IP Library › Granted Patent US 12,481,457
Granted Patent B2
US 12,481,457 · App. 18/134,359 · Granted Nov 25, 2025

Operating method of memory device for managing map data of each of plurality of storage devices, computing system including memory device, and operating method of computing system

Inventors: Jae-Gon Lee (Suwon-si, KR); Kyunghan Lee (Suwon-si, KR); Chon Yong Lee (Suwon-si, KR)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
G06F3/0659G06F3/0625G06F3/0631G06F3/0679
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 12,481,457
App. No.
18/134,359
Granted
Nov 25, 2025
Kind
B2
Abstract

An operating method of a memory device which communicates with a first storage device and a second storage device through an interface circuit is provided. The method includes receiving, from a host device, a first request including a command and a first logical block address; obtaining, based on the first logical block address, a first physical block address with reference to first map data dedicated for the first storage device; and sending, to the first storage device through the interface circuit, a second request including the first physical block address and the command.

Claims (96)

1 . An operating method of a memory device, the operating method comprising:

receiving first map data from a first storage device, the first map data being dedicated for the first storage device;

receiving second map data from a second storage device, the second map data being dedicated for the second storage device;

storing the first map data and the second map data in a map table;

receiving, from a host device through a first interface, a first request comprising a command and a first logical block address;

obtaining, based on the first logical block address, a first physical block address with reference to the first map data for managing data stored in the first storage device; and

sending, to the first storage device through a second interface, a second request comprising the first physical block address and the command, the second interface being different from the first interface,

wherein the host device comprises a compute express link (CXL) host interface circuit,

wherein the first storage device comprises a first CXL storage interface circuit, a first NAND interface circuit, a first non-volatile memory (NVM), first map data, and first user data,

wherein the second storage device comprises a second CXL storage interface circuit, a second NAND interface circuit, a second NVM, second map data, and second user data,

wherein the memory device comprises: a CXL memory interface circuit, a memory manager, a buffer memory interface circuit, and a buffer memory,

wherein the first interface is configured to communicate with the host device via the CXL host interface circuit and the memory device via the CXL memory interface circuit, and

wherein the second interface is configured to communicate with the first storage device via the first CXL storage interface circuit using CXL.mem characterized by a memory coherency, the second storage device via the second CXL storage interface circuit using CXL.mem characterized by the memory coherency, and the memory device via the CXL memory interface circuit,

wherein the second interface is a CXL interface, and the first interface and the second interface are implemented by a CXL switch.

2 . The operating method of claim 1 , wherein the sending the second request comprises sending the second request for memory allocation to the first storage device through the second interface using the P2P communication based on a CXL protocol.

3 . The operating method of claim 1 , wherein the sending the second request comprises sending the second request, to the first storage device through the second interface, by using CXL.mem protocol, based on the CXL interface.

4 . The operating method of claim 1 , further comprising:

receiving, from the host device through the first interface, a third request comprising the command and a second logical block address;

obtaining, based on the second logical block address, a second physical block address with reference to the second map data for managing data stored in the second storage device; and

sending, to the second storage device through the second interface, a fourth request comprising the second physical block address and the command.

5 . The operating method of claim 4 , wherein a remaining capacity of the memory device, other than a capacity for storing the first map data and the second map data, is used as a memory dedicated for the host device.

6 . The operating method of claim 1 , further comprising receiving, from the first storage device through the second interface, a first read response comprising the first user data stored in an area of the first storage device, which corresponds to the first physical block address, based on sending the second request to the first storage device,

wherein the command indicates a read operation.

7 . The operating method of claim 6 , further comprising:

based on receiving the first read response, obtaining the first logical block address with reference to the first map data based on the first physical block address; and

sending, to the host device through the first interface, a second read response including the first logical block address and the first user data.

8 . The operating method of claim 1 , further comprising receiving, from the first storage device through the second interface, a first write response comprising write map data indicating that the second user data are stored in the first storage device, based on sending the second request to the first storage device,

wherein the command indicates a write operation and the first request further includes the second user data corresponding to the command.

9 . The operating method of claim 8 , further comprising:

based on receiving the first write response, updating the first map data based on the write map data;

obtaining, based on the first physical block address, the first logical block address with reference to the updated first map data; and

sending a second write response comprising the first logical block address to the host device through the first interface.

10 . The operating method of claim 9 , further comprising:

based on sending the second write response to the host device, receiving a power-off request from the host device through the first interface;

based on receiving the power-off request, sending the updated first map data to the first storage device through the second interface; and

based on receiving the power-off request, sending the second map data dedicated for the second storage device to the second storage device through the second interface.

11 . The operating method of claim 1 , wherein the receiving the first request comprises:

receiving a first initialization request from the host device through the first interface;

based on receiving the first initialization request, sending a second initialization request to the first storage device through the second interface;

based on receiving the first initialization request, sending a third initialization request to the second storage device through the second interface;

based on sending the second initialization request, receiving a first initialization response comprising first capacity information of the first storage device and the first map data through the second interface;

based on sending the third initialization request, receiving a second initialization response comprising second capacity information of the second storage device and the second map data dedicated for the second storage device through the second interface;

based on receiving the first initialization response and the second initialization response, sending a third initialization response to the host device through the first interface; and

based on sending the third initialization response, receiving the first request comprising the command and the first logical block address from the host device through the first interface.

12 . A computing system comprising:

a host device comprising a compute express link (CXL) host interface circuit;

a first storage device comprising a first CXL storage interface circuit, a first NAND interface circuit, a first non-volatile memory (NVM), first map data, and first user data;

a second storage device comprising a second CXL storage interface circuit, a second NAND interface circuit, a second NVM, second map data, and second user data;

a memory device storing a mapping table including the first map data and the second map data, the first map data being dedicated for the first storage device and for managing data stored in the first storage device and the second map data being dedicated for the second storage device and for managing data stored in the second storage device, the memory device comprising a CXL memory interface circuit, a memory manager, a buffer memory interface circuit, and a buffer memory;

a first interface configured to communicate with the host device via the CXL host interface circuit and the memory device via the CXL memory interface circuit; and

a second interface configured to communicate with the first storage device via the first CXL storage interface circuit using CXL.mem characterized by a memory coherency, the second storage device via the second CXL storage interface circuit using CXL.mem characterized by the memory coherency, and the memory device via the CXL memory interface circuit, the second interface being a compute express link (CXL) interface, wherein the first interface and the second interface are implemented by a CXL switch,

wherein the memory device is configured to:

receive, from the host device through the first interface, a first request comprising a command and a first logical block address,

obtain, based on the first logical block address, a first physical block address with reference to the first map data of the mapping table, and

send, to the first storage device through the second interface, a second request comprising the first physical block address and the command, the second interface being different from the first interface and being a compute express link (CXL) interface.

13 . The computing system of claim 12 , wherein the first storage device includes a first CXL controller configured to communicate by using a CXL protocol, the second storage device includes a second CXL controller configured to communicate by using the CXL protocol, and the memory device includes a third CXL controller configured to communicate by using the CXL protocol.

14 . The computing system of claim 12 , wherein the first storage device is configured to:

based on receiving the second request, read the first user data stored in an area corresponding to the first physical block address; and

send, to the memory device through the second interface, a first read response comprising the first user data and the first physical block address, and

wherein the command indicates a read operation.

15 . The computing system of claim 14 , wherein the memory device is further configured to:

based on receiving the first read response through the second interface, obtain the first logical block address with reference to the first map data of the mapping table based on the first physical block address; and

send, to the host device through the first interface, a second read response comprising the first logical block address and the first user data.

16 . The computing system of claim 12 , wherein the first storage device is configured to:

based on sending the second request to the first storage device, store the second user data corresponding to the command in an area corresponding to the first physical block address through the second interface; and

send, to the memory device, a first write response comprising write map data indicating that the second user data are stored in the area corresponding to the first physical block address, and

wherein the command indicates a write operation.

17 . The computing system of claim 16 , wherein the memory device is further configured to:

based on receiving the first write response the second interface, update the first map data based on the write map data;

obtain the first logical block address from the first physical block address with reference to the updated first map data; and

send, to the host device through the first interface, a second write response comprising the first logical block address.

18 . The computing system of claim 17 , wherein the memory device is further configured to:

based on sending the second write response to the host device through the first interface, receive a power-off request from the host device;

based on receiving the power-off request, send the updated first map data to the first storage device through the second interface; and

based on receiving the power-off request, send the second map data dedicated for the second storage device to the second storage device through the second interface.

19 . The computing system of claim 12 , wherein the first storage device and the second storage device are connected in a cascade structure using the second interface.

20 . A system comprising:

a first storage device comprising a first compute express link (CXL) controller configured to communicate by using a plurality of CXL protocols;

a second storage device comprising a second CXL controller configured to communicate by using the plurality of CXL protocols;

a CXL switch; and

a volatile memory device comprising a third CXL controller configured to communicate by using the plurality of CXL protocols, configured to receive a first request and a second request from a host device through a first interface, and configured to transmit, through a second interface, the first request to the first storage device and the second request to the second storage device,

wherein the second interface is a CXL interface that is different from the first interface,

wherein the volatile memory device includes a mapping table having address information for the first storage device and the second storage device,

wherein the volatile memory device is configured to transmit a first physical address to the first storage device according to the first request and a second physical address to the second storage device according to the second request, based on the mapping table,

wherein the second interface interfaces to the CXL switch,

wherein the first storage device comprises a first direct memory access (DMA) engine,

wherein the second storage device comprises a second DMA engine,

wherein the first DMA engine using a peer-to-peer protocol (P2P) communication, without interference or control from the host device, is configured to transfer first map data for managing data stored in the first storage device from the first storage device to the mapping table in a buffer of the volatile memory device, and

wherein the second DMA engine using the P2P communication is configured to transfer second map data for managing data stored in the second storage device from the second storage device to the mapping table in the buffer of the volatile memory device,

wherein the host device comprises a CXL host interface circuit,

wherein the first storage device comprises a first CXL storage interface circuit, a first NAND interface circuit, a first non-volatile memory (NVM), first map data, and first user data,

wherein the second storage device comprises a second CXL storage interface circuit, a second NAND interface circuit, a second NVM, second map data, and second user data,

wherein the volatile memory device comprises: a CXL memory interface circuit, a memory manager, a buffer memory interface circuit, and a buffer memory,

wherein the first interface is configured to communicate with the host device via the CXL host interface circuit and the volatile memory device via the CXL memory interface circuit, and

wherein the second interface is configured to communicate with the first storage device via the first CXL storage interface circuit using CXL.mem characterized by a memory coherency, the second storage device via the second CXL storage interface circuit using CXL.mem characterized by the memory coherency, and the volatile memory device via the CXL memory interface circuit, and

wherein the first interface and the second interface are implemented by a CXL switch.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 13, 2023
From: LEE, JAE-GON; LEE, KYUNGHAN; LEE, CHON YONG
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 063318/0670 →
Priority Claims (1)
KR 10-2022-0056187 · May 6, 2022 · national
Continuity (1)
Related Publication 20230359394A1 · Nov 9, 2023
References Cited (24)
US 8166202B2 · Matsuda · 2012 [cited by applicant]
US 8738888B2 · Yamada et al. · 2014 [cited by applicant]
US 10409511B1 · Subbarao · 2019 [cited by examiner]
US 10896089B2 · Helmick et al. · 2021 [cited by applicant]
US 10992751B1 · Cudak et al. · 2021 [cited by applicant]
US 11226895B2 · Lee · 2022 [cited by applicant]
US 12215509B2 · Wiesenack et al. · 2025 [cited by applicant]
US 20110099325A1 · Roh · 2011 [cited by examiner]
US 20170003889A1 · Kim et al. · 2017 [cited by applicant]
US 20180136875A1 · Nimmagadda et al. · 2018 [cited by applicant]
US 20200264985A1 · Lee · 2020 [cited by examiner]
US 20200310958A1 · Han et al. · 2020 [cited by applicant]
US 20210089225A1 · Boyd · 2021 [cited by applicant]
US 20210173785A1 · Jin · 2021 [cited by examiner]
US 20210232343A1 · Kim · 2021 [cited by examiner]
US 20210311868A1 · Chen et al. · 2021 [cited by applicant]
US 20210311871A1 · Malladi et al. · 2021 [cited by applicant]
US 20210318980A1 · Pal et al. · 2021 [cited by applicant]
US 20220100669A1 · Choe · 2022 [cited by examiner]
US 20220114087A1 · Kim · 2022 [cited by examiner]
US 20230087462A1 · Yoon · 2023 [cited by examiner]
KR 1020180054394A · 2018 [cited by applicant]
KR 1020220056187A · 2022 [cited by applicant]
Communication dated Aug. 25, 2025, issued by European Patent Office in European Patent Application No. 23171249.8. [cited by applicant]