Patent
1996-03-20
1998-10-20
Bowler, Alyssa H.
395377, G06F 1582
Patent
active
058260978
ABSTRACT:
In an information processor formed of a program storage unit 2, a data pair production unit 3 and an operation unit 4 including an accumulator 41, when the sum of products of data ai and bi of the same generation .SIGMA. (ai*bi) is produced, a cumulative products instruction code MULA is read out from program storage unit 2. When a data pair related to the instruction code MULA is detected in production portion 3, a multiplication processing of the data pair and accumulation a processing of the multiplication result values using accumulator 41 according to the instruction code MULA are continuously executed in operation unit 4. Accordingly, the order of executing operation processing according to the instruction code MULA including the above-described multiplication processing and accumulation processing is not limited by the order of generations, and therefore data of different generations can be processed in parallel.
REFERENCES:
patent: 5117489 (1992-05-01), Komori et al.
patent: 5204828 (1993-04-01), Kohn
patent: 5327569 (1994-07-01), Shima et al.
Wong et al., "Biddle: A Bidirectional Data Driven Lisp Engine", IEEE, 1989, pp. 207-214.
Bowler Alyssa H.
Davis Jr. Walter D.
Sharp Kabushiki Kaisha
LandOfFree
Method of controlling execution of data flow program for perform does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of controlling execution of data flow program for perform, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of controlling execution of data flow program for perform will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-258507