US 12,443,508 B1
Method and system of optimizing the performance of a second computer by a first computer
Lawrence Kom, Redmond, WA (US); and Thomas Middleton Rutledge Fuller, Seattle, WA (US)
Assigned to Core Scientific, Inc., Austin, TX (US)
Filed by Core Scientific Operating Company, Bellevue, WA (US)
Filed on May 13, 2022, as Appl. No. 17/744,023.
Claims priority of provisional application 63/187,995, filed on May 13, 2021.
Int. Cl. G06F 11/34 (2006.01); G06Q 20/06 (2012.01)
CPC G06F 11/3495 (2013.01) [G06F 11/3409 (2013.01); G06Q 20/065 (2013.01); G06Q 2220/00 (2013.01); H04L 2209/56 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of computer operation, the method comprising:
(a) providing a first computer and a second computer including a plurality of hashboards;
(b) operating the second computer, including executing, by the plurality of hashboards, computational operations for solving hash-based challenges as part of a blockchain-based proof-of-work algorithm;
(c) modifying settings of the second computer;
(d) monitoring, via the first computer, changes to a plurality of operational parameters of the second computer after the settings are modified to identify a plurality of covariant parameters of the plurality of operational parameters, wherein the plurality of covariant parameters includes one or more groups, each group comprising one or more operational parameters and corresponding one or more performance parameters; and
(e) controlling, via the first computer, operation of the second computer according to the identified plurality of covariant parameters to increase computational efficiency of the second computer, wherein controlling includes refining the identified plurality of covariant parameters to a set of causations, the set of causations comprising confirmed cause-and-effect relationships between respective setting adjustments of the one or more operational parameters and resulting performance outcomes of the one or more performance parameters, identified by the first computer through controlled testing or analysis, and usable to optimize the performance of the second computer based on external factors;
wherein the settings of the second computer include a plurality of groups of settings; and
wherein modification of the settings includes iterating through the plurality of groups of settings for the plurality of hashboards to determine a respective optimal group of settings from the plurality of groups of settings for each hashboard.