IP Library Granted Patent US 12,189,946
Granted Patent B2
US 12,189,946 · App. 18/120,114 · Granted Jan 7, 2025

Data reduction device, data reduction method, and system including data reduction device

Inventors: Wonsik Lee (Seoul, KR); Jangwoo Kim (Seoul, KR)
Assignee: MangoBoost, Inc.
G06F3/0608G06F3/0644G06F3/0683
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 12,189,946
App. No.
18/120,114
Granted
Jan 7, 2025
Kind
B2
Abstract

A data reduction device, a data reduction method, and a system including the data reduction device are provided. The data reduction device includes a control module configured to generate a control signal in response to a first kernel request received from an external entity, a direct memory access (DMA) engine configured to read request data corresponding to the first kernel request from an external entity in response to the control signal, and a data reduction core configured in such a manner that the request data is reduced through a first operation to be generated first reduction data or the first reduction data is reduced through a second operation to be generated as second reduction data.

Claims (36)

1. A data reduction device comprising:

a circuitry configured to:

generate a control signal in response to a first kernel request received from an external entity;

read requested data corresponding to the first kernel request from an external entity in response to the control signal; and

reduce the requested data as a first reduction data by performing a first operation that is an offloaded operation corresponding to the first kernel request, and reduce the first reduction data as a second reduction data by performing a second operation when the first reduction data is a unique value.

2. The data reduction device of claim 1 , wherein the first operation is a hash operation.

3. The data reduction device of claim 1 , wherein the second operation is a compression operation.

4. The data reduction device of claim 1 , wherein the circuitry is further configured to control the second operation in response to a second kernel request received from the external entity.

5. The data reduction device of claim 1 , wherein the circuitry is further:

configured to schedule performance of the first operation and the second operation.

6. The data reduction device of claim 1 , wherein the circuitry performs the first operation and the second operation in parallel.

7. The data reduction device of claim 6 , wherein the circuitry performs the first or second operation separately for a respective external storage device.

8. The data reduction device of claim 1 , the circuitry is further configured to generate an interrupt signal when a predetermined number of the first kernel request or a second kernel request received from the external entity is processed.

9. The data reduction device of claim 1 , which is implemented as a chip or a card.

10. A system comprising:

a central processing unit (CPU) configured to generate a first host request;

a system memory into which requested data corresponding to the first host request is loaded; and

a data reduction device configured to reduce the requested data as a first reduction data by performing a first operation, and to reduce the first reduction data as a second reduction data by performing a second operation when the first reduction data is a unique value, in response to kernel requests corresponding to the first host request.

11. The system of claim 10 , wherein the first operation is a hash operation, and the second operation is a compression operation.

12. The system of claim 10 , wherein the data reduction device comprises a circuitry

configured to;

receive a first kernel request among the kernel requests to generate a control signal;

read the requested data from the system memory in response to the control signal; and

execute at least one arithmetic logic corresponding to the first operation or the second operation.

13. The system of claim 12 , wherein the circuitry is further:

configured to schedule performance of the first operation and the second operation.

14. The system of claim 12 , wherein the circuitry is further:

configured to generate an interrupt signal when a predetermined number of the first kernel request or a second kernel request among the kernel requests are processed.

15. The system of claim 10 , wherein the first host request is hooked to generate first and second kernel requests among the kernel requests, and the data reduction device performs the first operation in response to the first kernel request and performs the second operation in response to the second kernel request.

16. The system of claim 10 , wherein the first kernel requests comprise a type of the first or second operation, a size of data, a source address for the requested data and a destination address for the first or second reduction data.

17. A data reduction method comprising:

offloading a hash operation on requested data corresponding to a first host request, by a data reduction device;

outputting a result of the hash operation as a first device response corresponding to the first host request when the result of the hash operation is not a unique value, by the data reduction device;

and offloading a compression operation on the result of the hash operation when the result of the hash operation is a unique value, by the data reduction device.

18. The data reduction method of claim 17 , further comprising:

offloading a decompression operation on requested data corresponding to a second host request by the data reduction device.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 28, 2024
From: MANGOBOOST KOREA, INC.; SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION
To: MANGOBOOST, INC.
Reel/Frame 069333/0001 →
CHANGE OF NAME Recorded Sep 16, 2024
From: MANGOBOOST INC.
To: MANGOBOOST KOREA, INC.
Reel/Frame 068956/0666 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 7, 2023
From: MANGOBOOST INC.
To: MANGOBOOST INC.; SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION
Reel/Frame 065798/0358 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 5, 2023
From: KIM, JANGWOO
To: MANGOBOOST INC.
Reel/Frame 065769/0737 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 10, 2023
From: LEE, WONSIK
To: MANGOBOOST INC.
Reel/Frame 063279/0262 →
Priority Claims (2)
KR 10-2022-0135962 · Oct 20, 2022 · national
KR 10-2022-0190624 · Dec 30, 2022 · national
Continuity (2)
Related Publication 20240134521A1 · Apr 25, 2024
Related Publication 20240231613A9 · Jul 11, 2024
References Cited (18)
US 6185640B1 · Ross · 2001 [cited by examiner]
US 9659060B2 · Chambliss · 2017 [cited by examiner]
US 11321010B1 · Jiang · 2022 [cited by examiner]
US 11409667B1 · Ippatapu · 2022 [cited by examiner]
US 20160274792A1 · Ogawa · 2016 [cited by examiner]
US 20170293450A1 · Battaje · 2017 [cited by examiner]
US 20180188974A1 · Cayton · 2018 [cited by examiner]
US 20180335956A1 · Iyer · 2018 [cited by examiner]
US 20190286333A1 · Tsuda · 2019 [cited by examiner]
US 20210019066A1 · Li · 2021 [cited by examiner]
US 20220405220A1 · Zhou · 2022 [cited by examiner]
US 20230229773A1 · Madden, Jr. · 2023 [cited by examiner]
KR 20140094468A · 2014 [cited by examiner]
KR 20170054299A · 2017 [cited by examiner]
KR 1020190041954A · 2019 [cited by applicant]
KR 20200024193A · 2020 [cited by examiner]
WO WO2015180649A1 · 2015 [cited by examiner]
Mohammadamin Ajdari et al. “CIDR: A Cost-Effective In-Line Data Reduction System for Terabit-Per-Second Scale SSD Arrays”, 2019 IEEE International Symposium on HPCA, Mar. 28, 2019. [cited by applicant]