CN104378120A - Hsiao coding check matrix generation method for continuous MBU detection - Google Patents
Hsiao coding check matrix generation method for continuous MBU detection Download PDFInfo
- Publication number
- CN104378120A CN104378120A CN201410649686.7A CN201410649686A CN104378120A CN 104378120 A CN104378120 A CN 104378120A CN 201410649686 A CN201410649686 A CN 201410649686A CN 104378120 A CN104378120 A CN 104378120A
- Authority
- CN
- China
- Prior art keywords
- column vector
- check matrix
- search
- vector
- continuous
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a Hsiao coding check matrix generation method for continuous MBU detection. The Hsiao coding check matrix generation method includes the steps that firstly, the needed check code bit wide L is determined according to the Hamming inequality, column vectors based on L-bit check codes and meeting column vector rules are listed to form searching space, and priority ranking is carried out on the searching space according to the number of 1 in the column vectors; a check matrix is initialized, according to continuous overturning bit ineeding to be actually detected, a searching function and a discrimination function are adopted for obtaining the legal column vectors from the high-priority searching space as many as possible, the legal column vectors are supplemented into the check matrix, and finally the check matrix meeting the requirements is generated. Based on an error correcting and detecting circuit of the check matrix, on the premise that delay of a traditional SEC-DED checking circuit is not increased, continuous multi-bit data overturning can be detected, an MBU of Cache of a processor for astronavigation is responded, and the Hsiao coding check matrix generation method is suitable for Cache reliability strengthening scheme.
Description
Technical field
The invention belongs to aerospace purpose processor reliability field, relate to a kind of Hsiao coding checkout matrix generating method detected for continuous N BU.
Background technology
In contemporary processor and SoC chip, in-line memory area is respectively more than 30% with 60%, and therefore the reliability of on-chip memory is most important.Due to the impact of space single particle effect, the data in aerospace purpose processor Cache easily overturn, and along with integrated circuit technology progress, error pattern overturns (SBU) by traditional unit to be developed to Multiple-bit upsets (MBU).Space and the experiment of ground single-particle find, heavy particle can cause the upset of 10 ~ 15 Coutinuous store positions in 90nm SRAM (continuous Multiple-bit upsets is the key character of MBU).Based on this, in current slice, mainly to rely on high-order error correcting code (as RS, BCH code etc.) to realize system-level fault-tolerant for memory bank, high-order error correcting code has the ability of correcting and detecting Multiple-bit upsets, but its checking procedure is complicated, encoding and decoding in checking procedure often need several clock cycle, therefore use high-order error correcting code greatly can extend the read and write access cycle of memory.The read and write access cycle of Cache can have a strong impact on processor performance, and the high latency characteristic of high-order error correcting code makes it cannot be applied in the reinforcement protection scheme of Cache.
In order to reduce the read-write cycle of Cache to the full extent; usual employing SEC-DED coding or parity check etc. postpone less Scheme of Strengthening and protect Cache data; when processor finds that Cache data exist correctable error; then correct; when find not correctable error time; then force Cache not hit, from main memory, read the corresponding data copy of Cache.But SEC-DED or parity check all can not successfully manage the MBU phenomenon in Cache, namely cannot recover or the continuous Multiple-bit upsets of data in Cache memory cell that detection space single-particle causes, once Cache data cannot 100% recovery or detect Data flipping, processor will use instruction or data that continuous Multiple-bit upsets occurs, may cause unpredictable situations such as " race fly ".
In order to tackle the MBU problem of aerospace purpose processor Cache, a kind of low delay must be constructed, can correct or detect the error correcting code of continuous Multiple-bit upsets, based on the EDAC circuit of this error correcting code under the prerequisite not increasing Cache access delay, ensure the reliability of Cache data, maintain the reliability service of aerospace purpose processor.
Summary of the invention
The object of the invention is to the shortcoming overcoming above-mentioned prior art, provide a kind of Hsiao coding checkout matrix generating method detected for continuous N BU, the arbitrary column vector in the Hsiao coding checkout matrix that the method generates meets Hsiao coding criterion to facilitate delay of optimizing hardware.
For achieving the above object, the Hsiao coding checkout matrix generating method for continuous N BU detection of the present invention comprises the steps:
1) according to Hamming inequality 2
r>=k+r+1 determines the check code bit wide r needed for the information bit of k position;
2) list all L dimensional vectors meeting Hsiao coding criterion, described L dimensional vector sum equals
2n+1 is the number of binary one in L dimensional vector, according in L dimensional vector 1 number belonged to search volume A
2n+1, described search volume A
2n+1comprise
individual L dimensional vector, n be integer and
3) the binary system check matrix C of initialization L × M dimension, wherein, front k the column vector of M=k+L, binary system check matrix C is null vector, and a rear L column vector is made up of L rank unit matrix, then the column vector form of binary system check matrix C is C=[d
1d
2d
kc
1c
l];
4) judge the required continuous overturning figure place i detected, as the continuous overturning figure place i≤L+1 of required detection, then determine search function Func1 and search function Func2, wherein, search function Func1 ensures from search volume A
2n+1in the new vectorial b of middle taking-up and binary system check matrix C, already present arbitrary column vector does not repeat, and search function Func2 ensures from search volume A
2n+1l the column vector linear independence that the new vectorial b of middle taking-up is adjacent in binary system check matrix C with it, wherein, l ∈ [3, i], from search volume A
2n+1the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into the correspondence position of binary system check matrix C with the null vector in alternative initialization, obtains Hsiao coding checkout matrix;
5) as the continuous overturning figure place i > L+1 of required detection, then the check matrix C that can detect L+1 position continuous overturning is generated
1, determine decision function Func3, by decision function Func3 to check matrix C
1detect, judge check matrix C
1x column vector of middle arbitrary continuation whether linear correlation, wherein, x ∈ [L+2, i], when x column vector linear correlation of arbitrary continuation, then to search volume A
2n+1in column vector random alignment, the position of random inversion column vector;
6) step 5 is repeated) until check matrix C
1till meeting x column vector linear independence of arbitrary continuation, then Matrix C will be verified
1assignment, to check matrix C, obtains Hsiao coding checkout matrix.
Described search function Func1 meets all column vectors in traversal binary system check matrix C, any one column vector and search volume A
2n+1the new vectorial b of middle taking-up is all not identical.
Described search function Func2 meets from A
2n+1the new vectorial b of middle taking-up can be filled in any row in binary system check matrix C in 1st ~ kth row; Simultaneously, the column vector index p of search function Func2 to successively decrease i from M-(L-i+1), for M-(L-i+1) to any one the column vector index p in i, get i-1 the column vector comprising column vector p, by a described i-1 column vector from search volume A
2n+1search legal new vectorial b, and ensure l column vector linear independence of arbitrary neighborhood in a described i-1 column vector and new vectorial b.
The searchable index r that described decision function Func3 meets decision function Func3 is incremented to M-i+1 from 1, from the column vector that the searchable index r of any one function F unc3 that determines is corresponding, get a continuous drawing i column vector, decision function Func3 can meet x column vector linear independence of arbitrary neighborhood in this i vector.
Step 4) described in from search volume A
2n+1the correspondence position that the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into binary system check matrix C with the concrete operations of the null vector in alternative initialization is: search function Func2 is first from the A of high priority
3search for, work as A
3cannot meet, then A be expanded in search volume
2n+1for A
3+ A
5, work as A
3+ A
5still cannot meet, then once expand search volume A gradually
2n+1, until binary system check matrix C changes into do not tie up matrix containing the L × M of null vector.
The present invention has following beneficial effect:
Hsiao coding checkout matrix generating method for continuous N BU detection of the present invention first determines required check code bit wide according to Hamming inequality, then lists based on L bit check code and the column vector formation search volume A meeting Hsiao coding criterion
2n+1, and according in column vector 1 number to search volume A
2n+1priority arrangement, secondly initiation verification matrix, the continuous overturning figure place i detected according to actual needs utilizes search function and discriminant function to obtain legal column vector from high priority search volume to add to check matrix respectively as far as possible, obtain Hsiao coding checkout matrix, in the Hsiao coding checkout matrix that the present invention generates, arbitrary column vector all meets Hsiao coding criterion to facilitate hardware optimization, based on described Hsiao coding checkout matrix can design surface to the EDAC circuit of aerospace purpose processor Cache, when there is upset in data in EDAC electric circuit inspection to Cache, Cache is then forced not hit, force Cache controller to main memory request msg to processor transmission, and the Data Update Cache using main memory to return realizes the correction of Cache misdata, this EDAC circuit does not increase the delay of traditional SEC-DED checking circuit, the application of suitable Cache reliability Scheme of Strengthening.
Accompanying drawing explanation
Fig. 1 is check matrix generating method flow chart of the present invention.
Embodiment
Below in conjunction with specific embodiment and accompanying drawing, the present invention is described in further detail,
Hsiao coding checkout matrix generating method for continuous N BU detection of the present invention comprises the steps:
1) according to Hamming inequality 2
r>=k+r+1 determines the check code bit wide r needed for the information bit of k position;
2) list all L dimensional vectors meeting Hsiao coding criterion, described L dimensional vector sum equals
2n+1 is the number of binary one in L dimensional vector, according in L dimensional vector 1 number belonged to search volume A
2n+1, described search volume A
2n+1comprise
individual L dimensional vector, n be integer and
3) the binary system check matrix C of initialization L × M dimension, wherein, front k the column vector of M=k+L, binary system check matrix C is null vector, and a rear L column vector is made up of L rank unit matrix, then the column vector form of binary system check matrix C is C=[d
1d
2d
kc
1c
l];
4) judge the required continuous overturning figure place i detected, as the continuous overturning figure place i≤L+1 of required detection, then determine search function Func1 and search function Func2, wherein, search function Func1 ensures from search volume A
2n+1in the new vectorial b of middle taking-up and binary system check matrix C, already present arbitrary column vector does not repeat, and search function Func2 ensures from search volume A
2n+1l the column vector linear independence that the new vectorial b of middle taking-up is adjacent in binary system check matrix C with it, wherein, l ∈ [3, i], from search volume A
2n+1the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into the correspondence position of binary system check matrix C with the null vector in alternative initialization, obtains Hsiao coding checkout matrix;
5) as the continuous overturning figure place i > L+1 of required detection, then the check matrix C that can detect L+1 position continuous overturning is generated
1, determine decision function Func3, by decision function Func3 to check matrix C
1detect, judge check matrix C
1x column vector of middle arbitrary continuation whether linear correlation, wherein, x ∈ [L+2, i], when x column vector linear correlation of arbitrary continuation, then to search volume A
2n+1in column vector random alignment, the position of random inversion column vector;
6) step 5 is repeated) until check matrix C
1till meeting x column vector linear independence of arbitrary continuation, then Matrix C will be verified
1assignment, to check matrix C, obtains Hsiao coding checkout matrix.
Described search function Func1 meets all column vectors in traversal binary system check matrix C, any one column vector and search volume A
2n+1the new vectorial b of middle taking-up is all not identical.
Described search function Func2 meets from A
2n+1the new vectorial b of middle taking-up can be filled in any row in binary system check matrix C in 1st ~ kth row; Simultaneously, the column vector index p of search function Func2 to successively decrease i from M-(L-i+1), for M-(L-i+1) to any one the column vector index p in i, get i-1 the column vector comprising column vector p, by a described i-1 column vector from search volume A
2n+1search legal new vectorial b, and ensure l column vector linear independence of arbitrary neighborhood in a described i-1 column vector and new vectorial b.
The searchable index r that described decision function Func3 meets decision function Func3 is incremented to M-i+1 from 1, from the column vector that the searchable index r of any one function F unc3 that determines is corresponding, get a continuous drawing i column vector, decision function Func3 can meet x column vector linear independence of arbitrary neighborhood in this i vector.
Step 4) described in from search volume A
2n+1the correspondence position that the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into binary system check matrix C with the concrete operations of the null vector in alternative initialization is: search function Func2 is first from the A of high priority
3search for, work as A
3cannot meet, then A be expanded in search volume
2n+1for A
3+ A
5, work as A
3+ A
5still cannot meet, then once expand search volume A gradually
2n+1, until binary system check matrix C changes into do not tie up matrix containing the L × M of null vector.
Embodiment one
The check matrix generating method flow chart utilizing the present invention to provide, respectively to 32 information bits generate can detect continuous 8 with two check matrixes of continuous 25 bit flippings.
Comprise the following steps:
1) according to Hamming inequality 2
r>=k+r+1 determines the check code bit wide 6 needed for 32 information bits, and the check code bit wide needed for check matrix disclosed by the invention equals 7.
Step2: according to Hsiao coding criterion meet its require 7 dimensional vectors (binary vector) have 56 (
), wherein, high priority search volume A
3in the element that comprises as shown in table 1, second priority level search volume A
5in the element that comprises as shown in table 2, for convenience of expressing, the element in table 1 and table 2 is binary row vector, can be changed into column vector to each element transposition.
Table 1
| Sequence number | Vector | Sequence number | Vector |
| 1 | (1110000) | 19 | (0110001) |
| 2 | (1101000) | 20 | (0101100) |
| 3 | (1100100) | 21 | (0101010) |
| 4 | (1100010) | 22 | (0101001) |
| 5 | (1100001) | 23 | (0100110) |
| 6 | (1011000) | 24 | (0100101) |
| 7 | (1010100) | 25 | (0100011) |
| 8 | (1010010) | 26 | (0011100) |
| 9 | (1010001) | 27 | (0011010) |
| 10 | (1001100) | 28 | (0011001) |
| 11 | (1001010) | 29 | (0010110) |
| 12 | (1001001) | 30 | (0010101) |
| 13 | (1000110) | 31 | (0010011) |
| 14 | (1000101) | 32 | (0001110) |
| 15 | (1000011) | 33 | (0001101) |
| 16 | (0111000) | 34 | (0001011) |
| 17 | (0110100) | 35 | (0000111) |
| 18 | (0110010) |
Table 2
| Sequence number | Vector | Sequence number | Vector |
| 1 | (1111100) | 12 | (1011101) |
| 2 | (1111010) | 13 | (1011011) |
| 3 | (1111001) | 14 | (1010111) |
| 4 | (1110110) | 15 | (1001111) |
| 5 | (1110101) | 16 | (0111110) |
| 6 | (1110011) | 17 | (0111101) |
| 7 | (1101110) | 18 | (0111011) |
| 8 | (1101101) | 19 | (0110111) |
| 9 | (1101011) | 20 | (0101111) |
| 10 | (1100111) | 21 | (0011111) |
| 11 | (1011110) |
3) the binary system check matrix C of initialization L × M dimension, wherein M=k+L, before binary system check matrix C, k column vector is null vector, a last L column vector is made up of L rank unit matrix, this example generates the binary system check matrix C of a 7x39, wherein rear 7 of binary system check matrix C is classified as 7 rank unit matrixs, before 32 be classified as null vector, also be the region that function to be searched is filled, initialization matrix is as follows simultaneously.
4) judge the required continuous overturning figure place detected, in the present embodiment, 32 information bits are generated to the check matrix that can detect continuous 8 bit flippings, because 8≤8 (7+1);
5) search function of check matrix is determined.All column vectors (in this example being 39) in Func1 search function traversal binary system check matrix C, if wherein any one column vector and search volume A
2n+1the new vectorial b of middle taking-up is identical, then this function does not meet, and return value is 0.Func2 search function is from search volume A
2n+1the new vectorial b of middle taking-up may be filled into any row in binary system check matrix C in 1st ~ kth row, the column vector index p that search function Func2 travels through successively decreases 8 from 39, for from 39 to 8 any one column vector index p, get i-1 the column vector comprising column vector p and (comprise p, p-1, p-2 ... p-i+1), this i-1 column vector removal search space A is utilized
2n+1search a legal new vectorial b, and ensure l column vector linear independence (l ∈ [3 of arbitrary neighborhood in i vector of i-1 column vector and new vectorial b combination, i]), ensure that l column vector linear independence of arbitrary neighborhood in i vector needs i-l+1 equation.
6) from search volume A
2n+1the column vector that middle taking-up meets Func1 search function and Func2 search function is filled in i vector
ccorrespondence position, substitute the null vector in initialization, first from the A of high priority
3search for, A
3searchable index p increase progressively 1 to 35 from 1, the check matrix obtaining detecting continuous 8 bit data upsets is:
Embodiment two
Step 4 in embodiment one) in when 32 information bits are generated can detect the check matrix of continuous 25 bit flippings time, then 1) ~ 4) identical with embodiment one;
5) the check matrix C of energy 8 continuous overturnings is generated
1, Hypothesis Matrix C
1identical with the matrix in embodiment 1.
6) decision function Func3 is determined.The searchable index r of decision function Func3 is from 1 to M-i+1 (the corresponding 39-25+1=14 of the present embodiment), for from column vector corresponding to 1 to 14 any one searchable index r, get r the column vector comprising column vector r, decision function Func3 ensures l column vector linear independence of arbitrary neighborhood in this i vector, ensures that l column vector linear independence of arbitrary neighborhood in i vector needs i-l+1 equation.
7) suppose to utilize decision function Func3 to check matrix C
1judge, find that it cannot detect continuous print 16 bit flipping (check matrix C
1in deposit), then to search volume A
2n+1middle A
3column vector random alignment, the position of random inversion column vector;
8) then 7 are re-executed), until check matrix C
1meet x column vector linear independence of arbitrary continuation, will Matrix C be verified
1assignment, to check matrix C, obtains the check matrix of continuous 25 bit flippings.
The check matrix of described continuous 25 bit flippings is as follows:
The present invention patent discloses a kind of Hsiao coding checkout matrix generating method detected for continuous N BU, the Hsiao coding checkout matrix that the method generates does not increase the hardware consumption of traditional SECDED EDAC circuit, can detect the phenomenon of continuous N BU in memory (Multiple-bit upsets).Under the prerequisite not increasing Cache access delay, for the MBU phenomenon tackling Cache provides a kind of effective low expense encoding scheme, directly can substitute the EDAC circuit or parity checker that use in current C ache protection scheme.
Claims (5)
1., for the Hsiao coding checkout matrix generating method that continuous N BU detects, it is characterized in that, comprise the steps:
1) according to Hamming inequality 2
r≤ k+r+1 determines the check code bit wide r needed for the information bit of k position;
2) list all L dimensional vectors meeting Hsiao coding criterion, described L dimensional vector sum equals
2n+1 is the number of binary one in L dimensional vector, according in L dimensional vector 1 number belonged to search volume A
2n+1, described search volume A
2n+1comprise
individual L dimensional vector, n be integer and
L＝r+1；
3) the binary system check matrix C of initialization L × M dimension, wherein, front k the column vector of M=k+L, binary system check matrix C is null vector, and a rear L column vector is made up of L rank unit matrix, then the column vector form of binary system check matrix C is C=[d
1d
2d
kc
1c
l];
4) judge the required continuous overturning figure place i detected, as the continuous overturning figure place i≤L+1 of required detection, then determine search function Func1 and search function Func2, wherein, search function Func1 ensures from search volume A
2n+1in the new vectorial b of middle taking-up and binary system check matrix C, already present arbitrary column vector does not repeat, and search function Func2 ensures from search volume A
2n+1l the column vector linear independence that the new vectorial b of middle taking-up is adjacent in binary system check matrix C with it, wherein, l ∈ [3, i], from search volume A
2n+1the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into the correspondence position of binary system check matrix C with the null vector in alternative initialization, obtains Hsiao coding checkout matrix;
5) as the continuous overturning figure place i > L+1 of required detection, then the check matrix C that can detect L+1 position continuous overturning is generated
1, determine decision function Func3, by decision function Func3 to check matrix C
1detect, judge check matrix C
1x column vector of middle arbitrary continuation whether linear correlation, wherein, x ∈ [L+2, i], when x column vector linear correlation of arbitrary continuation, then to search volume A
2n+1in column vector random alignment, the position of random inversion column vector;
6) step 5 is repeated) until check matrix C
1till meeting x column vector linear independence of arbitrary continuation, then Matrix C will be verified
1assignment, to check matrix C, obtains Hsiao coding checkout matrix.
2. as claimed in claim 1 for the Hsiao coding checkout matrix generating method that continuous N BU detects, it is characterized in that, described search function Func1 meets all column vectors in traversal binary system check matrix C, any one column vector and search volume A
2n+1the new vectorial b of middle taking-up is all not identical.
3. as claimed in claim 1 for the Hsiao coding checkout matrix generating method that continuous N BU detects, it is characterized in that, described search function Func2 meets from A
2n+1the new vectorial b of middle taking-up can be filled in any row in binary system check matrix C in 1st ~ kth row; Simultaneously, the column vector index p of search function Func2 to successively decrease i from M-(L-i+1), for M-(L-i+1) to any one the column vector index p in i, get i-1 the column vector comprising column vector p, by a described i-1 column vector from search volume A
2n+1search legal new vectorial b, and ensure l column vector linear independence of arbitrary neighborhood in a described i-1 column vector and new vectorial b.
4. as claimed in claim 1 for the Hsiao coding checkout matrix generating method of continuous N BU detection, it is characterized in that, the searchable index r that described decision function Func3 meets decision function Func3 is incremented to M-i+1 from 1, from the column vector that the searchable index r of any one function F unc3 that determines is corresponding, get a continuous drawing i column vector, decision function Func3 can meet x column vector linear independence of arbitrary neighborhood in this i vector.
5., as claimed in claim 1 for the Hsiao coding checkout matrix generating method that continuous N BU detects, it is characterized in that, step 4) described in from search volume A
2n+1the correspondence position that the column vector that middle taking-up meets search function Func1 and search function Func2 is filled into binary system check matrix C with the concrete operations of the null vector in alternative initialization is: search function Func2 is first from the A of high priority
3search for, work as A
3cannot meet, then A be expanded in search volume
2n+1for A
3+ A
5, work as A
3+ A
5still cannot meet, then once expand search volume A gradually
2n+1, until binary system check matrix C changes into do not tie up matrix containing the L × M of null vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410649686.7A CN104378120B (en) | 2014-11-14 | 2014-11-14 | A kind of Hsiao coding checkout matrix generating methods detected for continuous N BU |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410649686.7A CN104378120B (en) | 2014-11-14 | 2014-11-14 | A kind of Hsiao coding checkout matrix generating methods detected for continuous N BU |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104378120A true CN104378120A (en) | 2015-02-25 |
| CN104378120B CN104378120B (en) | 2017-07-25 |
Family
ID=52556817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410649686.7A Active CN104378120B (en) | 2014-11-14 | 2014-11-14 | A kind of Hsiao coding checkout matrix generating methods detected for continuous N BU |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104378120B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110178312A (en) * | 2017-01-09 | 2019-08-27 | 高通股份有限公司 | To the low delay coding and decoding of bit reverse-poled code |
| CN112398485A (en) * | 2020-11-20 | 2021-02-23 | 中国人民解放军国防科技大学 | Check matrix generation method for correcting one-error-free code and two-error-correction adjacent code |
| CN114244374A (en) * | 2021-11-22 | 2022-03-25 | 成都博尔微晶科技有限公司 | Check matrix generation method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8516339B1 (en) * | 2011-04-01 | 2013-08-20 | Xilinx, Inc. | Method of and circuit for correcting adjacent bit errors in a memory |
| CN103886915A (en) * | 2012-12-19 | 2014-06-25 | 英飞凌科技股份有限公司 | Circuitry and method for correcting 3-bit errors containing adjacent 2-bit error |
| US8875002B1 (en) * | 2012-01-20 | 2014-10-28 | Cypress Semiconductor Corporation | Low cost adjacent double error correcting code |
-
2014
- 2014-11-14 CN CN201410649686.7A patent/CN104378120B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8516339B1 (en) * | 2011-04-01 | 2013-08-20 | Xilinx, Inc. | Method of and circuit for correcting adjacent bit errors in a memory |
| US8875002B1 (en) * | 2012-01-20 | 2014-10-28 | Cypress Semiconductor Corporation | Low cost adjacent double error correcting code |
| CN103886915A (en) * | 2012-12-19 | 2014-06-25 | 英飞凌科技股份有限公司 | Circuitry and method for correcting 3-bit errors containing adjacent 2-bit error |
Non-Patent Citations (1)
| Title |
|---|
| AVIJIT DUTTA 等: "Multiple Bit Upset Tolerant Memory Using a Selective Cycle Avoidance Based SEC-DED-DAEC Code", 《25TH IEEE VLSI TEST SYMPOSIUM 2007》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110178312A (en) * | 2017-01-09 | 2019-08-27 | 高通股份有限公司 | To the low delay coding and decoding of bit reverse-poled code |
| CN110178312B (en) * | 2017-01-09 | 2023-05-09 | 高通股份有限公司 | Low latency encoding and decoding of bit-reversed polarization codes |
| CN112398485A (en) * | 2020-11-20 | 2021-02-23 | 中国人民解放军国防科技大学 | Check matrix generation method for correcting one-error-free code and two-error-correction adjacent code |
| CN114244374A (en) * | 2021-11-22 | 2022-03-25 | 成都博尔微晶科技有限公司 | Check matrix generation method and device, electronic equipment and storage medium |
| CN114244374B (en) * | 2021-11-22 | 2022-08-05 | 成都博尔微晶科技有限公司 | Check matrix generation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104378120B (en) | 2017-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9213596B2 (en) | Handling errors in ternary content addressable memories | |
| CN101281481B (en) | Method for error correcting and detecting for memory anti-single particle overturn | |
| CN103971751A (en) | Detection And Decoding In Flash Memories With Selective Binary And Non-binary Decoding | |
| EP2748707B1 (en) | Digital error correction | |
| CN106371943A (en) | LDPC (low density parity check) decoding optimization method based on flash programming interference error perception | |
| TWI808153B (en) | Error detection and correction circuitry | |
| CN102122959A (en) | Data compression device for improving main memory reliability of computer, and method thereof | |
| CN101980339A (en) | Error correction encoding method for dynamic random access memory (DRAM) buffer | |
| CN104409103A (en) | Novel two-dimensional coding reinforcing method and circuit arrangement for aerospace memory | |
| CN104378120A (en) | Hsiao coding check matrix generation method for continuous MBU detection | |
| CN106328209A (en) | Storage single event multiple bit upset fault-tolerance method and circuit | |
| CN107301881B (en) | SRAM memory anti-radiation reinforcing method based on 4-bit adjacent and 3-bit burst error correcting codes and memory system | |
| CN102929743A (en) | First-stage cached data storage method and device with soft error tolerant function | |
| CN109496298A (en) | A kind of building method of EVENODD code | |
| CN105027084B (en) | The apparatus and method of control memory in mobile communication system | |
| CN107402725A (en) | Nonvolatile memory devices and its data deduplication method | |
| CN108021467B (en) | Memory fault tolerance protection method, device, equipment and storage medium | |
| CN103151078A (en) | Memorizer Error detection and correction code generation method | |
| Neelima et al. | Efficient adjacent 3D parity error detection and correction codes for embedded memories | |
| CN110751977B (en) | Memory chip fault-tolerant device and fault-tolerant error-correcting method based on LDPC code | |
| Liu et al. | A method to recover critical bits under a double error in SEC-DED protected memories | |
| CN104951559A (en) | Binary code rearrangement method based on bit weight | |
| CN106104491A (en) | There is calculating system and the operational approach thereof of data protection schemes | |
| Abbas et al. | Multiple cell upsets tolerant content-addressable memory | |
| US9053050B2 (en) | Determining a desirable number of segments for a multi-segment single error correcting coding scheme |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |