IP Library › Granted Patent US 12,190,124
Granted Patent B2
US 12,190,124 · App. 18/005,535 · Granted Jan 7, 2025

Method for determining configuration parameters of data processing device, electronic device and storage medium

Inventors: Weibin Ma (Guangdong, CN); Lihong Huang (Guangdong, CN); Haifeng Guo (Guangdong, CN); Zuoxing Yang (Guangdong, CN)
Assignee: SHENZHEN MICROBT ELECTRONICS TECHNOLOGY CO., LTD.
G06F9/44505G06N20/00G06F9/4401
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,190,124
App. No.
18/005,535
Granted
Jan 7, 2025
Kind
B2
Abstract

Disclosed is a method for determining configuration parameters of a data processing device, including: operating the data processing device by using configuration parameters, which are universal optimization configuration parameters obtained according to a universal operating parameter model; during the operating process, changing the configuration parameters to obtain a dedicated operating parameter data set, which includes a plurality of groups of operating parameters, each of which includes configuration parameters and capability parameters of the data processing device when the data processing device is operating under the configuration parameters; executing model training by using the dedicated operating parameter data set to obtain a dedicated operating parameter model; and obtaining optimal configuration parameters according to the dedicated operating parameter model, and operating the data processing device according to the optimal configuration parameters, where the optimal configuration parameters are configuration parameters corresponding to optimal capability parameters in the dedicated operating parameter data set.

Claims (24)

1. A method for determining configuration parameters of a data processing device, comprising:

operating the data processing device by using configuration parameters, wherein the configuration parameters are initially configured as universal optimization configuration parameters obtained according to a universal operating parameter model;

during the operating process of the data processing device, changing the configuration parameters of the data processing device to obtain a dedicated operating parameter data set of the data processing device, wherein the operating parameter dedicated data set comprises a plurality of groups of operating parameters, and each group of operating parameters comprises configuration parameters and capability parameters of the data processing device when the data processing device is operating under the configuration parameters;

executing model training by using the dedicated operating parameter data set to obtain a dedicated operating parameter model for the data processing device; and

obtaining optimal configuration parameters of the data processing device according to the dedicated operating parameter model, and operating the data processing device according to the optimal configuration parameters, wherein the optimal configuration parameters are configuration parameters corresponding to optimal capability parameters in the dedicated operating parameter data set, wherein the capability parameters include the computing power of the data processing device and the power of the data processing device.

2. The method according to claim 1 , wherein

the configuration parameters comprise: a frequency of each hash chip, a temperature of a hashboard, and a power supply output voltage of the data processing device.

3. The method according to claim 2 , wherein said changing the configuration parameters of the data processing device to obtain the dedicated operating parameter data set of the data processing device comprises:

changing the frequency of the each hash chip, the temperature of the hashboard, and/or the power supply output voltage of the data processing device, to obtain capability parameters of the data processing device under different configuration parameters, forming the operating parameters with the configuration parameters and the capability parameters of the data processing device corresponding to the configuration parameters, and forming the dedicated operating parameter data set of the data processing device with the plurality of groups of operating parameters.

4. The method according to claim 1 , wherein said obtaining the optimal configuration parameters of the data processing device according to the dedicated operating parameter model for the data processing device comprises:

by using the dedicated operating parameter model for the data processing device, traversing values of the configuration parameters to obtain the configuration parameters corresponding to the optimal capability parameters in the dedicated operating parameter data set, and taking the configuration parameters corresponding to the optimal capability parameters as the optimal configuration parameters of the data processing device.

5. The method according to claim 1 , further comprising:

obtaining the universal optimization configuration parameters by using the universal operating parameter model for the data processing device.

6. The method according to claim 5 , wherein the universal operating parameter model is obtained by using the following method:

forming operating parameters of a plurality of data processing devices into a universal operating parameter data set; and

executing model training by using the universal operating parameter data set, to obtain the universal operating parameter model, wherein

the operating parameters comprise configuration parameters of each data processing device and capability parameters of the data processing device when the data processing device is operating under the configuration parameters.

7. The method according to claim 6 , wherein said obtaining the universal optimization configuration parameters by using the universal operating parameter model comprises:

by using the universal operating parameter model, traversing values of the configuration parameters in the universal operating parameter model to obtain the configuration parameters corresponding to the optimal capability parameters in the universal operating parameter model, and taking the configuration parameters corresponding to the optimal capability parameters as the universal optimization configuration parameters of the data processing device.

8. A non-volatile computer-readable storage medium, storing instructions, wherein the instructions, when executed by a processor, cause the processor to perform the steps of the method for determining configuration parameters of a data processing device according to claim 1 .

9. An electronic device, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor, wherein

the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, to cause the at least one processor to perform the steps of the method for determining configuration parameters of a data processing device according to claim 1 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 13, 2023
From: MA, WEIBIN; HUANG, LIHONG; GUO, HAIFENG; YANG, ZUOXING
To: SHENZHEN MICROBT ELECTRONICS TECHNOLOGY CO., LTD.
Reel/Frame 062375/0075 →
Priority Claims (1)
CN 202011353553.7 · Nov 27, 2020 · national
Continuity (1)
Related Publication 20230289196A1 · Sep 14, 2023
References Cited (24)
US 11428766B2 · Leussler · 2022 [cited by examiner]
US 11509542B2 · Shirazipour · 2022 [cited by examiner]
US 20110283235A1 · Kling · 2011 [cited by examiner]
US 20160110657A1 · Gibiansky · 2016 [cited by examiner]
US 20180104500A1 · Blum · 2018 [cited by examiner]
US 20180239987A1 · Chen · 2018 [cited by examiner]
US 20190227814A1 · Bregman · 2019 [cited by examiner]
US 20190325307A1 · Li · 2019 [cited by examiner]
US 20200090073A1 · Zhan · 2020 [cited by examiner]
US 20200142466A1 · Naik · 2020 [cited by examiner]
US 20200272771A1 · Yoshikawa · 2020 [cited by examiner]
US 20220207401A1 · Ito · 2022 [cited by examiner]
US 20220238318A1 · Ishikawa · 2022 [cited by examiner]
US 20220295311A1 · Chuai · 2022 [cited by examiner]
US 20230176639A1 · Ma · 2023 [cited by examiner]
US 20230254709A1 · Dey · 2023 [cited by examiner]
US 20240098496A1 · Marzban · 2024 [cited by examiner]
CN 108733540A · 2018 [cited by examiner]
CN 109812927A · 2019 [cited by applicant]
CN 110390387A · 2019 [cited by applicant]
CN 111811110A · 2020 [cited by applicant]
CN 111966202A · 2020 [cited by applicant]
CN 112506649A · 2021 [cited by applicant]
International Search Report mailed Aug. 30, 2021 in International Application No. PCT/CN2021/097822. [cited by applicant]