Memory module, memory system including the same, and error correcting method thereof

Patent metadata

Field	Value
Publication number	US-10467091-B2
Application number	US-201715689263-A
Country	US
Kind code	B2
Filing date	Aug 29, 2017
Priority date	Jan 31, 2017
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

An error correcting method of a memory system includes: reading read data and an error correction code from a plurality of memory chips; correcting an error of the read data using the error correction code; temporarily storing the read data and the error correction code in a buffer when the correcting of the error fails; writing a certain input test pattern in the plurality of memory chips, reading an output test pattern written in the plurality of memory chips, and detecting a fail chip in which a chipkill occurs; recorrecting, based on a location of the detected fail chip, the error of the read data stored in the buffer using the error correction code stored in the buffer; and rewriting error-corrected read data and the error correction code in the plurality of memory chips.

First claim

What is claimed is:

1. An error correcting method of a memory system, comprising:
reading read data and an error correction code from a plurality of memory chips;
correcting an error of the read data using the error correction code;
temporarily storing the read data and the error correction code in a buffer if the correcting of the error fails;
writing a certain input test pattern in the plurality of memory chips, reading an output test pattern written in the plurality of memory chips, and detecting a fail chip in which a chipkill occurs based on a result of comparison between the input test pattern and the output test pattern;
recorrecting, based on a location of the detected fail chip, the error of the read data stored in the buffer using the error correction code stored in the buffer; and
rewriting error-corrected read data and the error correction code in the plurality of memory chips.

2. The error correcting method of claim 1 , wherein the recorrecting of the error of the read data stored in the buffer comprises:
generating a syndrome flag by calculating a syndrome from the read data stored in the buffer using the error correction code stored in the buffer;
generating an erasure location polynomial for determining a location of an erasure symbol based on the location of the detected fail chip;
outputting a modified syndrome by multiplying the syndrome flag by the erasure location polynomial;
calculating a coefficient of an error location polynomial and a coefficient of an error evaluation polynomial using the modified syndrome;
calculating a location of the error from the error location polynomial and the error evaluation polynomial, and calculating a weight of the error at the calculated location of the error; and
correcting the error of the read data stored in the buffer based on the location of the error and the weight of the error.

3. The error correcting method of claim 1 , wherein the error correction code is a Reed-Solomon error correction code.

4. The error correcting method of claim 1 , wherein the memory system corrects the error including N-bit random error occurring in the plurality of memory chips and one chipkill error, where N is an integer of 1 or more.

5. The error correcting method of claim 1 , wherein a number of bits of the error correction code is determined by [2*(a number of correctable symbols of a location-unknown error)+(a number of correctable symbols of a location-known error)], where each of the correctable symbols is formed of M bits, M being an integer of 2 or more.

6. The error correcting method of claim 1 , wherein, when the correcting of the error succeeds, it is determined that the fail chip is not present, and the correcting of the error is terminated.

7. The error correcting method of claim 1 , wherein the certain input test pattern includes an all-zero pattern or an all-one pattern.

8. A memory system comprising:
a plurality of memory chips suitable for storing data and an error correction code;
an error correction circuit suitable for correcting an error of the data read from the plurality of memory chips using the error correction code read from the plurality of memory chips, and temporarily storing the read data and the error correction code in a buffer if the correction of the error fails; and
a fail chip detection circuit suitable for writing a certain input test pattern in the plurality of memory chips, reading an output test pattern written in the plurality of memory chips, and detecting a fail chip in which a chipkill occurs based on a result of comparison between the input test pattern and the output test pattern, if the correction of the error fails,
wherein the error correction circuit recorrects, based on a location of the detected fail chip, the error of the read data stored in the buffer using the error correction code stored in the buffer, and rewrites error-corrected read data and the error correction code in the plurality of memory chips.

9. The memory system of claim 8 , wherein the error correction circuit comprises:
a syndrome generator suitable for generating a syndrome flag by calculating a syndrome from the read data using the error correction code;
an erasure location calculator suitable for generating an erasure location polynomial for determining a location of an erasure symbol based on the location of the detected fail chip;
a multiplier suitable for outputting a modified syndrome by multiplying the syndrome flag by the erasure location polynomial;
a Berlekamp-Massey algorithm processor suitable for calculating a coefficient of an error location polynomial and a coefficient of an error evaluation polynomial using the modified syndrome;
a Chien search/Forney algorithm processor suitable for calculating a location of the error from the error location polynomial and the error evaluation polynomial, and calculating a weight of the error at the calculated location of the error; and
an error correction unit suitable for correcting the error of the read data based on the location of the error and the weight of the error.

10. The memory system of claim 8 , wherein the error correction circuit uses a Reed-Solomon error correction algorithm.

11. The memory system of claim 8 , wherein the memory system corrects the error including N-bit random error occurring in the plurality of memory chips and one chipkill error, where N is an integer of 1 or more.

12. The memory system of claim 8 , wherein a number of bits of the error correction code is determined by [2*(a number of correctable symbols of a location-unknown error)+(a number of correctable symbols of a location-known error)], where each of the correctable symbols is formed of M bits, M being an integer of 2 or more.

13. The memory system of claim 8 , wherein, when the correcting of the error succeeds, the error correction circuit determines that the fail chip is not present, and terminates the correcting of the error.

14. The memory system of claim 8 , wherein the certain input test pattern includes an all-zero pattern or an all-one pattern.

15. The memory system of claim 8 ,
wherein the error correction circuit and the fail chip detection circuit are included in a memory controller, and
wherein the plurality of memory chips are included in a memory module.

16. A memory module comprising:
a plurality of memory chips suitable for storing data and an error correction code;
an error correction circuit suitable for correcting an error of the data read from the plurality of memory chips using the error correction code read from the plurality of memory chips, and temporarily storing the read data and the error correction code in a buffer if the correction of the error fails; and
a fail chip detection circuit suitable for writing a certain input test pattern in the plurality of memory chips, reading an output test pattern written in the plurality of memory chips, and detecting a fail chip in which a chipkill occurs based on a result of comparison between the input test pattern and the output test pattern, if the correction of the error fails,
wherein the error correction circuit recorrects, based on a location of the detected fail chip, the error of the read data stored in the buffer using the error correction code stored in the buffer, and rewrites error-corrected read data and the error correction code in the plurality of memory chips.

17. The memory module of claim 16 , wherein the error correction circuit uses a Reed-Solomon error correction algorithm.

18. The memory module of claim 16 , wherein the memory module corr

Assignees

• Sk Hynix Inc

Inventors

• Park Jong-Hyun
• Lee Sung-Eun
• Koo Ja-Hyun
• Jeong Seung-Gyu

Classifications

• H03M13/1515

  Reed-Solomon codes · CPC title

• H03M13/19

  Single error correction without using particular properties of the cyclic codes, e.g. Hamming codes, extended or generalised Hamming codes · CPC title

• G11C29/4401

  for self repair · CPC title

• G11C29/42 Primary

  using error correcting codes [ECC] or parity check · CPC title

• G11C5/04

  Supports for storage elements {, e.g. memory modules}; Mounting or fixing of storage elements on such supports · CPC title