# US 2016/0365876 A1 · Use of error correcting code to carry additional data bits

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0365876 A1
- Document ID: US20160365876A1
- Status: Published application
- Kind: A1
- Application number: 14/740,100
- Filed: 2015-06-15
- Published: 2016-12-15
- Earliest claimed: 2015-06-15
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Daniel Greenspan; Asaf Rubinstein; Julius Yuli Mandelblat
- Web page: https://patentgrep.com/patent/US20160365876A1

## CPC

- H03M 13/2942: {wherein a block of parity bits is computed only from combined information bits or only from parity bits, e.g. a second block of parity bits is computed from a first block of parity bits obtained by systematic encoding of a block of information bits, or a block of parity bits is obtained by an XOR combination of sub-blocks of information bits}
- G06F 11/1076: {Parity data used in redundant arrays of independent storages, e.g. in RAID systems}
- H03M 13/05: using block codes, i.e. a predetermined number of check bits joined to a predetermined number of information bits {(H03M13/2906 takes precedence)}
- H03M 13/451: {using a set of candidate code words, e.g. ordered statistics decoding [OSD]}
- H03M 13/19: Single error correction without using particular properties of the cyclic codes, e.g. Hamming codes, extended or generalised Hamming codes
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Integrated circuits, systems and methods are disclosed in which data bits protected by error correction code (ECC) detection and correction may be increased such that a combination of primary and additional bits may also be ECC protected using existing ECC allocation, without affecting ECC capabilities. For example, the additional bits may be encoded into phantom bits that are in turn used in combination with the primary bits, to generate an ECC. This ECC may then be combined with the primary bits to form a code word. The code word may be transmitted (or stored) so that when the data bits are received (or retrieved), assumed values of the phantom bits may be decoded, using the ECC, back into the additional bits without the phantom bits or the additional bits ever having transmitted (or stored).

## Claims

### Claim 1

An integrated circuit comprising:
a data encoding circuit to prepare data for error correction, the data encoding circuit further to:
receive a plurality of first data bits;
receive a plurality of second data bits; and
generate an error correcting code (ECC) from a combination of the plurality of first data bits and a plurality of third data bits derived from a conversion of the plurality of second data bits,
processing logic to form a code word from a combination of the ECC and the plurality of first data bits;
wherein a first combination of the plurality of second data bits enables correction of single bit errors and detection of double bit errors in the code word, and
wherein a plurality of other combinations of the plurality of second data bits enables detection of single bit errors in the code word.

### Claim 2 (depends on 1)

The integrated circuit of claim 1, wherein the plurality of second data bits comprises additional bits to be encoded within the ECC for later decoding, and wherein the processing logic further to transmit the plurality of first data bits with the code word.

### Claim 3 (depends on 1)

The integrated circuit of claim 1, wherein the data encoding circuit further comprises an encoder to convert the plurality of second data bits to the plurality of third data bits.

### Claim 4 (depends on 1)

The integrated circuit of claim 1, wherein the data encoding circuit further comprises an error correcting code (ECC) generator to:
generate the ECC; and
transmit the ECC to be combined with the plurality of first data bits.

### Claim 5 (depends on 1)

The integrated circuit of claim 1, wherein the first combination comprises the plurality of second data bits being all zero (“0”), and wherein the plurality of other combinations comprises at least one bit of the plurality of second bits being a one (“1”).

### Claim 6

An integrated circuit comprising a data decoding circuit to detect and correct errors in data following reception of transmitted data, wherein the data decoding circuit to:
receive a first code word, wherein the first code word is derived from: a plurality of first data bits, a plurality of second data bits, and an error correcting code algorithm;
generate a second code word from the first code word by appending, to the first code word, assumed values of a plurality of third data bits, wherein the plurality of third data bits were derived from a conversion of the plurality of second data bits during data encoding;
correct single bit errors and detect double bit errors in a first code word portion of the second code word for a first combination of the plurality of third data bits and the plurality of first data bits;
detect single bit errors in the first code word portion of the second code word for a plurality of other combinations of the plurality of third data bits and the plurality of first data bits; and
derive from the second code word, as corrected, the plurality of first data bits and the plurality of second data bits.

### Claim 7 (depends on 6)

The integrated circuit of claim 6, wherein the data decoding circuit further to derive from the second code word, as corrected, indications of correctable errors and uncorrectable errors within the second code word.

### Claim 8 (depends on 6)

The integrated circuit of claim 6, wherein the first combination comprises the plurality of third data bits being all zero (“0”), and wherein the plurality of other combinations comprises one bit of the plurality of third data bits being a one (“1”).

### Claim 9 (depends on 6)

The integrated circuit of claim 6, wherein the first code word comprises a received version of the plurality of first data bits and an error correcting code (ECC) generated from a combination of the plurality of first data bits and the plurality of third data bits, wherein the assumed values are values for the plurality of third data bits within the first combination, and wherein the data decoding circuit further to:
execute error detection and correction, using the ECC, on the second code word; and
output the second code word, as corrected.

### Claim 10 (depends on 9)

The integrated circuit of claim 9, wherein, to execute the error detection and correction, the data decoding circuit further to:
correct any single bit errors and detect any double bit errors in the first code word portion when values of the plurality of third data bits correspond to those of the first combination; and
detect single bit errors in the first code word portion when the values of the plurality of third data bits correspond to those of one of the plurality of other combinations.

### Claim 11 (depends on 9)

The integrated circuit of claim 9, wherein the data decoding circuit further comprises a decoder to:
decode the plurality of second data bits from the plurality of third data bits, as corrected, wherein the plurality of second data bits are additional bits to be transmitted to a data requesting component with the plurality of first data bits; and
output the plurality of second data bits with the plurality of first data bits in response to a data request.

### Claim 12

A system on a chip (SoC) comprising:
a data encoding circuit to prepare data for error correction when being stored in memory, the data encoding circuit to:
receive a plurality of first data bits and a plurality of second data bits;
derive a plurality of third data bits from the plurality of second data bits;
generate an error correcting code (ECC) from the combination of the plurality of first data bits and the plurality of third data bits; and
output, to store in the memory, a first code word comprising the ECC and the plurality of first data bits;
a data decoding circuit to perform error correction on the data read from the memory, the data decoding circuit to:
retrieve, from the memory, the first code word;
generate a second code word from the first code word by appending, to the first code word, assumed values of the plurality of third data bits;
using the ECC, correct single bit errors and detect double bit errors in a first code word portion of the second code word for a first combination of the plurality of third data bits and the plurality of first data bits;
detect, using the ECC, single bit errors in the first code word portion of the second code word for a plurality of other combinations of the plurality of third data bits and the plurality of first data bits; and
derive from the second code word, as corrected, the plurality of first data bits and the plurality of second data bits.

### Claim 13 (depends on 12)

The SoC of claim 12, wherein the assumed values correspond to values of the plurality of third data bits within the first combination.

### Claim 14 (depends on 12)

The SoC of claim 12, wherein the data decoding circuit further to derive from the second code word, as corrected, indications of correctable errors and uncorrectable errors within the code word.

### Claim 15 (depends on 12)

The SoC of claim 12, wherein the data encoding circuit further comprises an encoder to convert the plurality of second data bits to the plurality of third data bits, and the plurality of second data bits comprise additional bits to also be provided in response to a read request for the plurality of first data bits.

### Claim 16 (depends on 15)

The SoC of claim 15, wherein the plurality of first data bits and the plurality of second data bits comprise tag bits for memory address metadata.

### Claim 17 (depends on 15)

The SoC of claim 15, wherein the data decoding circuit further comprises a decoder to:
decode the plurality of second data bits from the plurality of third data bits; and
output the plurality of second data bits with the plurality of first data bits in response to the read request.

### Claim 18 (depends on 17)

The SoC of claim 17, wherein a zero output value of the plurality of second data bits is recreated as a NOR of the plurality of third data bits in the encoder.

### Claim 19 (depends on 12)

The SoC of claim 12, wherein the first combination comprises the plurality of third data bits being all zero (“0”), and wherein the plurality of other combinations comprises one bit of the plurality of third data bits being a one (“1”).

### Claim 20

A method comprising:
receiving, by a data encoding circuit that prepares data for error correction before transmission, a plurality of first data bits and a plurality of second data bits;
converting the plurality of second data bits to a plurality of third data bits;
generating, by the data encoding circuit, an error correcting code (ECC) from a combination of the plurality of first data bits and the plurality of third data bits; and
transmitting, by processing logic, a first code word comprising the ECC and the plurality of first data bits in response to a data request;
wherein a first combination of the plurality of third data bits and the plurality of first data bits enables, through use of the ECC, correction of single bit errors and detection of double bit errors in the code word, and
wherein a plurality of other combinations of the plurality of third data bits and the plurality of first data bits enables, through use of the ECC, detection of single bit errors in the code word.

### Claim 21 (depends on 20)

The method of claim 20, wherein the data bits comprise cache metadata related to storage in cache memory, the method further comprising transmitting the code word to a data requesting component.

### Claim 22 (depends on 20)

The method of claim 20, further comprising:
receiving, by a data decoding circuit in response to the data request, the code word, wherein the code word is a first code word;
generating a second code word from the first code word by appending, to the first code word, assumed values of the plurality of third data bits;
correcting, by the data decoding circuit using the ECC, single bit errors in a first code portion of the second code word and detecting, by the data decoding circuit using the ECC, double bit errors in the first code portion of the second code word for the first combination;
detecting, by the data decoding circuit using the ECC, single bit errors in the first code portion of the second code word for the plurality of other combinations; and
deriving, from the second code word as corrected by the data decoding circuit, the plurality of first data bits and the plurality of third data bits.

### Claim 23 (depends on 22)

The method of claim 22, further comprising:
decoding, by the data decoding circuit, the plurality of second data bits from the plurality of third data bits, the plurality of second data bits comprising additional bits to be provided with the plurality of first data bits; and
outputting the plurality of second data bits with the plurality of first data bits in response to the data request.

### Claim 24 (depends on 20)

The method of claim 20, wherein the first combination comprises the plurality of third data bits being all zero (“0”), and wherein the plurality of other combinations comprises one bit of the plurality of third data bits being a one (“1”).
