Apparatus and method for signal processing

• US 5,974,521 A
• Filed: 03/31/1998
• Issued: 10/26/1999
• Est. Priority Date: 12/12/1993
• Status: Expired due to Fees

• Current Assignee: GSI Technology Israel Ltd. (GSI Technology Incorporated)
• Original Assignee: Neomagic Israel Ltd.
• Inventors: Akerib, Avidan
• Primary Examiner(s): Pan, Daniel H.
• Application Number:
  US09/052,164
• Time in Patent Office: 574 Days
• Field of Search: 395/309, 395/386, 395/800.13, 395/853, 395/800.14, 395/800.19, 395/800.11, 395/800.35, 704/290, 365/231, 365/125, 711/108, 711/202, 711/125, 364/749, 364/DIG. 1, 364/DIG. 2
• US Class Current: 712/11
• CPC Class Codes: G06F 15/8023 Two dimensional arrays, e.g. mesh, torus
• CPC Class Codes: G06F 15/8038 Associative processors
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 10/955 using specific electronic processors

Abstract

An associative signal processing apparatus for processing a plurality of samples of an incoming signal in parallel, the apparatus comprising: (a) an array of processors, each processor including a multiplicity of associative memory cells, the memory cells being operative to perform: (i) compare operations, in parallel, on the plurality of samples of the incoming signal; and (ii) write operations, in parallel, on the plurality of samples of the incoming signal; and (b) an I/O buffer register including a multiplicity of associative memory cells, the register being operative to: (i) input the plurality of samples of the incoming signal to the array of processors in parallel by having the I/O buffer register memory cells perform at least one associative compare operation and the array memory cells perform at least one associative write operation; and (ii) receive, in parallel, a plurality of processed samples from the array of processors by having the array memory cells perform at least one associative compare operation and the I/O buffer register memory cells perform at least one write operation.

Claims

1. An associative signal processing apparatus for processing a plurality of samples of an incoming signal in parallel, the apparatus comprising:

(a) an array of processors, each processor including a multiplicity of associative memory cells, said memory cells being operative to perform;

(i) compare operations, in parallel, on the plurality of samples of the incoming signal; and

(ii) write operations, in parallel, on the plurality of samples of the incoming signal; and

(b) an I/O buffer register including a multiplicity of associative memory cells, said register being operative to;

(i) input the plurality of samples of the incoming signal to said array of processors in parallel by having said I/O buffer register memory cells perform at least one associative compare operation and said array memory cells perform at least one associative write operation; and

(ii) receive, in parallel, a plurality of processed samples from said array of processors by having said array memory cells perform at least one associative compare operation and said I/O buffer register memory cells perform at least one write operation.

2. The apparatus of claim 1, wherein said array of processors and said I/O buffer register are arranged on a single chip.

3. The apparatus of claim 1, further comprising:

(c) a register array operative to store responders arriving from said array memory cells and from said I/O buffer register memory cells, and to provide communication, within a single cycle, between a plurality of pairs of non-adjacent processors.

4. The apparatus of claim 1, wherein said I/O buffer register and said array of processors are operative in parallel.

5. The apparatus of claim 1, wherein said at least one I/O buffer register associative memory cell is configurable as at least one of said multiplicity of processor memory cells.

6. The apparatus of claim 1, wherein the apparatus is operative in video real time.

7. The apparatus of claim 1. wherein the signal includes an image.

8. The apparatus of claim 7, wherein said image is a color image.

9. The apparatus of claim 7, wherein said image is input to said I/O buffer register according to a first order, said first order differing from a row/column order of said image.

10. The apparatus of claim 1, wherein each of the plurality of samples is input to said I/O buffer register according to a first order, said first order differing from an order of the plurality of samples within the incoming signal.

11. The apparatus of claim 1, wherein said I/O buffer register is in communication with a plurality of processors in said array of processors.

12. The apparatus of claim 1, wherein said I/O buffer register is operative to transfer data to said array of processors using associative processing methods.

13. An associative signal processing apparatus for processing a plurality of samples of an incoming signal in parallel, the apparatus comprising:

(a) an array of processors, each processor including a multiplicity of associative memory cells, said memory cells being operative to perform;

(i) compare operations, in parallel, on the plurality of samples of the incoming signal; and

(ii) write operations, in parallel, on the plurality of samples of the incoming signal;

(b) a register array including at least one register operative to;

(i) store, in parallel, responders arriving from said associative memory cells in a plurality of said processors; and

(ii) provide communication, within a single cycle, between a plurality of pairs of non-adjacent processors in said array of processors, and

(c) an image correction system whereby;

(i) a multiplicity of pixels from a distorted image are provided to a respective multiplicity of said associative memory cells;

(ii) a transformation for an output of said image to compensate for said distortion is provided; and

(iii) said transformation is executed in parallel for a plurality of said pixels via said register array.

14. A method for processing a distorted image, the distorted image including a plurality of pixels, the method comprising the steps of:

(a) providing an array of processors, each processor including a multiplicity of associative memory cells, said memory cells being operative to perform;

(i) compare operations, in parallel, on at least a portion of the plurality of pixels; and

(ii) write operations, in parallel, on at least a portion of the plurality of pixels;

(b) providing a register array including at least one register operative to;

(i) store responders arriving from said associative memory cells in a plurality of said processors; and

(ii) provide communication, within a single cycle, between a plurality of pairs of non-adjacent processors in said array of processors;

(c) providing each of the plurality of pixels to at least one of said processors; and

(d) transforming at least a portion of the plurality of pixels in parallel to compensate for a distortion of the distorted image, by arranging, in parallel, in a plurality of said processors, at least two of the pixels in a single processor via said register array, and by performing in parallel, compare and write operations on a plurality of said pairs of pixels.

15. The method of claim 14, further comprising the step of:

(d) providing an I/O buffer register including a multiplicity of associative memory cells, said register being operative to;

(i) input and output data;

(ii) input a plurality of samples of said data to said array of processors in parallel by having said I/O buffer register memory cells perform at least one associative compare operation and said array memory cells perform at least one associative write operation; and

(ii) receive, in parallel, a plurality of processed samples from said array of processors by having said array memory cells perform at least one associative compare operation and said I/O buffer reigster memory cells perform at least one write operation;

(e) inputting a first plurality of pixels to said I/O buffer register while performing step (d) on a second plurality of pixels;

(f) exchanging said first and second pluralities of pixels in parallel by performing compare and write operations on said I/O buffer.

16. The method of claim 14, further comprising the step of:

(d) providing an I/O buffer register including a multiplicity of associative memory cells said register being operative to;

(i) input and output data;

(ii) input a plurality of samples of said data to said array of processors in parallel by having said I/O buffer register memory cells perform at least one associative compare operation and said array memory cells perform at least one associative write operation; and

(ii) receive, in parallel, a plurality of processed samples from said array of processors by having said array memory cells perform at least one associative compare operation and said I/O buffer register memory cells perform at least one write operation;

(e) outputting a first plurality of pixels from said I/O buffer register while performing step (d) on a second plurality of pixels.

17. The method of claim 16, wherein step (e) futher comprises outputting a third plurality of pixels from said I/O buffer register while performing step (d) on a second plurality of pixels.

18. The method of claim 17, wherein said third plurality of pixels are output from said I/O buffer register while said first plurality of pixels are input to said I/O buffer register.