer systems
US6182232B1 (en) * 1999-01-29 2001-01-30 Micron Electronics, Inc. Power and thermal management based on a power supply output
US10278304B2 (en) * 2014-02-27 2019-04-30 International Business Machines Corporation Fan control of a computer system based on power ratio
US20190155348A1 (en) * 2016-04-29 2019-05-23 Hewlett Packard Enterprise Development L.P. Fan control
US20190249678A1 (en) * 2018-02-13 2019-08-15 Quanta Computer Inc. Management of multiple fan modules
CN111103943A (en) * 2018-10-25 2020-05-05 中国信息通信研究院 Method and device for determining liquid cooling energy efficiency ratio of liquid cooling system

Similar Documents

Publication Publication Date Title
US10082846B2 (en) Temperature sensing system
CN105393187B (en) Hot configuration file based on the temperature information for calculating device location
US9678490B2 (en) Systems and methods for temperature-based performance optimization of memory devices
US11181956B2 (en) Controlling fan speed of server
KR101386868B1 (en) Dynamic updating of thresholds in accordance with operating conditions
US10146279B2 (en) Solid state memory thermal regulation
US7412614B2 (en) Power management using a pre-determined thermal characteristic of a memory module
US9658661B2 (en) Climate regulator control for device enclosures
TWI432947B (en) Method of controlling the cooling fan of computer
US7117114B2 (en) On-die temperature control data for communicating to a thermal actuator
US7484380B2 (en) Determining maximum cooling for a component by retrieving an offset value
US20170374760A1 (en) Fan control based on measured heat flux
US20150050121A1 (en) Fan control system and method for controlling fan speed
US20140362518A1 (en) Thermal management of a portable computing device
US10475485B2 (en) Systems and methods for power and thermal throttling of memory devices via capacity reduction
US20200073456A1 (en) Adjusting a power limit in response to a temperature difference
US10001800B1 (en) Systems and methods for determining temperatures of integrated circuits
CN110873069B (en) Method and device for controlling fan parameters
WO2022039747A1 (en) Power ratios for power adjustments
US11971764B2 (en) Storage device, multi-component device and method of controlling operation of the same
CN107882763B (en) Rotational speed control device and method thereof
JP6725576B2 (en) Cooling system and electronic equipment
US20220187885A1 (en) Controlling speed of cooling elements
US20170031397A1 (en) Systems and methods for management of surface temperature in an information handling system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20950462

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20950462

Country of ref document: EP

Kind code of ref document: A1