Compensation of read errors

Patent metadata

Field	Value
Publication number	US-11157352-B2
Application number	US-201916575598-A
Country	US
Kind code	B2
Filing date	Sep 19, 2019
Priority date	Oct 2, 2018
Publication date	Oct 26, 2021
Grant date	Oct 26, 2021

Abstract

A method for compensating for a read error is disclosed, wherein each of n states are read from memory cells of a memory, the states being determined in a time domain. If the n states do not form a code word of a k-from-n code, a plurality of states from the n states, which were determined within a reading window, are provided with a first valid assignment and fed to an error processing stage. If the error processing does not indicate an error, the n states are further processed with the first valid assignment, and if the error processing indicates an error, the plurality of states that were determined within the reading window are provided with a second valid assignment and the n states are further processed with the second valid assignment. Accordingly, a device, a system and a computer program product are also disclosed.

First claim

What is claimed is:

1. A method for compensating for a read error in a k-from-n code in which k bits of n bits in a valid code word have a same value and remaining n-k bits have a different value, comprising:
reading each of n states from n memory cells of a memory, respectively, during a reading window in a time domain, and
when the n states do not form a code word of the k-from-n code,
setting states of m of the n memory cells that have fastest states to respective states read during the reading window;
setting states of n-m-x of the n memory cells that have slowest states to a different state than the states of the m of the n memory cells;
setting states of x remaining memory cells to states corresponding to a first valid assignment;
feeding the n states to an error processing stage,
when the error processing stage does not indicate an error, processing the n states, and
when the error processing stage indicates an error, setting states of the x remaining memory cells to states corresponding to a second valid assignment and processing the n states with the second valid assignment.

2. The method of claim 1 , wherein the first valid assignment is a first code word and the second valid assignment is a second code word.

3. The method of claim 1 , wherein the memory cells are read in groups of n memory cells.

4. The method of claim 1 , wherein the memory cells are complementary memory cells of a complementary memory.

5. The method of claim 1 , wherein the fastest states correspond to states that have reached a first threshold value prior to the reading window and the slowest states correspond to states that have not reached a second threshold value during the reading window.

6. The method of claim 1 , determining that the n states are not a code word of the k-from-n code when at least one other fastest state is determined for a k-th fastest state during the reading window.

7. The method of claim 1 , wherein:
for k=3 a k fastest and a k−1 fastest states are determined in parallel,
for k=4 a k fastest, a k−1 fastest and a k−2 fastest states are determined in parallel, or
for k=5 a k fastest, a k−1 fastest, a k−2 fastest and a k−3 fastest states are determined in parallel.

8. The method of claim 1 , wherein the error processing comprises an error detection and/or error correction.

9. The method of claim 1 , further comprising a processing circuit functionally coupled between the memory and an error processing circuit, which is coupled to a system bus.

10. The method of claim 1 , wherein the memory comprises at least one of:
floating-gate-cells;
PCRAM,
RRAM,
MRAM,
MONOS components,
nanocrystal cells, and
ROM.

11. A device for compensating for a read error in a k-from-n code in which k bits of n bits in a valid code word have a same value and remaining n-k bits have a different value, comprising:
a memory;
a processing circuit operably coupled to the memory; and
an error processing circuit coupled to the processing circuit,
wherein the processing circuit is configured to:
read each of n states from n memory cells of the memory, respectively, during a reading window in a time domain,
when the n states do not form a code word of the k-from-n code,
set states of m of the n memory cells that have fastest states to respective states read during the reading window;
set states of n-m-x of the n memory cells that have slowest states to a different state than the states of the m of the n memory cells;

set states of x remaining memory cells to states corresponding to a first valid assignment;
feed the n states to the error processing circuit,
when the error processing circuit does not indicate an error, process the n states, and
when the error processing circuit indicates an error, set states of the x remaining memory cells to states corresponding to a second valid assignment and process the n states with the second valid assignment.

12. A device for compensating for a read error in a k-from-n code in which k bits of n bits in a valid code word have a same value and remaining n-k bits have a different value, comprising:
means for reading each of n states from n memory cells of a memory, the n states being read during a reading window in a time domain,
means for setting states of m of the n memory cells that have fastest states to respective states read during the reading window, setting states of n-m-x of the n memory cells that have slowest states to a different state than the states of the m of the n memory cells, and setting states of x remaining memory cells to states corresponding to a first valid assignment when the n states do not form a code word of the k-from-n code;
means for feeding the n states to an error processing stage when the n states do not form a code word of a k-from-n code, and
means for
further processing the n states when the error processing stage does not indicate an error,
setting states of the x remaining memory cells to states corresponding to a second valid assignment when the error processing stage indicates an error, and
further processing the n states corresponding to the second valid assignment.

13. A non-transitory computer-readable storage medium comprising instructions that when executed by a processor circuit cause the processor circuit to:
read each of n states from n memory cells of a memory, respectively, during a reading window in a time domain,
when the n states do not form a code word of a k-from-n code in which k bits of n bits in a valid code word have a same value and remaining n-k bits have a different value,
setting states of m of the n memory cells that have fastest states to respective states read during the reading window;
setting states of n-m-x of the n memory cells that have slowest states to a different state than the states of the m of the n memory cells;
setting states of x remaining memory cells to states corresponding to a first valid assignment;
feed the n states to an error processing circuit,
when the error processing circuit does not indicate an error, process the n states, and
when the error processing circuit indicates an error, setting states of the x remaining memory cells to states corresponding to a second valid assignment and process the n states with the second valid assignment.

14. The method of claim 1 , wherein k=3, n=6, x=2, and m=2.

15. The method of claim 1 , wherein m=k−1.

16. The device of claim 11 , wherein the fastest states correspond to states that have reached a first threshold value prior to the reading window and the slowest states correspond to states that have not reached a second threshold value during the reading window.

17. The device of claim 11 , wherein:
for k=3 a k fastest and a k−1 fastest states are determined in parallel,
for k=4 a k fastest, a k−1 fastest and a k−2 fastest states are determined in parallel, or
for k=5 a k fastest, a k−1 fastest, a k−2 fastest and a k−3 fastest states are determined in parallel.

18. The device of claim 11 , wherein the memory comprises at least one of:
floating-gate-cells;
PCRAM,
RRAM,
MRAM,
MONOS components,
nanocrystal cells, and
ROM.

19. The device of claim 11 , wherein k=3, n=6, x=2, and m=2.

20. The device of claim 11 , wherein m=k−1.

Assignees

• Infineon Technologies Ag

Inventors

• Kern Thomas
• Goessel Michael

Classifications

• G06F11/0751

  Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06) · CPC title

• G11C7/1006 Primary

  Data managing, e.g. manipulating data before writing or reading out, data bus switches or control circuits therefor · CPC title

• G11C13/0061

  Timing circuits or methods · CPC title

• G06F11/1004 Primary

  to protect a block of data words, e.g. CRC or checksum (G06F11/1076 takes precedence; security arrangements for protecting computers or computer systems against unauthorized activity G06F21/00) · CPC title

• G11C11/1693

  Timing circuits or methods · CPC title