US 12,293,796 B2
Storage system and method for implementation of symmetric tree models for read threshold calibration
Eran Sharon, Rishon Lezion (IL); Ariel Navon, Revava (IL); Alexander Bazarsky, Holon (IL); David Avraham, San Jose, CA (US); Nika Yanuka, Hadera (IL); and Idan Alrod, Herzeliya (IL)
Assigned to Sandisk Technologies, Inc., Milpitas, CA (US)
Filed by Western Digital Technologies, Inc., San Jose, CA (US)
Filed on Aug. 30, 2022, as Appl. No. 17/899,073.
Application 17/899,073 is a continuation in part of application No. 17/838,481, filed on Jun. 13, 2022, granted, now 12,283,328.
Prior Publication US 2023/0410869 A1, Dec. 21, 2023
Int. Cl. G11C 11/00 (2006.01); G11C 11/16 (2006.01); G11C 16/08 (2006.01); G11C 16/10 (2006.01); G11C 16/14 (2006.01); G11C 16/26 (2006.01); G11C 16/34 (2006.01); G11C 29/52 (2006.01); G11C 16/04 (2006.01)
CPC G11C 16/3459 (2013.01) [G11C 11/1673 (2013.01); G11C 16/08 (2013.01); G11C 16/102 (2013.01); G11C 16/14 (2013.01); G11C 16/26 (2013.01); G11C 16/3495 (2013.01); G11C 29/52 (2013.01); G11C 16/0483 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A storage system comprising:
a memory; and
a processor coupled with the memory and configured to:
input a plurality of parameters of the memory into a binary full-depth symmetrically-sorted tree, wherein:
the tree is binary in that each node of the tree either has only two child nodes or no child nodes, an internal node is a node with two child nodes, and an external node is a node with no child nodes;
the tree is full-depth in that all paths from each internal node in a given tier of the tree have a same number of nodes; and
the tree is symmetrically-sorted in that splits from each internal node to child nodes in a same tier of the tree are based on a comparison of a same one of the plurality of parameters of the memory with a same condition, wherein different tiers of the tree compare different respective ones of the plurality of parameters of the memory with different respective conditions;
perform parallel comparisons of the different respective ones of the plurality of parameters of the memory with the different respective conditions associated with each tier of the tree, wherein a comparison performed at a given tier of the tree is independent of a comparison performed at another tier of the tree;
select a read threshold from one of the external nodes of the tree, wherein each external node of the tree comprises at least one read threshold generated from performing the parallel comparisons; and
use the selected read threshold to read a wordline in the memory.