IP Library › Granted Patent US 12,499,009
Granted Patent B2
US 12,499,009 · App. 18/415,627 · Granted Dec 16, 2025

Interleaved Reed-Solomon (IRS) with collaborative decoding

Inventors: Joseph M. McCrate (Boise, ID); Kirthi Shenoy (Boise, ID); Marco Sforzin (Boise, ID); Brian M. Twait (Boise, ID)
Assignee: Micron Technology, Inc.
G06F11/1016G06F11/1004G06F11/1012G06F11/1044G06F11/1068G06F11/1072H03M13/1575H03M13/373
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 12,499,009
App. No.
18/415,627
Granted
Dec 16, 2025
Kind
B2
Abstract

Provided is a memory system comprising a plurality of memory components. The ECC decoding is configured to construct first and second codewords from a single set of data within the plurality of memory components and perform error correction code (ECC) decoding on the first and second codewords received read from the plurality of memory components wherein the ECC decoding is configured to (i) detect random errors in the first received codeword and (ii) use data associated with the detected random errors to correct erasures in the second received codeword.

Claims (37)

1 . A memory system comprising:

a plurality of memory components; and

a controller in communication with the plurality of memory components and configured to:

perform error correction code (ECC) decoding on first and second received codewords read from the plurality of memory components;

respectively calculate first and second syndromes for the first and second received codewords in parallel;

combine results of the first and second syndromes in a multiple shift register computation to generate a single set of error location polynomials (ELP);

produce a set of polynomial roots from the single set of ELPs; and

determine error magnitudes separately for each of the first and second codewords responsive to the single set of ELPs.

2 . The memory system of claim 1 , wherein the calculating corrects the first and second codewords.

3 . The memory system of claim 1 , wherein the ECC decoding includes calculating syndromes of the first and second codewords.

4 . The memory system of claim 3 , wherein the ECC decoding includes calculating error location polynomials (ELPs) from the calculated syndromes.

5 . The memory system of claim 3 , wherein the ECC decoding includes deriving polynomial root values from the calculated ELPs.

6 . The memory system of claim 1 , wherein the random errors include at least one of bit and symbol errors.

7 . The memory system of claim 1 , wherein the plurality of memory components includes dynamic random access memory (DRAM) devices.

8 . The memory system of claim 7 , wherein the memory system is constructed in accordance compute express link (CXL) principles.

9 . The memory system of claim 8 , wherein the ECC decoding is performed in accordance with Reed Solomon (RS) codes.

10 . A method comprising:

performing, via a plurality of memory components in communication with a controller, error correction code (ECC) decoding on first and second received codewords read from the plurality of memory components;

respectively calculating first and second syndromes for the first and second received codewords in parallel;

combining results of the first and second syndromes in a multiple shift register computation to generate a single set of error location polynomials (ELP);

producing a set of polynomial roots from the single set of ELPs; and

determining error magnitudes separately for each of the first and second codewords responsive to the single set of ELPs.

11 . The method of claim 10 , wherein the calculating corrects the first and second codewords.

12 . The method of claim 10 , wherein the ECC decoding includes calculating syndromes of the first and second codewords.

13 . The method of claim 12 , wherein the ECC decoding includes calculating error location polynomials (ELPs) from the calculated syndromes.

14 . The method of claim 13 , wherein the ECC decoding includes deriving polynomial root values from the calculated ELPs.

15 . The method of claim 10 , wherein the random errors include at least one of bit and symbol errors.

16 . The method of claim 10 , wherein the plurality of memory components includes dynamic random access memory (DRAM) devices.

17 . A non-transitory computer readable medium comprising computer executable instructions that, if executed by a computing device, cause the computing device to perform a method for use by a memory controller of a memory system including a plurality of memory components, the method comprising:

performing, via a plurality of memory components in communication with a controller, error correction code (ECC) decoding on first and second received codewords read from the plurality of memory components;

respectively calculating first and second syndromes for the first and second received codewords in parallel;

combining results of the first and second syndromes in a multiple shift register computation to generate a single set of error location polynomials (ELP);

producing a set of polynomial roots from the single set of ELPs; and

determining error magnitudes separately for each of the first and second codewords responsive to the single set of ELPs.

18 . The non-transitory computer readable medium of claim 17 , wherein the ECC decoding includes calculating syndromes of the first and second codewords.

19 . The non-transitory computer readable medium of claim 18 , wherein the ECC decoding includes calculating error location polynomials (ELPs) from the calculated syndromes.

20 . The non-transitory computer readable medium of claim 19 , wherein the memory system is constructed in accordance compute express link (CXL) principles.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 16, 2024
From: MCCRATE, JOSEPH M.; SHENOY, KIRTHI; SFORZIN, MARCO; TWAIT, BRIAN M.
To: MICRON TECHNOLOGY, INC.
Reel/Frame 068912/0139 →
Continuity (3)
Provisional Application 63480175 · Jan 17, 2023
Provisional Application 63480183 · Jan 17, 2023
Related Publication 20240296090A1 · Sep 5, 2024
References Cited (12)
US 5850405A · Wimmer · 1998 [cited by examiner]
US 5878058A · Im · 1999 [cited by examiner]
US 6122766A · Fukuoka · 2000 [cited by examiner]
US 9755667B1 · Chen · 2017 [cited by examiner]
US 20100131824A1 · Kolze · 2010 [cited by examiner]
US 20100253555A1 · Weingarten · 2010 [cited by examiner]
US 20100299580A1 · Neznanov · 2010 [cited by examiner]
US 20130104007A1 · Northcott · 2013 [cited by examiner]
US 20140032990A1 · Goettfert · 2014 [cited by examiner]
US 20200019460A1 · Cadloni · 2020 [cited by examiner]
“Decoding of parallel Reed-Solomon codes with applications to product and concatenated codes” by Krachkovsky Published by Proceedings. 1998 IEEE International Symposium on Information Theory https://ieeexplore.ieee.org/… [cited by examiner]
A Low-Complexity Reed-Solomon Decoder by Jiang Published in: 2008 4th IEEE International Conference on Circuits and Systems for Communications https://ieeexplore.ieee.org/document/4536759?source=IQplus (Year: 2008). [cited by examiner]