IP Library Granted Patent US 12,436,880
Granted Patent B2
US 12,436,880 · App. 18/545,561 · Granted Oct 7, 2025

Selective single-level memory cell operation

Inventor: Donghua Zhou (Suzhou, CN)
Assignee: Micron Technology, Inc.
G06F12/0246G06F2212/7206
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 12,436,880
App. No.
18/545,561
Granted
Oct 7, 2025
Kind
B2
Abstract

A method includes selectively configuring a first subset of non-volatile memory blocks to operate in a single-level mode, configuring the first subset of non-volatile memory blocks to collectively operate as a pseudo single-level cache, writing data associated with performance of a memory operation to the first subset of non-volatile memory blocks, and migrating the data from the first subset of non-volatile memory blocks to a second subset of non-volatile memory blocks.

Claims (40)

1. A method comprising:

configuring a first subset of non-volatile memory blocks of a non-volatile memory to collectively operate as a pseudo single-level cache responsive to detection of a backup power supply failure event;

writing data associated with a memory operation to the first subset of non-volatile memory blocks configured as the pseudo single-level cache; and

migrate the data from the first subset to a second subset of non-volatile memory blocks of the non-volatile memory.

2. The method of claim 1 , further comprising selectively configuring the first subset of non-volatile memory blocks to operate in a single-level mode responsive to detection of an asynchronous power loss (APL) event.

3. The method of claim 2 , further comprising selectively configuring free non-volatile memory blocks to operate in the single-level mode.

4. The method of claim 3 , further comprising:

maintaining a quantity of blocks in a free block pool that is equal to or greater than a target quantity of blocks; and

selectively configuring, from the free block pool, the free non-volatile memory blocks to operate in the single-level mode until a quantity of blocks in the first subset of non-volatile memory blocks is equal to the target quantity of blocks.

5. The method of claim 1 , further comprising determining a target quantity block in the first subset of non-volatile memory blocks based on an expected operational lifetime of the first subset of non-volatile memory blocks, the second subset of non-volatile memory blocks, or both.

6. The method of claim 1 , further comprising determining, based on comparison of an expected operational lifetime of the second subset of non-volatile memory blocks, a target quantity of the first subset of non-volatile memory blocks.

7. The method of claim 1 , further comprising designating, based on an expected operation lifetime of the first subset of non-volatile memory blocks being equal to an expected operational lifetime of the second subset of non-volatile memory blocks, a target quantity of the first subset of non-volatile memory blocks.

8. The method of claim 2 , wherein selectively configuring the first subset of non-volatile memory blocks to operate in the single-level mode further comprises generating a target quantity of the first subset of non-volatile memory blocks subsequent to detection of the backup power supply failure event.

9. The method of claim 1 , further comprising writing data, associated with performance of a plurality of memory operations, to sequential blocks of non-volatile memory included in the first subset of non-volatile memory blocks.

10. An apparatus, comprising:

a volatile memory;

a non-volatile memory comprising non-volatile memory blocks; and

a controller configured to:

responsive to detection of a backup power supply failure event, selectively configure a first subset of non-volatile memory blocks of the non-volatile memory to operate in a single-level mode; and

in response to receipt of signaling indicative of an access request from a host:

write data associated with a memory operation to the volatile memory;

write the data from the volatile memory to the first subset of non-volatile memory blocks; and

migrate the data from the first subset of non-volatile memory blocks to a second subset of non-volatile memory blocks of the non-volatile memory.

11. The apparatus of claim 10 , wherein the controller is further configured to responsive to detection of the backup power supply failure event, selectively configure the first subset of non-volatile memory blocks to operate as a pseudo single-level cache.

12. The apparatus of claim 11 , wherein the controller is to configure the first subset of non-volatile memory blocks to a multi-level mode in an absence of a detection of the backup power supply failure event.

13. The apparatus of claim 10 , wherein the first subset of the non-volatile memory blocks has a respective block size that is less than a respective block size of the second subset of non-volatile memory blocks.

14. The apparatus of claim 10 , wherein the first subset of non-volatile memory blocks have a page size that is less than a page size of the second subset of non-volatile memory blocks.

15. The apparatus of claim 10 , wherein a sum of a first quantity of the first subset of non-volatile memory blocks and a second quantity of the second subset of non-volatile memory blocks is equal to a total block count of the non-volatile memory.

16. A system comprising:

a volatile memory; and

a non-volatile memory; and

a processing device to perform operations comprising:

operate the volatile memory in accordance with a write-back cache policy;

configure a first portion of the non-volatile memory to operate in a single-level mode as a pseudo single-level cache responsive to detection of a backup power supply failure event;

write data from the volatile memory to the first portion of the non-volatile memory configured to operate as the pseudo single-level cache; and

responsive to a threshold amount of data being written to the first portion of the non-volatile memory, internally migrate the data from the first portion of the non-volatile memory to a second portion of the non-volatile memory.

17. The system of claim 16 , wherein blocks in the first portion of the non-volatile memory are configured to operate collectively as the pseudo single-level cache by being assigned consecutive block index numbers.

18. The system of claim 16 , wherein the non-volatile memory is comprised of multi-level cells, triple level cells, quad-level cells, or penta-level cells.

19. The system of claim 16 , wherein the threshold amount of data is equal to a page size of a page included in a non-volatile memory block in the second portion of the non-volatile memory.

20. The system of claim 16 , wherein the processing device is further to operate the volatile memory in accordance with a write-through cache policy responsive to a detection of the backup power supply failure event.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: ZHOU, DONGHUA
To: MICRON TECHNOLOGY, INC.
Reel/Frame 066089/0140 →
Continuity (2)
Continuation 17824725 · May 25, 2022
Related Publication 20240134788A1 · Apr 25, 2024
References Cited (13)
US 7363520B1 · Maier, Jr. · 2008 [cited by examiner]
US 8482993B2 · Strasser et al. · 2013 [cited by applicant]
US 10248317B2 · Yano et al. · 2019 [cited by applicant]
US 10324843B1 · Erel · 2019 [cited by examiner]
US 11182105B2 · Lee et al. · 2021 [cited by applicant]
US 20120250408A1 · Takeyama et al. · 2012 [cited by applicant]
US 20160211035A1 · Shapira · 2016 [cited by examiner]
US 20170277245A1 · Paley · 2017 [cited by examiner]
US 20200194075A1 · Igahara et al. · 2020 [cited by applicant]
US 20200293221A1 · Jang et al. · 2020 [cited by applicant]
US 20200342945A1 · Sarkar et al. · 2020 [cited by applicant]
US 20210011818A1 · Kim · 2021 [cited by examiner]
US 20220253239A1 · Jang et al. · 2022 [cited by applicant]