Data compression and encoding in a memory system
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-012/00
G06F-015/16
G06F-013/12
G06F-012/02
G06F-012/04
출원번호
US-0279914
(2011-10-24)
등록번호
US-8892809
(2014-11-18)
발명자
/ 주소
Yang, Xueshi
출원인 / 주소
Marvell World Trade Ltd.
인용정보
피인용 횟수 :
1인용 특허 :
8
초록▼
Embodiments provide a method comprising receiving input data comprising a plurality of data sectors; compressing the plurality of data sectors to generate a corresponding plurality of compressed data sectors; splitting a compressed data sector of the plurality of compressed data sectors to generate
Embodiments provide a method comprising receiving input data comprising a plurality of data sectors; compressing the plurality of data sectors to generate a corresponding plurality of compressed data sectors; splitting a compressed data sector of the plurality of compressed data sectors to generate a plurality of split compressed data sectors; and storing the plurality of compressed data sectors, including the plurality of split compressed data sectors, in a plurality of memory pages of a memory.
대표청구항▼
1. A method comprising: receiving input data comprising a plurality of data sectors;compressing individual data sectors of the plurality of data sectors to generate a corresponding plurality of compressed data sectors;splitting an individual compressed data sector of the plurality of compressed data
1. A method comprising: receiving input data comprising a plurality of data sectors;compressing individual data sectors of the plurality of data sectors to generate a corresponding plurality of compressed data sectors;splitting an individual compressed data sector of the plurality of compressed data sectors to generate a plurality of split compressed data sectors;adding additional bits to individual split compressed data sectors of the plurality of split compressed data sectors to generate padded individual split compressed data sectors, wherein the number of additional bits added to the individual split compressed data sectors is based, at least in part, on sizes of individual memory pages of a memory; andstoring each of the padded individual split compressed data sectors in the individual memory pages of the memory. 2. The method of claim 1, wherein the splitting of the individual compressed data sector comprises splitting the individual compressed data sector to generate a first split compressed data sector and a second split compressed data sector of the plurality of split compressed data sectors, andthe storing of each of the padded individual compressed data sectors further comprises: storing the first split compressed data sector in a first memory page of the plurality of memory pages; andstoring the second split compressed data sector in a second memory page of the plurality of memory pages. 3. The method of claim 2, wherein the individual compressed data sector is a first compressed data sector, andstoring the first split compressed data sector in the first memory page further comprises: grouping the first split compressed data sector with a second compressed data sector of the plurality of compressed data sectors; andstoring the first split compressed data sector and the second compressed data sector in the first memory page. 4. The method of claim 3, wherein storing the first split compressed data sector in the first memory page further comprises: grouping the first split compressed data sector with the second compressed data sector such that a threshold code rate is achieved while encoding the first split compressed data sector and the second compressed data sector. 5. The method of claim 4, wherein storing the first split compressed data sector in the first memory page further comprises: grouping the first split compressed data sector with the second compressed data sector such that the first split compressed data sector and the second compressed data sector, after being encoded, fit in the first memory page. 6. The method of claim 3, wherein the storing the second split compressed data sector in the second memory page further comprises: storing the second split compressed data sector in the second memory page such that no other compressed data sector is stored in the second memory page. 7. The method of claim 1, wherein splitting the individual compressed data sector further comprises: determining that a compression ratio for the individual compressed data sector exceeds a desired code rate for encoding the individual compressed data sector; andin response to determining that the compression ratio exceeds the desired code rate, splitting the individual compressed data sector. 8. The method of claim 1, further comprising: encoding the plurality of compressed data sectors prior to storing each of the padded individual split compressed data sectors. 9. The method of claim 1, further comprising: generating a table that, for each of the plurality of data sectors, indicates one or more of the memory pages of the memory in which a corresponding compressed data sector is stored. 10. The method of claim 9, wherein the splitting of the individual compressed data sector comprises splitting the individual compressed data sector to generate a first split compressed data sector and a second split compressed data sector, wherein the individual compressed data sector is generated from a given data sector,the storing of each of the padded individual split compressed data sectors further comprises: storing the first split compressed data sector in a first memory page of the memory pages; andstoring the second split compressed data sector in a second memory page of the memory pages, andthe generating the table comprises generating a table such that the table indicates that a particular data sector is stored in the first memory page and the second memory page. 11. The method of claim 1, further comprising: generating a table that indicates, for individual memory pages of the memory pages, a number of valid compressed data sectors stored in each of the individual memory pages. 12. The method of claim 11, further comprising: changing a particular data sector of the plurality of data sectors, wherein the particular data sector is compressed to generate a first compressed data sector, and wherein the first compressed data sector is stored in a first memory page and a second memory page of the memory pages; andin response to changing the particular data sector, updating the table such that, for each of the first memory page and the second memory page, the number of valid compressed data sectors stored in each of the individual memory pages is adjusted. 13. A memory system comprising: a memory module;a compressor module configured to compress each of a plurality of data sectors to generate a corresponding plurality of individual compressed data sectors;a splitting module configured to split the individual compressed data sectors to generate a plurality of split compressed data sectors;a padding module to add additional bits to individual split compressed data sectors of the plurality of split compressed data sectors to generate padded individual split compressed data sectors, wherein the number of additional bits added to the padded individual split compressed data sectors is based, at least in part, on sizes of individual memory pages of the memory module; anda memory controller configured to store each of the padded individual split compressed data sectors in the individual memory pages of the memory module. 14. The memory system of claim 13, further comprising: an encoder module configured to encode the plurality of individual compressed data sectors prior to storing each of the padded individual split compressed data sectors. 15. The memory system of claim 13, wherein the plurality of split compressed data sectors includes a first split compressed data sector and a second split compressed data sector, the memory system further comprising: a grouping module configured to group the first split compressed data sector with the second split compressed data sector of the plurality of split compressed data sectors, wherein the memory controller is configured to store the first split compressed data sector and the second split compressed data sector in a particular page of the memory pages.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (8)
Rydbeck Nils R. C. (Vildanden J101 22234 Lund SW) Sundberg Carl-Erik Wilhelm (Vildanden C506 22234 Lund SW), Adaptive error correcting transmission system.
Moertl Daniel Frank (Rochester MN) Stevens John Douglas (Rochester MN) Van Grinsven Gene Steven (Rochester MN) Walk Bruce Marshall (Rochester MN), Storage method and hierarchical padding structure for direct access storage device (DASD) data compression.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.