Boots – shoes – and leggings
Patent
1984-08-10
1987-08-11
Williams, Jr., Archie E.
Boots, shoes, and leggings
364757, G06F 752
Patent
active
046866450
ABSTRACT:
A digital data processor for matrix/matrix multiplication includes a systolic array of nearest neighbor connected gated full adders. The adders are arranged to multiply two input data bits and to add their product to an input cumulative sum bit and a carry bit from a lower order bit computation. The result and input data bits are output to respective neighboring cells, a new carry bit being recirculated for later addition to a higher order bit computation. Column elements of one matrix and row elements of the other are input to either side of the array bit-serially, least significant bit leading, for mutual counterpropagation therethrough with a cumulative time delay between input of adjacent columns or rows. Bit-level matrix interactions for product matrix computation occur at individual cells. Pairs of intercalated adder trees are connected switchably to the array to accumulate bit-level contributions to product matrix elements.
REFERENCES:
patent: 4493048 (1985-01-01), Kung et al.
patent: 4507748 (1985-03-01), Cotton
patent: 4533993 (1985-08-01), McCanny et al.
patent: 4592004 (1986-05-01), Bocker et al.
patent: 4639857 (1987-01-01), McCanny et al.
Effective Pipelining of Digital Systems, by Jump et al., IEEE Transactions on Computers, vol. C-27, No. 9, Sep. 1978, pp. 855-865.
Mead et al., Introduction to VLSI Systems, Oct. 1980, pp. 276-280.
Kung, "Why Systolic Architectures?", Computer, vol. 15, No. 1, Jan. 82, pp. 37-46, IEEE, Long Beach, CA.
McCanny et al., "Bit-Level Systolic Array Circuit for Matrix Vector Multiplication", IEEE Proceedings, vol. 130, part G, No. 4, Aug. 1983, pp. 125-130.
Foster et al., "The Design of Special-Purpose VLSI Chips", Computer, vol. 13, No. 1, Jan. 1980, IEEE Long Beach, CA, pp. 26-40.
Thompson et al., "Digital Arithmetic Units for a High Data Rate", The Radio and Electronic Engineer, vol. 45, No. 3, Mar. 1975, pp. 116-120, London, GB.
Hallin et al., "Pipelining of Arithmetic Functions", IEEE Transactions on Computers, vol. 21, No. 8, Aug. 1972, pp. 880-886, IEEE, New York, U.S.A.
Kung et al., "Matrix Triangularisation by Systolic Arrays", SPIE, vol. 298, Real Time Signal Processing, 4 (1981), pp. 19-26.
McCanny John V.
McWhirter John G.
Wood Kenneth W.
National Research Development Corporation
Nguyen Long
Williams Jr. Archie E.
LandOfFree
Pipelined systolic array for matrix-matrix multiplication does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Pipelined systolic array for matrix-matrix multiplication, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pipelined systolic array for matrix-matrix multiplication will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-407225