IP Library › Granted Patent US 12664066
Granted Patent B1
US 12664066 · App. 19/187,350 · Granted Jun 23, 2026

Retrieval of integrated circuit chip data

Inventors: Diana Pham (Santa Clara, CA); Marshall Long (Sugarland, TX); Matangi Vaidyanathan (Santa Clara, CA); Sairam Jalakam Devarajulu (Santa Clara, CA); Sridhar Chirravuri (Sunnyvale, CA)
Assignee: Auradine, Inc.
G06F11/3058G06F11/3006
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 12664066
App. No.
19/187,350
Granted
Jun 23, 2026
Kind
B1
Abstract

A method includes: receiving, at an asset management server, status data from a plurality of computing devices that are remote from the asset management server; storing the status data in a telemetry database; receiving, at the asset management server, a first request from a user device; in response to the first request, obtaining, from the telemetry database, a first subset of the status data, and providing the first subset of the status data to the user device; receiving, at the asset management server, a second request from the user device; and, in response to the second request, obtaining, from the telemetry database, a second subset of the status data that includes status data not included in the first subset of the status data, and providing the second subset of the status data to the user device.

Claims (70)

1 . A method, comprising:

receiving, at an asset management server, status data from a plurality of computing devices that are remote from the asset management server,

wherein each of the plurality of computing devices comprises a plurality of IC chips configured to perform a common type of computation in parallel with one another, and

wherein the status data comprises at least one of a computation rate, a power consumption, or a computation efficiency;

storing, by the asset management server, the status data in a telemetry database;

receiving, at the asset management server, a first request from a user device;

in response to the first request, obtaining, by the asset management server from the telemetry database, a first subset of the status data, and providing the first subset of the status data to the user device;

receiving, at the asset management server, a second request from the user device; and

in response to the second request, obtaining, by the asset management server from the telemetry database, a second subset of the status data that comprises status data not included in the first subset of the status data, and providing the second subset of the status data to the user device,

wherein the first subset of the status data is limited to status data for a first subset of the plurality of computing devices, to thereby reduce bandwidth usage associated with status data retrieval,

wherein the second subset of the status data comprises status data for at least one computing device of the plurality of computing devices that is not included in the first subset of the plurality of computing devices,

wherein the first subset of the status data and the second subset of the status data are presented in a table in a user interface of the user device,

wherein different computing devices of the plurality of computing devices correspond to different rows of the table, and

wherein the first subset of the plurality of computing devices and the second subset of the plurality of computing devices correspond to respective sets of rows that are displayed at different times.

2 . The method of claim 1 , wherein the first subset of the plurality of computing devices and the second subset of the plurality of computing devices are associated, respectively, with a first group-specific objective for the common type of computation and a second group-specific objective for the common type of computation,

wherein the first group-specific objective is different from the second group-specific objective, and

wherein the method comprises controlling the plurality of computing devices to perform the common type of computation based on the first and second group-specific objectives.

3 . The method of claim 1 , wherein the first subset of the plurality of computing devices and the second subset of the plurality of computing devices are associated, respectively, with a first site-specific power plan and a second site-specific power plan,

wherein the first site-specific power plan and the second site-specific power plan comprise respective different maxima of rate of increase in power consumption by the first subset of the plurality of computing devices and the second subset of the plurality of computing devices,

wherein the first site-specific power plan is different from the second site-specific power plan, and

wherein the method comprises controlling the plurality of computing devices to perform the common type of computation based on the first and second site-specific power plans.

4 . The method of claim 1 , wherein the first subset of the status data is limited to a first subset of types of status data, from among a plurality of types of the status data, and wherein the second subset of the status data comprises at least one type of status data that is not included in the first subset of types of status data.

5 . The method of claim 4 , wherein the first subset of types of status data comprises at least one of the computation rate or the power consumption.

6 . The method of claim 4 , comprising receiving, at the asset management server, a request to alter which one or more types of status data are included in the first subset of types of status data.

7 . The method of claim 1 , comprising controlling the plurality of computing devices to perform the common type of computation based on instructions received at the asset management server from the user device.

8 . The method of claim 1 , wherein the common type of computation comprises a hash computation or a machine learning computation.

9 . The method of claim 1 , wherein the common type of computation comprises a hash computation or a machine learning computation.

10 . An asset management server comprising:

one or more processors; and

one or more non-transitory, computer-readable storage media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving status data from a plurality of computing devices that are remote from the asset management server,

wherein each of the plurality of computing devices comprises a plurality of IC chips configured to perform a common type of computation in parallel with one another, and

wherein the status data comprises at least one of a computation rate, a power consumption, or a computation efficiency;

storing the status data in a telemetry database;

receiving a first request from a user device;

in response to the first request, obtaining, from the telemetry database, a first subset of the status data, and providing the first subset of the status data to the user device;

receiving a second request from the user device; and

in response to the second request, obtaining, from the telemetry database, a second subset of the status data that comprises status data not included in the first subset of the status data, and providing the second subset of the status data to the user device,

wherein the first subset of the status data is limited to a first subset of types of status data, from among a plurality of types of the status data, to thereby reduce bandwidth usage associated with status data retrieval,

wherein the second subset of the status data comprises at least one type of status data that is not included in the first subset of types of status data,

wherein the first subset of the status data and the second subset of the status data are presented in a table in a user interface of the user device,

wherein different computing devices of the plurality of computing devices correspond to different rows of the table, and

wherein the second request is triggered by a user selection of a row of the table.

11 . The asset management server of claim 10 , wherein the first subset of the status data is limited to status data for a first subset of the plurality of computing devices, and wherein the second subset of the status data comprises status data for at least one computing device of the plurality of computing devices that is not included in the first subset of the plurality of computing devices.

12 . The asset management server of claim 11 , wherein the first subset of the plurality of computing devices and the second subset of the plurality of computing devices are associated, respectively, with a first group-specific objective for the common type of computation and a second group-specific objective for the common type of computation,

wherein the first group-specific objective is different from the second group-specific objective, and

wherein the operations comprise controlling the plurality of computing devices to perform the common type of computation based on the first and second group-specific objectives.

13 . The asset management server of claim 11 , wherein the first subset of the plurality of computing devices and the second subset of the plurality of computing devices are associated, respectively, with a first site-specific power plan and a second site-specific power plan,

wherein the first site-specific power plan and the second site-specific power plan comprise respective different maxima of rate of increase in power consumption by the first subset of the plurality of computing devices and the second subset of the plurality of computing devices,

wherein the first site-specific power plan is different from the second site-specific power plan, and

wherein the operations comprise controlling the plurality of computing devices to perform the common type of computation based on the first and second site-specific power plans.

14 . The asset management server of claim 10 , wherein the first subset of types of status data comprises at least one of the computation rate or the power consumption.

15 . The asset management server of claim 10 , wherein the common type of computation comprises a hash computation or a machine learning computation.

16 . A method, comprising:

receiving, at an asset management server, status data from a plurality of computing devices that are remote from the asset management server,

wherein each of the plurality of computing devices comprises a plurality of IC chips configured to perform a common type of computation in parallel with one another, and

wherein the status data comprises at least one of a computation rate, a power consumption, or a computation efficiency;

storing, by the asset management server, the status data in a telemetry database;

receiving, at the asset management server, a first request from a user device;

in response to the first request, obtaining, by the asset management server from the telemetry database, a first subset of the status data, and providing the first subset of the status data to the user device;

receiving, at the asset management server, a second request from the user device; and

in response to the second request, obtaining, by the asset management server from the telemetry database, a second subset of the status data that comprises status data not included in the first subset of the status data, and providing the second subset of the status data to the user device,

wherein the first subset of the status data is limited to a first subset of types of status data, from among a plurality of types of the status data, to thereby reduce bandwidth usage associated with status data retrieval, and

wherein the second subset of the status data comprises at least one type of status data that is not included in the first subset of types of status data,

wherein the first subset of the status data and the second subset of the status data are presented in a table in a user interface of the user device,

wherein different computing devices of the plurality of computing devices correspond to different rows of the table, and

wherein the second request is triggered by a user selection of a row of the table.

17 . The method of claim 16 , wherein the first subset of types of status data comprises at least one of the computation rate or the power consumption.

18 . The method of claim 16 , comprising receiving, at the asset management server, a request to alter which one or more types of status data are included in the first subset of types of status data.

19 . The method of claim 16 , comprising controlling the plurality of computing devices to perform the common type of computation based on instructions received at the asset management server from the user device.