Workload thermolysis curves
In an example implementation according to aspects of the present disclosure, a system includes a thermal sensor and a processor. The processor determines that a workload surpasses a high workload threshold. The processor determines that the workload transcends a low workload threshold after the workload abates. The processor determines a measured thermolysis curve based on a reading from the thermal sensor. The processor compares the measured thermolysis curve against a target thermolysis curve and generates a filter event based on the comparing.
1 . A system comprising:
a thermal sensor to sample a temperature of a thermal zone of the system and output a reading;
a processor communicatively coupled to the thermal sensor, the processor to:
monitor a workload of a micro-processing device in the thermal zone;
determine that the workload surpasses a high workload threshold;
determine that the workload transcends a low workload threshold, wherein the low workload threshold corresponds to an abatement in the workload after surpassing the high workload threshold;
determine a measured thermolysis curve based on a reading from the thermal sensor, responsive to the workload transcending the low workload threshold;
compare the measured thermolysis curve against a target thermolysis curve; and
generate a filter event based on the comparing, wherein the filter event indicates to change a filter associated with the thermal zone.
2 . The system of claim 1 , further comprising the processor to:
transmit the measured thermolysis curve to a cloud-based system, wherein the cloud-based system utilizes the measured thermolysis curve in calculating an updated target thermolysis curve.
3 . The system of claim 2 , further comprising the processor to transmit the filter event to the cloud-based system.
4 . The system of claim 1 , further comprising the processor to:
determine, responsive to the workload transcending the low work workload threshold, a time value, wherein the time value corresponds to a period of time wherein the workload remains below the low workload threshold;
compare the time value to a time value threshold; and
discard a sample thermolysis curve responsive to the time value being less than the time value threshold.
5 . The system of claim 4 , wherein the time value corresponds to a collection time of the sample thermolysis curve.
6 . The system of claim 1 , wherein the micro-processing device is at least one of a graphics processing unit or a central processing unit.
7 . The system of claim 6 ,
wherein the thermal zone is a location within a computing device that includes the micro-processing device, the thermal sensor, and a fan, and
wherein, to generate the filter event, the processor is to:
output a notification as an auditory or visual code to indicate to change the filter associated with the thermal zone.
8 . The system of claim 7 , wherein, to output the notification as an auditory or visual code, the processor is to at least one of:
transmit an inter process message to an application to cause presentation of the notification, or
cause presentation of the notification as a pop up notification.
9 . A method comprising:
monitoring a workload of a micro-processing device in a thermal zone;
determining that the workload surpasses a high workload threshold;
determining that the workload transcends a low workload threshold, wherein the low workload threshold corresponds to an abatement in the workload after surpassing the high workload threshold;
collecting, from a thermal sensor to sample a temperature of the thermal zone, a series of temperature measurements during a period of time after the abatement;
determining a measured thermolysis curve based on the series of temperature measurements, responsive to the workload transcending the low workload threshold;
comparing the measured thermolysis curve against a target thermolysis curve; and
generating a filter event based on the comparing, wherein the filter event indicates to change a filter associated with the thermal zone.
10 . The method of claim 9 , further comprising transmitting the measured thermolysis curve to a cloud-based system, wherein the cloud-based system utilizes the measured thermolysis curve in calculating an updated target thermolysis curve.
11 . The method of claim 9 , further comprising transmitting the filter event to a cloud-based system.
12 . The method of claim 9 , further comprising:
determining, responsive to the workload transcending the low workload threshold, a time value, wherein the time value corresponds to a period of time wherein the workload remains below the low workload threshold;
comparing the time value to a time value threshold; and
discarding a sample thermolysis curve responsive to the time value being less than the time value threshold.
13 . The method of claim 12 , wherein the time value corresponds to a collection time of the sample thermolysis curve.
14 . The method of claim 9 , wherein the workload corresponds to a processing utilization percentage of the micro-processing device.
15 . A non-transitory computer readable medium comprising instructions executable by a processor to:
monitor a workload of a micro-processing device in a thermal zone;
determine that the workload surpasses a high workload threshold;
determine that the workload transcends a low workload threshold, wherein the low workload threshold corresponds to an abatement in the workload after surpassing the high workload threshold;
collect, from a thermal sensor to sample a temperature of the thermal zone, a series of temperature measurements during a period of time after the abatement;
determine a measured thermolysis curve based on the series of temperature measurements, responsive to the workload transcending the low workload threshold;
receive a target thermolysis curve from a cloud-based system, wherein the target thermolysis curve corresponds to an aggregated system benchmark;
compare the measured thermolysis curve against the target thermolysis curve; and
generate a filter event based on the comparing, wherein the filter event indicates to change a filter associated with the thermal zone.
16 . The computer readable medium of claim 15 , further comprising instructions executable by the processor to transmit the measured thermolysis curve to the cloud-based system, wherein the cloud-based system utilizes the measured thermolysis curve in calculating an updated target thermolysis curve.
17 . The computer readable medium of claim 15 , further comprising instructions executable by the processor to transmit the filter event to the cloud-based system.
18 . The computer readable medium of claim 15 , further comprising instructions executable by the processor to:
determine, responsive to the workload transcending the low workload threshold, a time value, wherein the time value corresponds to a period of time wherein the workload remains below the low workload threshold;
compare the time value to a time value threshold; and
discard a sample thermolysis curve responsive to the time value being less than the time value threshold.
19 . The computer readable medium of claim 18 , wherein the time value corresponds to a collection time of the sample thermolysis curve.
20 . The computer readable medium of claim 15 , wherein the workload corresponds to a processing utilization percentage of the micro-processing device.