System of rotating data in a plurality of processing elements
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-015/76
G06F-005/01
출원번호
US-0372683
(2012-02-14)
등록번호
US-8856493
(2014-10-07)
우선권정보
GB-0309194.9 (2003-04-23)
발명자
/ 주소
Beaumont, Mark
출원인 / 주소
Micron Technology, Inc.
대리인 / 주소
Dorsey & Whitney LLP
인용정보
피인용 횟수 :
0인용 특허 :
38
초록▼
A method of rotating data in a plurality of processing elements comprises a plurality of shifting operations and a plurality of storing operations, with the shifting and storing operations coordinated to enable a three shears operation to be performed on the data. The plurality of storing operations
A method of rotating data in a plurality of processing elements comprises a plurality of shifting operations and a plurality of storing operations, with the shifting and storing operations coordinated to enable a three shears operation to be performed on the data. The plurality of storing operations is responsive to the processing element's positions.
대표청구항▼
1. An array of processing elements, comprising: a plurality of processing elements arranged in rows and columns,wherein the array of processing elements is configured to perform a plurality of shilling operations, each shifting operation being performed using a plurality of the rows or the columns a
1. An array of processing elements, comprising: a plurality of processing elements arranged in rows and columns,wherein the array of processing elements is configured to perform a plurality of shilling operations, each shifting operation being performed using a plurality of the rows or the columns and being performed such that each processing, element in each row or column receives data originally held by every other processing element in that row or column, respectively, andwherein the array of processing elements is configured to perform a plurality of selecting operations, each selecting operation being performed by the plurality of processing elements on the received data, where each of the received data is a candidate for selection, the shifting and selecting operations coordinated to enable a three shears operation to be performed on the data. 2. The array of processing elements of claim 1, wherein the plurality of selecting operations are responsive to initial counts which are either loaded into at least certain of said processing elements or calculated locally based on the processing element's location. 3. The of processing elements of claim 2, wherein each of the plurality of processing elements is configured to maintain a current count for each initial count, said current counts being responsive to said initial counts and a number of data shifts performed. 4. The array of processing elements of claim 3, wherein, in maintaining current counts, each of the plurality of processing elements is configured to alter said initial counts at programmable intervals by a programmable amount. 5. The array of processing elements of claim 4, wherein said initial counts are decremented in response to a shifting of data to produce said current counts. 6. The array of processing elements of claim 5, wherein the selecting operation is performed when a current count in a processing element is non-positive. 7. The array of processing elements of claim 1, further configured to select which processing elements are active in response to a row select signal and a column select signal. 8. The array of processing elements of claim 1, wherein the three shears operation rotates a matrix comprising the data 90 degrees. 9. The array of processing elements of claim 1, wherein the plurality of shifting operations and the plurality of selecting operations include:a first shifting operation and a first selecting operation coordinated to enable a first shear operation in a first direction;a second shifting operation and a second selecting operation coordinated to enablea second shear operation in a second direction; anda third shifting operation and a third selecting operation coordinated to enable a third shear operation in a third direction. 10. The array of processing elements of claim 9, wherein the first shifting operation is a west to east wrap shift;wherein the second shifting operation is a north to south wrap shift; and wherein the third shifting operation is an east to west wrap shift. 11. A system for performing operations on data values, comprising: a processing element in an array of processing elements, wherein the processing element is a member of a row and a column of the array,wherein the processing element is configured to perform a plurality of shifting operations, each shifting operation being performed by loading a data value from a neighboring processing element in the row or the column and being performed such that the processing element loads data values originally held by every other processing element of the row or the column, respectively, andwherein the processing element is configured to perform a plurality of selecting operations on the loaded data values, where each of the loaded data values is a candidate for selection, said shifting and selecting operations coordinated to enable a three shears operation to be performed on the data values. 12. The system of claim 11, wherein the plurality of selecting operations are responsive to an initial count which is either loaded, into the processing element or calculated locally based on the processing element's location. 13. The system of claim 12, wherein the processing element is configured to maintain a current count for the initial count, said current count being responsive to said initial count and a number of data shifts performed. 14. The system of claim 13, wherein, in maintaining the current count, the processing element is configured to alter the initial count at programmable intervals by a programmable amount. 15. The system of claim 14, wherein said initial count is decremented in response to a shifting of data values to produce said current count. 16. The system of claim 15, wherein the selecting operation is performed when the current count is non-positive. 17. The system of claim 11, wherein the processing element is selected to be active in response to a row select signal and a column select signal. 18. The system of claim 11, wherein the three shears operation rotates a matrix comprising the data values 90 degrees. 19. The system of claim 11, wherein the plurality of shifting operations and the plurality of selecting operations include: a first shifting operation and a first selecting operation coordinated to enable a first shear operation in a first direction;a second shifting operation and a second selecting operation coordinated to enable a second shear operation in a second direction; anda third shifting operation and a third selecting operation coordinated to enable a third shear operation in a third direction. 20. The system of claim 19, wherein the first shifting operation is a west to east wrap shift; wherein the second shifting operation is a north to south wrap shift; and wherein the third shifting operation is an east to west wrap shift.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (38)
Crozier George W. (Hatfield PA), Apparatus for high speed image rotation.
Barker Thomas Norman ; Collins Clive Allan ; Dapp Michael Charles ; Dieffenderfer James Warren ; Knowles Billy Jack ; Lesmeister Donald Michael ; Miles Richard Ernest ; Nier Richard Edward ; Richards, Fully distributed processing memory element.
Glover Michael A. (10 Hemlock Way Durham NH 03824), Massively parallel SIMD processor which selectively transfers individual contiguously disposed serial memory elements.
David Karger ; Eric Lehman ; F. Thomson Leighton ; Matthew Levine ; Daniel Lewin ; Rina Panagrahy, Method and apparatus for distributing requests among a plurality of resources.
Hinsley Christopher Andrew,GBX, Operating system for use with computer networks incorporating two or more data processors linked together for parallel processing and incorporating improved dynamic load-sharing techniques.
Mori Kazutaka (Higashiyamato JPX), Parallel data processing system with plural-system bus configuration capable of fast data communication between processo.
Pechanek Gerald G. (Cary NC) Vassiliadis Stamatis (Zoetermeer NLX), Processor using folded array structures for transposition memory and fast cosine transform computation.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.