CN117215783A - Memory bank frequency adjustment method and device based on real-time temperature - Google Patents
Memory bank frequency adjustment method and device based on real-time temperature Download PDFInfo
- Publication number
- CN117215783A CN117215783A CN202311167234.0A CN202311167234A CN117215783A CN 117215783 A CN117215783 A CN 117215783A CN 202311167234 A CN202311167234 A CN 202311167234A CN 117215783 A CN117215783 A CN 117215783A
- Authority
- CN
- China
- Prior art keywords
- temperature
- frequency
- memory bank
- real
- preset
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000011897 real-time detection Methods 0.000 claims abstract description 5
- 230000002222 downregulating effect Effects 0.000 claims description 20
- 238000012544 monitoring process Methods 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 17
- 230000036760 body temperature Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 abstract description 8
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000003828 downregulation Effects 0.000 description 5
- 230000033228 biological regulation Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 230000003827 upregulation Effects 0.000 description 3
- 206010033799 Paralysis Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009530 blood pressure measurement Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002155 anti-virotic effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007334 memory performance Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a memory bank frequency adjustment method and device based on real-time temperature, wherein the method comprises the following steps: when the server is started, running the memory bank according to a preset super-frequency; the real-time detection server is used for detecting real-time temperature parameters of the whole machine under the condition that the memory bank is at a preset super-frequency, wherein the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature and motherboard temperature; and adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is the corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank. The invention can pre-determine the gradient relation between the frequency of the memory strip and the temperature of the whole server, when in start-up, the server can operate at high frequency and detect the operating temperature of the whole server in real time, then the working frequency of the memory strip is up-regulated or down-regulated according to the gradient relation, and on the basis of improving the efficiency of the server, the server can operate at high frequency in a safe state.
Description
Technical Field
The invention relates to the technical field of server working state adjustment, in particular to a memory bank frequency adjustment method and device based on real-time temperature.
Background
The memory bank of the server is a common important component, the operation frequency of the memory bank is an important parameter affecting the operation stability of the memory bank, and how to operate the memory bank at a high frequency under the condition of stability so as to improve the efficiency of the whole server system has very important significance.
The current method for controlling the memory bank to operate at the over frequency is to perform pressure measurement on the memory bank after the memory bank is screened, determine the over frequency range of the current memory bank according to the pressure measurement result, and then control the memory bank to operate according to the over frequency range so as to improve the efficiency of the server.
However, the methods commonly used at present have the following technical problems: the memory strip runs in a continuous over-frequency state, so that not only is the running power consumption high, but also high temperature is generated, and the memory strip and the server are both in a high-temperature environment; and the shutdown or paralysis of the server is easily caused under the high-temperature environment, even the equipment of the server is damaged, and the normal use of the server is influenced.
Disclosure of Invention
The invention provides a memory bank frequency adjustment method and device based on real-time temperature, wherein the method is used for predetermining the gradient relation between the memory bank frequency and the temperature of the whole server, enabling the server to operate at high frequency and detecting the operating temperature of the whole server in real time when the server is started, and adjusting the working frequency of the memory bank according to the gradient relation so as to enable the server to perform high-frequency work in a safe state.
A first aspect of an embodiment of the present invention provides a method for adjusting a memory bank frequency based on a real-time temperature, where the method includes:
when the server is started, running the memory bank according to a preset over-frequency, wherein the preset over-frequency is the highest running frequency of the memory bank;
the real-time detection server is used for detecting real-time temperature parameters of the whole machine under the condition that the memory bank is at a preset super-frequency, wherein the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature and motherboard temperature;
and adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is a corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank.
In a possible implementation manner of the first aspect, the adjusting, in real time, the operating frequency of the memory bank based on the real-time temperature parameter of the complete machine and a preset gradient relation includes:
calculating a temperature average value by using the memory bank temperature, the server box temperature and the main board temperature;
if the temperature average value is larger than or equal to the temperature value of a first temperature interval of a preset gradient relation, continuously adjusting the working frequency of the memory bank according to the first stepping frequency until the working frequency of the memory bank reaches a preset safety frequency;
And if the temperature average value is smaller than the temperature value of the first temperature interval of the preset gradient relation, continuously adjusting the working frequency of the memory bank according to the second step frequency until the working frequency of the memory bank reaches the preset overtrequency frequency.
In a possible implementation manner of the first aspect, the continuously up-regulating the operating frequency of the memory bank according to the second step frequency includes:
if the temperature average value is in a second temperature interval of a preset gradient relation, continuously up-regulating the working frequency of the memory bank according to a preset first time interval and a second stepping frequency;
and continuously adjusting the working frequency of the memory bank according to a preset second time interval and a second stepping frequency if the temperature average value is in a third temperature interval of a preset gradient relation, wherein the temperature value of the second temperature interval is larger than that of the third temperature interval.
In a possible implementation manner of the first aspect, the continuously up-regulating the operating frequency of the memory bank includes:
extracting a plurality of temperature frequency parameters of the memory bank from the flash memory, wherein each temperature frequency parameter corresponds to the working frequency of the memory bank at one temperature;
calling a driving interface of the built-in frequency mapping equipment to send a frequency switching command and a plurality of temperature frequency parameters to the memory bank, and storing the current storage data of the memory bank into the virtual memory in a mirror image mode;
And pulling up a reset pin of the memory bank, and copying the current storage data of the virtual memory to the memory bank again after the memory bank completes the working frequency adjustment according to a plurality of temperature frequency parameters.
In a possible implementation manner of the first aspect, after the step of continuously down-regulating the operating frequency of the memory bank according to the first step frequency, the method further includes:
determining the down-regulating duration of the working frequency of the continuous down-regulating memory bank;
when the down-regulating time length is longer than the preset operation time length, closing the service process according to a preset process list;
and restarting the service process of the preset process list when the real-time temperature of the server is lower than the preset running temperature value.
In a possible implementation manner of the first aspect, the calculating a temperature average value using the memory bank temperature, the server box temperature, and the motherboard temperature includes:
screening two temperature values with the largest numerical values from the memory bank temperature, the server box temperature and the main board temperature;
and calculating the average value of the two temperature values with the maximum numerical value to obtain the temperature average value.
In a possible implementation manner of the first aspect, a memory bank of the server is provided with a memory bank temperature sensor, a main board of the server is provided with a main board temperature sensor, and a box body of the server is provided with a box body temperature sensor;
The real-time detection server includes:
and creating a temperature monitoring process, and calling the temperature monitoring process according to a preset acquisition time interval, so as to acquire real-time temperature from the memory bank temperature sensor, the main board temperature sensor and the box body temperature sensor through a sensor interface of the temperature monitoring process, and obtain real-time temperature parameters of the whole machine.
In a possible implementation manner of the first aspect, the operation of constructing the preset gradient relation includes:
determining a plurality of different envisaged temperature values, wherein the plurality of the envisaged temperature values are arranged in a gradient manner according to any interval difference value;
calculating the limit working frequency of the memory bank under each of the envisaged temperature values respectively;
and generating a gradient relation by using the limit working frequencies and the envisaged temperature values.
A second aspect of an embodiment of the present invention provides a memory bank frequency adjustment device based on real-time temperature, where the device includes:
the system comprises an over-frequency starting module, a memory bank, a power-on module and a power-off module, wherein the over-frequency starting module is used for operating the memory bank according to a preset over-frequency when the server is started, and the preset over-frequency is the highest operating frequency of the memory bank;
The temperature detection module is used for detecting real-time temperature parameters of the whole machine of the server when the memory bank is at a preset super-frequency, and the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature and motherboard temperature;
the frequency adjustment module is used for adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is a corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank.
In a possible implementation manner of the second aspect, the frequency adjustment module is further configured to:
calculating a temperature average value by using the memory bank temperature, the server box temperature and the main board temperature;
if the temperature average value is larger than or equal to the temperature value of a first temperature interval of a preset gradient relation, continuously adjusting the working frequency of the memory bank according to the first stepping frequency until the working frequency of the memory bank reaches a preset safety frequency;
and if the temperature average value is smaller than the temperature value of the first temperature interval of the preset gradient relation, continuously adjusting the working frequency of the memory bank according to the second step frequency until the working frequency of the memory bank reaches the preset overtrequency frequency.
In a possible implementation manner of the second aspect, the frequency adjustment module is further configured to:
if the temperature average value is in a second temperature interval of a preset gradient relation, continuously up-regulating the working frequency of the memory bank according to a preset first time interval and a second stepping frequency;
and continuously adjusting the working frequency of the memory bank according to a preset second time interval and a second stepping frequency if the temperature average value is in a third temperature interval of a preset gradient relation, wherein the temperature value of the second temperature interval is larger than that of the third temperature interval.
In a possible implementation manner of the second aspect, the frequency adjustment module is further configured to:
extracting a plurality of temperature frequency parameters of the memory bank from the flash memory, wherein each temperature frequency parameter corresponds to the working frequency of the memory bank at one temperature;
calling a driving interface of the built-in frequency mapping equipment to send a frequency switching command and a plurality of temperature frequency parameters to the memory bank, and storing the current storage data of the memory bank into the virtual memory in a mirror image mode;
and pulling up a reset pin of the memory bank, and copying the current storage data of the virtual memory to the memory bank again after the memory bank completes the working frequency adjustment according to a plurality of temperature frequency parameters.
In a possible implementation manner of the second aspect, the frequency adjustment module is further configured to:
determining the down-regulating duration of the working frequency of the continuous down-regulating memory bank;
when the down-regulating time length is longer than the preset operation time length, closing the service process according to a preset process list;
and restarting the service process of the preset process list when the real-time temperature of the server is lower than the preset running temperature value.
In a possible implementation manner of the second aspect, the frequency adjustment module is further configured to:
screening two temperature values with the largest numerical values from the memory bank temperature, the server box temperature and the main board temperature;
and calculating the average value of the two temperature values with the maximum numerical value to obtain the temperature average value.
In one possible implementation manner of the second aspect, the memory bank of the server is provided with a memory bank temperature sensor, the main board of the server is provided with a main board temperature sensor, and the box body of the server is provided with a box body temperature sensor;
the temperature detection module is further used for:
and creating a temperature monitoring process, and calling the temperature monitoring process according to a preset acquisition time interval, so as to acquire real-time temperature from the memory bank temperature sensor, the main board temperature sensor and the box body temperature sensor through a sensor interface of the temperature monitoring process, and obtain real-time temperature parameters of the whole machine.
In a possible implementation manner of the second aspect, the operation of constructing the preset gradient relation includes:
determining a plurality of different envisaged temperature values, wherein the plurality of the envisaged temperature values are arranged in a gradient manner according to any interval difference value;
calculating the limit working frequency of the memory bank under each of the envisaged temperature values respectively;
and generating a gradient relation by using the limit working frequencies and the envisaged temperature values.
Compared with the prior art, the memory bank frequency adjustment method and device based on the real-time temperature provided by the embodiment of the invention have the beneficial effects that: the invention can pre-determine the gradient relation between the frequency of the memory strip and the temperature of the whole server, when in start-up, the server can operate at high frequency and detect the operating temperature of the whole server in real time, then the working frequency of the memory strip is up-regulated or down-regulated according to the gradient relation, and on the basis of improving the efficiency of the server, the server can operate at high frequency in a safe state.
Drawings
FIG. 1 is a flow chart of a method for adjusting memory bank frequency based on real-time temperature according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating an operation of a method for adjusting a memory bank frequency based on a real-time temperature according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a memory bank frequency adjustment device based on real-time temperature according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In order to solve the above-mentioned problems, the following detailed description and the explanation will be given by the following specific embodiments to a memory bank frequency adjustment method based on real-time temperature according to the embodiments of the present application.
Referring to fig. 1, a flow chart of a method for adjusting a memory bank frequency based on a real-time temperature according to an embodiment of the application is shown.
In one embodiment, the method is applicable to the kernel of a server. In an alternative embodiment, the server may be a POWER server, wherein the POWER (Performance Optimization With Enhanced RISC) instruction set architecture is one of the most common CPU architectures, which is a RISC-based Instruction Set Architecture (ISA).
As an example, the memory bank frequency adjustment method based on the real-time temperature may include the following steps:
s11, operating the memory bank according to a preset over-frequency when the server is started, wherein the preset over-frequency is the highest operating frequency of the memory bank.
In an embodiment, in order to enable the server to operate in a high-performance state, when the server is started, the memory bank may be operated according to a preset over-frequency, where the preset over-frequency may be the highest operating frequency of the memory bank, or may be a frequency at which the memory bank reaches an optimal state when operating by continuously adjusting various indexes.
In an actual scenario, since the frequency in the Memory default XMP profile SPD of the server is fixed, in order to enable the Memory bank to operate in an optimal state when the server is started, in an implementation manner, a plurality of sets of parameters may be stored in a Memory (Memory EEPROM, also referred to as a readable and writable storage medium) in advance, where each set of parameters corresponds to a working frequency of a Memory bank, and a set of frequencies in an optimal state is included.
Then, when the power-on is started, various indexes are continuously adjusted to achieve the optimal state during operation, the parameters which are most in line with the current operation state are obtained through screening from a plurality of sets of parameters, the frequency of the set of parameters is used as the preset over-frequency, the frequency is stored in an SPI ROM (serial communication interface-based storage medium), and the power-on is operated at the highest frequency during starting.
S12, detecting real-time temperature parameters of the whole machine of the server in real time when the memory bank is at a preset super-frequency, wherein the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature, and motherboard temperature.
In one embodiment, since the memory bank is in a state of a preset over-frequency, the memory bank generates a high temperature, and the power consumption of the server increases, and the temperature increases.
Therefore, in order to avoid paralysis of the whole server, the temperature of the memory bank, the temperature of the server box body and the temperature of the server main board need to be detected respectively to obtain real-time temperature parameters of the whole machine, so that frequency adjustment processing can be performed on the memory bank comprehensively by combining each temperature.
In an alternative embodiment, the memory bank of the server is provided with a memory bank temperature sensor, the main board of the server is provided with a main board temperature sensor, and the box of the server is provided with a box body temperature sensor.
As an example, step S12 may include the following sub-steps:
s121, a temperature monitoring process is established, and the temperature monitoring process is called according to a preset collection time interval, so that real-time temperature is collected from the memory bank temperature sensor, the main board temperature sensor and the box body temperature sensor through a sensor interface of the temperature monitoring process, and real-time temperature parameters of the whole machine are obtained.
In one implementation, after the server is started, the kernel may start a temperature monitoring service, specifically, a temperature monitoring process, where the main functions of the service or process are: real-time data of the three-way temperature sensor is collected through a sensor interface (e.g., get_sensor_data). Alternatively, the frequency of collecting data may be once per second in order to improve detection accuracy.
In yet another implementation, the temperature acquisition function may also be triggered automatically by the user. For example, after starting the server, the user may select XMP Profile (over-frequency setting mode) through the BMC interface, and then the server may enter the linux kernel mode, that is, turn on the OC function. And meanwhile, the kernel starts a temperature detection background service to acquire the temperature in real time.
S13, adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is a corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank.
In an embodiment, when the real-time temperature parameter of the whole machine is collected, the frequency to be adjusted can be determined according to the magnitude of the real-time temperature parameter of the whole machine in a preset gradient relation, and then the working frequency of the memory bank can be adjusted according to the determined frequency.
For example, when the temperature is high, the working frequency of the memory bank is adjusted to be gradually reduced so as to ensure that the system or the server is not halted; when the temperature is low, the working frequency of the memory bank is adjusted to be gradually increased so as to ensure that the system or the server is in an efficient working state.
It should be noted that, the preset gradient relationship is a corresponding relationship between the temperature interval of the whole machine of the server and the frequency speed of the memory bank. The temperature is high, the frequency-down regulation is quick, the temperature is low, the frequency-up regulation is slow, the temperature is very low, and the frequency-up regulation is quick.
It should be noted that, the preset gradient relation may be that actual measurement is performed in advance according to the memory strips, the main board size and the server box size of different models, and then the data obtained by actual measurement and the temperature are recorded to obtain the corresponding adjustment relation.
In one embodiment, step S13 may include the sub-steps of:
s131, calculating a temperature average value by using the memory bank temperature, the server box temperature and the main board temperature.
In an embodiment, a temperature average value of the whole server may be calculated according to the memory bank temperature, the server box temperature and the motherboard temperature, and the temperature average value is used to represent the overall temperature.
In one embodiment, the memory bank temperature and the motherboard temperature may be too high, but the server case is larger, the temperature is lower, resulting in a lower overall temperature average; it is also possible that the temperature of the memory bank and the temperature of the server box are too high, and the motherboard has a heat dissipating device, the temperature of which is low, resulting in a low overall temperature average; at this time, the memory bank may be already in a fast damaged state, but the temperature average value is low, so that the frequency modulation process cannot be triggered.
To avoid the above, step S131 may include the following sub-steps, as an example:
s1311, screening the two maximum temperature values from the memory bank temperature, the server box temperature and the main board temperature.
S1312, calculating the average value of the two temperature values with the largest numerical values to obtain a temperature average value.
Specifically, the two highest temperatures can be arbitrarily selected from the three temperatures of the memory bank temperature, the server box temperature and the main board temperature, and then the average value of the two temperature values is calculated to obtain the temperature average value.
And S132, continuously reducing the working frequency of the memory bank according to the first step frequency if the temperature average value is larger than or equal to the temperature value of the first temperature interval of the preset gradient relation until the working frequency of the memory bank reaches the preset safety frequency.
In an embodiment, the preset gradient relation is specifically a corresponding relation between a complete machine temperature interval of the server and a frequency of the memory bank is adjusted, that is, a certain temperature interval corresponds to a certain frequency modulation rate.
Therefore, after determining the average temperature value, it can be determined in which temperature interval of the preset gradient relation the average temperature value corresponds. Furthermore, the time interval for adjusting the working frequency of the memory bank can be determined according to the temperature of the memory bank, and then the working frequency of the memory bank can be adjusted according to the time interval.
In this embodiment, the preset gradient relationship may be provided with N complete machine temperature intervals, including: a first temperature zone, a second temperature zone, …, and an nth temperature zone. Wherein the temperature value of the first temperature interval is highest, the temperature value of the second temperature interval is next lowest, and so on.
If the average temperature value is larger than or equal to the temperature value of the first temperature interval of the preset gradient relation, the whole server is in a high-temperature state, and the whole server needs to be cooled rapidly, so that the equipment and the device can be prevented from being burnt.
Therefore, the working frequency of the memory bank can be continuously and downwards adjusted according to the first step frequency until the working frequency of the memory bank reaches the preset safety frequency.
Wherein the first step frequency may be a frequency preset by the user for each down-turn, for example, 100MHZ, 200MHZ, 500MHZ, etc. The preset safe frequency is the frequency of safe operation of the memory bank, for example, 5000MHZ, 6000MHZ or 7000MHZ, etc. The frequency values can be adjusted according to actual needs.
It is assumed that the temperature value of the first temperature interval is 80-85 deg.c, the average temperature value is 89 deg.c, the first step frequency is 500MHZ, the time interval is 1 second, and the preset safety frequency is 5000MHZ. The average temperature value is larger than the temperature value of the first temperature interval, and the working frequency of the memory bank is 8000MHz. The working frequency of the memory bar can be reduced by 500MHz every second, the working frequency of the memory bar is reduced to 5000MHz after 6 times of adjustment, the preset safety frequency is reached, and the adjustment is completed.
In the continuous down-regulation process, the average temperature value of the server can be detected and calculated in real time, whether the average temperature value is larger than or equal to the temperature value of the first temperature interval of the preset gradient relation is judged, and when the average temperature value is smaller than the temperature value of the first temperature interval of the preset gradient relation, the working frequency of the memory bank can be not regulated any more.
In one embodiment, because the frequency of the memory bank is too high, the frequency of the memory bank may not reach the preset safe frequency after multiple adjustments, so as to avoid burning the device at high temperature, where, as an example, after step S132, the method may further include the following steps:
s21, determining the down-regulating duration of the working frequency of the continuous down-regulating memory bank.
S22, closing the service process according to a preset process list when the down-regulating time length is longer than the preset operation time length.
S23, restarting the service process of the preset process list when the real-time temperature of the server is lower than the preset running temperature value.
Specifically, the time from triggering the down-regulation frequency processing can be counted, and the down-regulation duration of the down-regulation processing can be obtained by counting the time from the triggering to the current time node.
If the down-regulating time length is longer than the preset operation time length, the frequency of the memory bank cannot reach the preset safety frequency after the memory bank is regulated for a plurality of times, and at the moment, the processes of the server can be closed one by one according to a preset process list.
For example, the created temperature monitoring service can monitor the load of the CPU in real time, when the temperature is higher than 80 degrees, the monitoring service issues: the sub-1 command is issued once per second, so that the DDR memory bank is controlled to drop the frequency by 200MHz. The frequency is reduced once per second, thus ensuring rapid frequency reduction and heat generation reduction.
The down-regulating time length can be counted while the down-regulating time is issued, and if the temperature in 10S is not reduced below 80 ℃, the system load is reduced through killing the process.
Specifically, the user may count some insignificant processes in advance, and put the processes into a list to obtain a preset process list. Some insignificant processes may include: non-timeliness tasks such as a disk cleaning process, an antivirus process and the like.
These processes can be killed first when the down-conversion is performed, and when the real-time temperature of the server is lower than the preset operation temperature value (for example, when the real-time temperature is lower than 60 degrees), the service process or tasks of the preset process list can be restarted, so that the server can work normally again.
In this embodiment, when the temperature is too high, the fast down-conversion processing is started to be executed, the temperature can be reduced by 200MHZ per second, if the temperature is still high, the progress of the system blacklist is killed, and then the load of the CPU can be reduced, so that the temperature of the server is not increased any more.
And S133, continuously adjusting the working frequency of the memory bank according to the second step frequency if the temperature average value is smaller than the temperature value of the first temperature interval of the preset gradient relation until the working frequency of the memory bank reaches the preset over-frequency.
If the average temperature value is smaller than the temperature value of the first temperature interval of the preset gradient relation, the temperature is lower, the frequency of the memory strip can be adjusted, and the operating efficiency of the whole server is improved by adjusting the working frequency of the memory strip.
In actual operation, the operating frequency of the memory bank may be continuously adjusted up according to a second step frequency, where the second step frequency may be a preset frequency that is adjusted up by a user, for example, 100MHZ, 200MHZ, or 500 MHZ.
In one embodiment, the temperature of the whole machine is not high, so that the working frequency of the memory bank can be adjusted according to different temperatures and different frequency modulation rates, and the temperature of equipment faults caused by rapid frequency adjustment is avoided.
As an example, step S133 may include the following sub-steps:
s1331, continuously up-regulating the working frequency of the memory bank according to a preset first time interval and a second stepping frequency if the temperature average value is in a second temperature interval of a preset gradient relation.
S1332, continuously up-regulating the working frequency of the memory bank according to a preset second time interval and a second stepping frequency if the temperature average value is in a third temperature interval of a preset gradient relation, wherein the temperature value of the second temperature interval is larger than that of the third temperature interval.
In an implementation manner, the preset gradient relation may be provided with N complete machine temperature intervals, including: a first temperature zone, a second temperature zone, …, and an nth temperature zone. And the temperature value of the second temperature interval is larger than the temperature value of the third temperature interval.
If the temperature average value is in a second temperature interval of a preset gradient relation, the temperature of the whole machine is higher; if the average temperature value is in a third temperature interval of a preset gradient relation, the temperature of the whole machine is lower.
If the temperature of the whole machine is higher, the working frequency of the memory bank can be adjusted slowly, and if the temperature of the whole machine is lower, the working frequency of the memory bank can be adjusted quickly.
For example, the first time interval is preset to 1 minute, the second time interval is preset to 30 seconds, and the second step frequency is 200MHZ.
If the temperature average value is in a second temperature interval of a preset gradient relation, the working frequency of the memory bank can be adjusted up to 200MHz every minute; if the average temperature value is within a third temperature interval of a preset gradient relation, the working frequency of the memory bank can be adjusted up to 200MHz every 30 seconds.
In the up-regulation process, the up-regulation process can be continuously carried out until the working frequency of the memory bank reaches the preset over-frequency.
It should be noted that, when the temperature is in the normal region and the higher region, the frequency up can be started, that is, the time interval for adjusting the working frequency can be shortened again, and the frequency modulation rate is improved. The steps of the steps can be the same or different; the upgrade frequency may be the same or different. The method is used for fast frequency cutting of the whole system, so that the server can operate in the DDR over-frequency mode as much as possible, and the operation speed of the server is improved.
For example, the load of the CPU is monitored in real time, and when the real-time temperature is lower than 70 degrees, a command is issued to the frequency mapping device: add+1, can control the memory bank DDR to raise the flat rate 200MHz. Once every 5 minutes, the frequency can be raised to the highest preset over-frequency (e.g., 6400 MHZ) as long as the temperature is not higher than 80 degrees while checking the real-time temperature.
In one embodiment, the operation of frequency up-regulation may be a process performed after frequency down-regulation, and in this process, it may be difficult to automatically rise after the frequency is reduced, and the process may be performed at a low frequency.
To avoid the above, the step of continuously up-regulating the operating frequency of the memory bank may include the following sub-steps, as an example:
s31, extracting a plurality of temperature frequency parameters of the memory bank from the flash memory, wherein each temperature frequency parameter corresponds to the working frequency of the memory bank at one temperature.
S32, calling a driving interface of the built-in frequency mapping equipment to send a frequency switching command and a plurality of temperature frequency parameters to the memory bank, and storing the current storage data of the memory bank into the virtual memory in a mirror image mode.
S33, pulling up a reset pin of the memory bank, and copying the current storage data of the virtual memory to the memory bank again after the memory bank completes the working frequency adjustment according to a plurality of temperature frequency parameters.
In an embodiment, the invention can solve the problem that the memory bank cannot be frequency-modulated after frequency reduction through hardware frequency mapping equipment.
Specifically, the memory can be directly controlled, the memory bank is electrified and initialized, and several temperature frequency parameters (also called as DDR algorithm) are obtained from the Flash memory (Flash), and the detection of the memory bank during the DDR algorithm is the obtained parameters, specifically, the frequency parameters which are analyzed in the foregoing and are obtained by continuously adjusting various indexes to achieve the optimal state during the operation can be obtained.
The switching command and parameters can be sent out through a driving interface of the frequency mapping device, algorithm data are sent to the memory bank through three data lines which are linear to the memory bank, the data mirror image of the whole memory bank is stored on the virtual memory, then a reset pin (arm reset pin) on the memory bank is pulled, and after the memory bank is reset, the memory bank is cut to required high frequency according to several temperature and frequency parameters. And copying the data mirror image of the memory bank on the virtual memory to the memory bank under the new frequency, thereby completing frequency up-conversion and switching.
The DDR frequency is dynamically adjusted through the additional hardware, so that the noninductive switching from low frequency to high frequency is realized.
In an embodiment, in order to accurately determine the correspondence between temperature and frequency, the operation of constructing the preset gradient relationship may include the following steps:
s41, determining a plurality of different envisaged temperature values, wherein the plurality of the envisaged temperature values are arranged in a gradient mode according to any interval difference value.
S42, calculating the limit working frequency of the memory bank under each envisaged temperature value respectively.
S43, utilizing a plurality of limit working frequencies and a plurality of envisaged temperature values to generate a gradient relation.
Specifically, real-time data of three paths of temperature sensors can be collected in advance, the frequency is collected once per second, then an algorithm of the average value of the highest two paths is taken to obtain a real-time temperature, and research and development personnel obtain a typical temperature value of the POWER server through continuous debugging.
For example, 60 ℃,70 ℃,80 ℃, wherein 80 ℃ is the limiting temperature of the DDR, and when the limiting temperature reaches the limiting temperature, the components are possibly damaged, so that when the limiting temperature is higher than the limiting temperature, the frequency reduction needs to be triggered to reduce the temperature.
Setting the temperature of 80 ℃ and above as a first temperature interval, belonging to a high-risk area, and setting the temperature of 70 ℃ to 80 ℃ as a second temperature interval, belonging to a risk area, wherein the memory bank can not be down-converted, but the load of the CPU is reduced to balance. The third temperature range from 60 ℃ to 70 ℃ belongs to the normal region, and the region does not need to be subjected to frequency reduction and load reduction. The temperature lower than 60 ℃ is a fourth temperature interval, belongs to a low-efficiency area, and can increase the speed through frequency rising in the low-efficiency area and increase the load through increasing the process concurrency.
Then, the optimal frequency of operation in different temperature intervals can be recorded, and the frequency modulation time interval in different temperature intervals can be set at the same time, so that the frequency modulation rate can be determined.
Referring to fig. 2, an operation flowchart of a memory bank frequency adjustment method based on real-time temperature according to an embodiment of the present invention is shown.
Specifically, in an actual application scenario, the operation of the memory bank frequency adjustment method based on the real-time temperature includes the following steps:
first, after Linux, the kernel creates a temperature detection process through a look call.
And secondly, obtaining three sensor data through a sensor interface get_sensor_data, and calculating the real-time temperature.
And thirdly, performing frequency modulation according to the real-time temperature value, wherein the method comprises the following steps: rapidly reducing the frequency to 200MHz at a temperature of more than 80 ℃; the temperature is higher than 70 ℃ and lower than 80 ℃, the frequency is increased normally, the frequency is increased once per minute, and the frequency is increased by 200MHZ; the temperature is higher than 60 ℃ and lower than 70 ℃, the frequency is increased normally, the frequency is increased every 2 minutes, and the frequency is increased by 200MHZ; the temperature is less than 60 ℃, the frequency is rapidly increased, and the step is 200MHz once per second.
And step four, until the frequency reaches 6400MHz.
Through the algorithm of the temperature value, the temperature of the whole server and the DDR local temperature can be considered from the global view of the system, and the local temperature is kept from being damaged due to overhigh.
The invention fully utilizes the buffer area defined by the memory temperature. The memory bank from any memory manufacturer has a temperature buffer area, and normally cannot reach the value, so that the memory performance is utilized to the maximum extent.
The preset gradient relation is a stepped frequency management strategy, so that the dead halt caused by the overhigh memory temperature can be prevented, the adjustment process tends to be mild, and the user is not felt. Meanwhile, the frequency supported by the memory can be used to the maximum extent, and the over-frequency effect is achieved.
When the overall temperature is too high, the temperature is rapidly reduced to a safe range through rapid frequency modulation, if the real-time temperature cannot be reduced, the load is reduced, and the system is ensured to be cooled.
In addition, the DDR frequency is dynamically adjusted through additional hardware, so that the noninductive switching from low frequency to high frequency is realized.
In this embodiment, the embodiment of the present invention provides a memory bank frequency adjustment method based on real-time temperature, which has the following beneficial effects: the invention can pre-determine the gradient relation between the frequency of the memory strip and the temperature of the whole server, when in start-up, the server can operate at high frequency and detect the operating temperature of the whole server in real time, then the working frequency of the memory strip is up-regulated or down-regulated according to the gradient relation, and on the basis of improving the efficiency of the server, the server can operate at high frequency in a safe state.
The embodiment of the invention also provides a memory bank frequency adjusting device based on the real-time temperature, and referring to fig. 3, a schematic structural diagram of the memory bank frequency adjusting device based on the real-time temperature is shown.
As an example, the memory bank frequency adjustment device based on the real-time temperature may include:
the over-frequency starting module 301 is configured to operate the memory bank according to a preset over-frequency when the server is started, where the preset over-frequency is the highest operating frequency of the memory bank;
the temperature detection module 302 is configured to detect, in real time, a real-time temperature parameter of a complete machine of the server when the memory bank is at a preset super-frequency, where the real-time temperature parameter of the complete machine includes: memory bank temperature, server box temperature and motherboard temperature;
the frequency adjustment module 303 is configured to adjust the operating frequency of the memory bank in real time based on the real-time temperature parameter of the complete machine and a preset gradient relationship, where the preset gradient relationship is a corresponding relationship between the complete machine temperature of the server and the frequency of the memory bank.
Optionally, the frequency adjustment module is further configured to:
calculating a temperature average value by using the memory bank temperature, the server box temperature and the main board temperature;
if the temperature average value is larger than or equal to the temperature value of a first temperature interval of a preset gradient relation, continuously adjusting the working frequency of the memory bank according to the first stepping frequency until the working frequency of the memory bank reaches a preset safety frequency;
And if the temperature average value is smaller than the temperature value of the first temperature interval of the preset gradient relation, continuously adjusting the working frequency of the memory bank according to the second step frequency until the working frequency of the memory bank reaches the preset overtrequency frequency.
Optionally, the frequency adjustment module is further configured to:
if the temperature average value is in a second temperature interval of a preset gradient relation, continuously up-regulating the working frequency of the memory bank according to a preset first time interval and a second stepping frequency;
and continuously adjusting the working frequency of the memory bank according to a preset second time interval and a second stepping frequency if the temperature average value is in a third temperature interval of a preset gradient relation, wherein the temperature value of the second temperature interval is larger than that of the third temperature interval.
Optionally, the frequency adjustment module is further configured to:
extracting a plurality of temperature frequency parameters of the memory bank from the flash memory, wherein each temperature frequency parameter corresponds to the working frequency of the memory bank at one temperature;
calling a driving interface of the built-in frequency mapping equipment to send a frequency switching command and a plurality of temperature frequency parameters to the memory bank, and storing the current storage data of the memory bank into the virtual memory in a mirror image mode;
And pulling up a reset pin of the memory bank, and copying the current storage data of the virtual memory to the memory bank again after the memory bank completes the working frequency adjustment according to a plurality of temperature frequency parameters.
Optionally, the frequency adjustment module is further configured to:
determining the down-regulating duration of the working frequency of the continuous down-regulating memory bank;
when the down-regulating time length is longer than the preset operation time length, closing the service process according to a preset process list;
and restarting the service process of the preset process list when the real-time temperature of the server is lower than the preset running temperature value.
Optionally, the frequency adjustment module is further configured to:
screening two temperature values with the largest numerical values from the memory bank temperature, the server box temperature and the main board temperature;
and calculating the average value of the two temperature values with the maximum numerical value to obtain the temperature average value.
Optionally, the memory bank of the server is provided with a memory bank temperature sensor, the main board of the server is provided with a main board temperature sensor, and the box body of the server is provided with a box body temperature sensor;
the temperature detection module is further used for:
and creating a temperature monitoring process, and calling the temperature monitoring process according to a preset acquisition time interval, so as to acquire real-time temperature from the memory bank temperature sensor, the main board temperature sensor and the box body temperature sensor through a sensor interface of the temperature monitoring process, and obtain real-time temperature parameters of the whole machine.
Optionally, the operation of constructing the preset gradient relation includes:
determining a plurality of different envisaged temperature values, wherein the plurality of the envisaged temperature values are arranged in a gradient manner according to any interval difference value;
calculating the limit working frequency of the memory bank under each of the envisaged temperature values respectively;
and generating a gradient relation by using the limit working frequencies and the envisaged temperature values.
It will be clearly understood by those skilled in the art that, for convenience and brevity, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Further, an embodiment of the present application further provides an electronic device, including: the memory, the processor and the computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the memory bank frequency adjustment method based on the real-time temperature according to the embodiment.
Further, an embodiment of the present application also provides a computer-readable storage medium, where a computer-executable program is stored, where the computer-executable program is configured to cause a computer to perform the method for adjusting a memory bank frequency based on a real-time temperature according to the above embodiment.
It will be appreciated by those skilled in the art that embodiments of the present application may also be provided including a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), devices and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and variations should also be regarded as being within the scope of the invention.
Claims (10)
1. The memory bank frequency adjustment method based on the real-time temperature is characterized by comprising the following steps of:
when the server is started, running the memory bank according to a preset over-frequency, wherein the preset over-frequency is the highest running frequency of the memory bank;
the real-time detection server is used for detecting real-time temperature parameters of the whole machine under the condition that the memory bank is at a preset super-frequency, wherein the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature and motherboard temperature;
and adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is a corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank.
2. The method for adjusting the frequency of a memory bank based on the real-time temperature according to claim 1, wherein the adjusting the operating frequency of the memory bank based on the real-time temperature parameter of the whole machine and a preset gradient relation in real time comprises:
calculating a temperature average value by using the memory bank temperature, the server box temperature and the main board temperature;
if the temperature average value is larger than or equal to the temperature value of a first temperature interval of a preset gradient relation, continuously adjusting the working frequency of the memory bank according to the first stepping frequency until the working frequency of the memory bank reaches a preset safety frequency;
And if the temperature average value is smaller than the temperature value of the first temperature interval of the preset gradient relation, continuously adjusting the working frequency of the memory bank according to the second step frequency until the working frequency of the memory bank reaches the preset overtrequency frequency.
3. The method for adjusting the frequency of a memory bank based on real-time temperature according to claim 2, wherein continuously adjusting the operating frequency of the memory bank according to the second step frequency comprises:
if the temperature average value is in a second temperature interval of a preset gradient relation, continuously up-regulating the working frequency of the memory bank according to a preset first time interval and a second stepping frequency;
and continuously adjusting the working frequency of the memory bank according to a preset second time interval and a second stepping frequency if the temperature average value is in a third temperature interval of a preset gradient relation, wherein the temperature value of the second temperature interval is larger than that of the third temperature interval.
4. A method for adjusting a memory bank frequency based on real-time temperature according to any one of claims 2 or 3, wherein continuously up-regulating the operating frequency of the memory bank comprises:
extracting a plurality of temperature frequency parameters of the memory bank from the flash memory, wherein each temperature frequency parameter corresponds to the working frequency of the memory bank at one temperature;
Calling a driving interface of the built-in frequency mapping equipment to send a frequency switching command and a plurality of temperature frequency parameters to the memory bank, and storing the current storage data of the memory bank into the virtual memory in a mirror image mode;
and pulling up a reset pin of the memory bank, and copying the current storage data of the virtual memory to the memory bank again after the memory bank completes the working frequency adjustment according to a plurality of temperature frequency parameters.
5. The method for adjusting a memory bank frequency based on a real-time temperature according to claim 2, wherein after the step of continuously down-regulating the operating frequency of the memory bank according to the first step frequency, the method further comprises:
determining the down-regulating duration of the working frequency of the continuous down-regulating memory bank;
when the down-regulating time length is longer than the preset operation time length, closing the service process according to a preset process list;
and restarting the service process of the preset process list when the real-time temperature of the server is lower than the preset running temperature value.
6. The real-time temperature-based memory bank frequency adjustment method according to claim 2, wherein calculating a temperature average value using the memory bank temperature, the server box temperature, and the motherboard temperature comprises:
Screening two temperature values with the largest numerical values from the memory bank temperature, the server box temperature and the main board temperature;
and calculating the average value of the two temperature values with the maximum numerical value to obtain the temperature average value.
7. The method for adjusting the frequency of a memory bank based on real-time temperature according to any one of claims 1, 2, 3, 5 or 6, wherein the memory bank of the server is provided with a memory bank temperature sensor, a main board of the server is provided with a main board temperature sensor, and a box body of the server is provided with a box body temperature sensor;
the real-time detection server includes:
and creating a temperature monitoring process, and calling the temperature monitoring process according to a preset acquisition time interval, so as to acquire real-time temperature from the memory bank temperature sensor, the main board temperature sensor and the box body temperature sensor through a sensor interface of the temperature monitoring process, and obtain real-time temperature parameters of the whole machine.
8. The method for adjusting a memory bank frequency based on a real-time temperature according to any one of claims 1, 2, 3, 5 or 6, wherein the operation of constructing the preset gradient relation comprises:
Determining a plurality of different envisaged temperature values, wherein the plurality of the envisaged temperature values are arranged in a gradient manner according to any interval difference value;
calculating the limit working frequency of the memory bank under each of the envisaged temperature values respectively;
and generating a gradient relation by using the limit working frequencies and the envisaged temperature values.
9. A memory bank frequency adjustment device based on real-time temperature, the device comprising:
the system comprises an over-frequency starting module, a memory bank, a power-on module and a power-off module, wherein the over-frequency starting module is used for operating the memory bank according to a preset over-frequency when the server is started, and the preset over-frequency is the highest operating frequency of the memory bank;
the temperature detection module is used for detecting real-time temperature parameters of the whole machine of the server when the memory bank is at a preset super-frequency, and the real-time temperature parameters of the whole machine comprise: memory bank temperature, server box temperature and motherboard temperature;
the frequency adjustment module is used for adjusting the working frequency of the memory bank in real time based on the real-time temperature parameter of the whole machine and a preset gradient relation, wherein the preset gradient relation is a corresponding relation between the temperature of the whole machine of the server and the frequency speed of the memory bank.
10. A computer-readable storage medium storing a computer-executable program for causing a computer to execute the real-time temperature-based memory bank frequency adjustment method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311167234.0A CN117215783A (en) | 2023-09-11 | 2023-09-11 | Memory bank frequency adjustment method and device based on real-time temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311167234.0A CN117215783A (en) | 2023-09-11 | 2023-09-11 | Memory bank frequency adjustment method and device based on real-time temperature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117215783A true CN117215783A (en) | 2023-12-12 |
Family
ID=89040018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311167234.0A Pending CN117215783A (en) | 2023-09-11 | 2023-09-11 | Memory bank frequency adjustment method and device based on real-time temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117215783A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573381A (en) * | 2024-01-16 | 2024-02-20 | 苏州元脑智能科技有限公司 | Method, system, equipment and storage medium for expanding memory frequency modulation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1687867A (en) * | 2005-05-25 | 2005-10-26 | 威盛电子股份有限公司 | Method for regulating internal storage frequency |
| CN111324196A (en) * | 2020-02-03 | 2020-06-23 | Oppo广东移动通信有限公司 | Memory operation frequency adjusting method and device, storage medium and electronic equipment |
| US20230043091A1 (en) * | 2021-08-03 | 2023-02-09 | Micron Technology, Inc. | Performing refresh operations of a memory device according to a dynamic refresh frequency |
-
2023
- 2023-09-11 CN CN202311167234.0A patent/CN117215783A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1687867A (en) * | 2005-05-25 | 2005-10-26 | 威盛电子股份有限公司 | Method for regulating internal storage frequency |
| CN111324196A (en) * | 2020-02-03 | 2020-06-23 | Oppo广东移动通信有限公司 | Memory operation frequency adjusting method and device, storage medium and electronic equipment |
| US20230043091A1 (en) * | 2021-08-03 | 2023-02-09 | Micron Technology, Inc. | Performing refresh operations of a memory device according to a dynamic refresh frequency |
Non-Patent Citations (1)
| Title |
|---|
| 张欣 等: "基于EMS的一次调频监控系统方案设计", 《电力系统通信》, vol. 30, no. 6, 10 June 2009 (2009-06-10), pages 55 - 58 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117573381A (en) * | 2024-01-16 | 2024-02-20 | 苏州元脑智能科技有限公司 | Method, system, equipment and storage medium for expanding memory frequency modulation |
| CN117573381B (en) * | 2024-01-16 | 2024-03-29 | 苏州元脑智能科技有限公司 | Method, system, equipment and storage medium for expanding memory frequency modulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117215783A (en) | Memory bank frequency adjustment method and device based on real-time temperature | |
| CN110799757B (en) | Fan control method, fan control device and electronic equipment | |
| US20130283099A1 (en) | System and method for tesing stability of server | |
| US9746858B2 (en) | Control device for automatically starting warm-up | |
| CN107608865B (en) | Data storage method and device | |
| CN103186439A (en) | Server test system and server stability test method | |
| KR20190007486A (en) | Systems and methods for determining turbo machine safe start clearances | |
| CN104794016A (en) | Mobile terminal crash testing and processing method and system | |
| CN107480522B (en) | ELF file execution control system and method | |
| CN114151373B (en) | Method, system, terminal and storage medium for regulating and controlling rotation speed of server fan | |
| EP3703250A1 (en) | Servo driver and state change detecting method | |
| CN109582505B (en) | BIOS option default value recovery system, method and device | |
| CN111059860A (en) | Refrigerator and intelligent operation control method thereof | |
| WO2020034491A1 (en) | Overexcitation limiting method and system for excitation regulator | |
| CN112523913B (en) | Unmanned aerial vehicle automatic starting method and system, storage medium and electronic equipment | |
| CN111140517A (en) | Water temperature rise rate-based water pump shutdown control method, device and system | |
| CN113581014B (en) | Adaptive battery working condition cold strategy method, device, equipment and readable storage medium | |
| CN112636564B (en) | Converter control method and device, converter, electronic device and storage medium | |
| CN112656209B (en) | Dry burning detection method and device and storage medium | |
| CN110519389B (en) | Parameter adjusting method and device for engineering equipment, engineering equipment and storage medium | |
| CN113818514A (en) | Judgment method, controller and device for flameout of excavator and excavator | |
| CN111857319A (en) | Intelligent optimization method and system for server power consumption | |
| CN117489627B (en) | Fan locked rotor test method and device, control terminal equipment and storage medium | |
| CN111290886A (en) | Method for automatically recovering operation of equipment and water heater | |
| US11630674B2 (en) | Smart overclocking method conducted in basic input/output system (BIOS) of computer device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |