Patent
1996-01-23
1998-02-24
Tung, Kee M.
395706, G06F 1580
Patent
active
057218838
DESCRIPTION:
BRIEF SUMMARY
TECHNICAL FIELD
This invention relates to a compiling method for parallel processing program which generates execution codes of a program prepared by using program language for allowing a plurality of arithmetic processors to carry out image processing in parallel, an image processing apparatus for carrying out image processing by parallel processing of a plurality of operations, and an image processing method for allowing the image processing apparatus to be operative.
BACKGROUND ART
Generally, in the parallel processing system, in distributing procedure (processing) defined by user to a plurality of processors to allow them to carry out parallel processing, the program developer carries out description and preparation of program so as to carry out these distributed procedures every respective processors.
When the procedure defined by user is assumed to be load in the parallel processing system, the program developer prepares source program so that distribution of load with respect to respective processors is suitably carried out in advance in a parallel processing system as described above.
Accordingly, the program developer must describe source program so that load to individual processors is intentionally distributed in order to realize the processing of high efficiency.
However, in the preparation of the program, the work in which distribution of load to individual processors is caused to be conscious would be forced on the program developer by the number of processors to which load is distributed. This heavily makes the burden on the program developer.
In the image processing using such a parallel processing system, in the case where picture division processing is carried out, there are instances where the number of small areas obtained by division is greater than the number of processors and the number of small areas cannot be divided (is indivisible) by the number of processors, so there results remainder area, i.e., fraction area in picture. When such fraction area takes place, any one of the processors would be caused to carry out fraction processing with respect to the fraction area.
Moreover, in the case where load is distributed, when processing for integrally performing operation of results of image processing in small areas obtained by dividing a picture is imposed on a portion of processors, the portion of the processors is required to have two kinds of execution codes of execution code for arithmetic processing with respect to the small areas and the above-described integration processing execution code for integrally performing operation. Because preparation of such a program causes the program developer to carry out preparation of program in which the above-mentioned integration processing is caused to be conscious as well, the burden is heavier than the burden described above.
Further, two kinds of execution codes are delivered to the processor, whereby the execution code quantity with respect to the processor would increase to more degree as compared to the execution code quantity for arithmetic processing with respect to the small areas. In addition, such integration processing is supplemented, whereby the capacity of memory used is spent substantially twice.
This invention has been made in view of actual circumstances as described above, and its object is to provide a compiling method for parallel processing program which can suppress increase in execution codes to be generated without making heavy burden on the program developer.
Another object of this invention is to provide an image processing apparatus and an image processing method adapted for generating execution codes in dependency upon, e.g., application program used, etc., thus making it possible to carry out image processing of which efficiency is higher than that of the prior art.
DISCLOSURE OF THE INVENTION
With a view to solving the above-described problems, a compiling method for parallel processing program according to this invention is directed to a compiling method for parallel processing program, which compil
REFERENCES:
patent: 5088034 (1992-02-01), Ihara et al.
patent: 5230053 (1993-07-01), Zaiki et al.
patent: 5437034 (1995-07-01), Tanaka et al.
Microprocessing And Microprogramming, vol. 30, No. 1/05, Aug. 1, 1990 pp. 365-370, XP000141671 Vasconcelos N Q Et Al. "An Environment For Parallel Programming In Pascal1" *paragraph 3* *paragraph 5*.
Journal Of Parallel And Distributed Computing, vol. 6, No. 3, Jun. 1, 1989 pp. 598-622, XP 000133097 Chu C H "A Model For An Intelligent Operating System For Executing Image Understanding Tasks On A Reconfigurable Parallel Architecture" *p. 607, line 3 -line 31*.
Computer Technology Review, vol. VI, No. 3, 1986 Los Angeles US, pp. 41-45 P. Hampton And R. Denker "Multiprocessors APs simplify calculations for image processing" *p. 45, line 14 -line 27; figure 1,2*.
Hasebe, Jun et al., "Real Time Image Processing System SIPS -High-Speed Processing Method-", IPSJ General Convention Lecture Transaction, vol. 35th, No. 3, pp. 2017-2018 (1987).
Katsuo Satoshi
Shigata Taro
Frommer William S.
Sinderbrand Alvin
Sony Corporation
Tung Kee M.
LandOfFree
System and method for implementing parallel image processing does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for implementing parallel image processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for implementing parallel image processing will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1881282