US 12,405,916 B2
Nonlinear, decentralized processing unit and related systems or methodologies
Rachel St.Clair, S. Delray Beach, FL (US)
Assigned to Simuli, Inc., S. Delray Beach, FL (US)
Filed by SIMULI, INC, La Jolla, CA (US)
Filed on Nov. 30, 2023, as Appl. No. 18/524,373.
Application 18/524,373 is a continuation of application No. 17/979,573, filed on Nov. 2, 2022, granted, now 11,868,305.
Application 17/979,573 is a continuation in part of application No. 17/728,864, filed on Apr. 25, 2022, granted, now 11,569,842, issued on Jan. 31, 2023.
Prior Publication US 2024/0095207 A1, Mar. 21, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H03M 7/40 (2006.01); G06F 9/30 (2018.01); G06F 15/78 (2006.01)
CPC G06F 15/7814 (2013.01) [G06F 9/30036 (2013.01)] 3 Claims
OG exemplary drawing
 
1. An improved resource-conservative computer processor chip optimized for hypervector algebra to store, process, and losslessly retrieve information comprising:
a process flow module;
a hypervector data embedding module on-chip;
a hypervector instruction encoding module;
a hypervector desaturation module; and,
a hypervector decoding module that is on-chip;
an intelligent self-activation software to monitor when data has been associated together and stored in an on-chip record, wherein the activation software:
sequesters hypervectors that are active in a global memory;
forms suggestions and generalizations of complete datasets from available partial data;
activates sequestered hypervectors by returning them to the global memory; and,
updates the on-chip record continuously.