IP Library Granted Patent US 7,130,985
Granted Patent B2
US 7,130,985 · App. 10/284,163 · Granted Oct 31, 2006

Parallel processor executing an instruction specifying any location first operand register and group configuration in two dimensional register file

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,130,985
App. No.
10/284,163
Granted
Oct 31, 2006
Kind
B2
Abstract

Described herein is a data processor that comprises a register memory and a processor unit. The processor unit simultaneously executes a single instruction on a plurality of operands in the register memory. The plurality of operands may be one or more contiguous regions. The contiguous regions may be specified as an address and a format such as a row, a column, or a neighborhood relative to the address.

Claims (25)

1. An integrated circuit comprising:

a two-dimensional register memory; and

a parallel processor for executing an instruction simultaneously on a first plurality of operands in the two-dimensional register memory, wherein the instruction comprises

an operation,

a first address of a first operand in the first plurality of operands, wherein the first operand may be located anywhere in the two-dimensional register memory, and

a first configuration identifying the first plurality of operands,

wherein the parallel processor executes the operation on an arbitrarily located first plurality of operands in the two-dimensional register memory.

2. The integrated circuit as claimed in claim 1 , wherein an operand in the first register memory is specified by a first address in a second register memory.

3. The integrated circuit as claimed in claim 1 , wherein an address of an operand in the first register memory is specified in the instruction.

4. The integrated circuit as claimed in claim 2 , wherein the instruction comprises an indication of a second address relative to the first address.

5. The integrated circuit as claimed in claim 2 , wherein the instruction comprises an indication of an operation, and wherein the second register memory comprises an indication of a second address relative to the first address.

6. The intearated circuit as claimed in claim 5 , wherein the operation is an addition operation.

7. The integrated circuit as claimed in claim 1 , wherein the first register memory is an element of a scalar unit.

8. The integrated circuit as claimed in claim 1 , wherein the processor unit is a vector unit.

9. The integrated circuit of claim 1 , wherein the first form of contiguous cells corresponds to a plurality of neighboring addresses, wherein each neighboring address is adjacent to the first address.

10. The integrated circuit as claimed in claim 1 , wherein the first register memory comprises an array of cells, and wherein each cell in the array can be specified as a pair of coordinates.

11. The integrated circuit as claimed in claim 10 , wherein each cell of the array is capable of storing 8 or more bits.

12. The integrated circuit as claimed in claim 10 , wherein the array extends in two dimensions and the cells of the array are located on rows in the first dimension and columns in the second dimension.

13. The integrated circuit as claimed in claim 1 , wherein the first register memory and the processor unit are arranged on the same integrated circuit.

14. The integrated circuit of claim 1 , wherein the first configuration corresponds to a horizontal arrangement with respect to the first address.

15. The integrated circuit of claim 1 , wherein the first configuration corresponds to a vertical arrangement with respect to the first address.

16. The integrated circuit of claim 4 , wherein the second address corresponds to a horizontal arrangement with respect to the first address.

17. The integrated circuit of claim 4 , wherein the second address corresponds to a vertical arrangement with respect to the first address.

18. The integrated circuit of claim 4 , wherein the second address corresponds to a plurality of neighboring addresses, wherein each neighboring address is adjacent to the first address.

19. The integrated circuit of claim 1 , wherein the operation is performed on the first plurality of operands and a second plurality of operands, and wherein the instruction further comprises a second address of a second operand in the second plurality of operands and a second configuration of the second plurality of operands.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 25, 2018
From: BROADCOM EUROPE LIMITED
To: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.
Reel/Frame 046019/0030 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 1, 2017
From: BROADCOM CORPORATION
To: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.
Reel/Frame 041706/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 8, 2005
From: ALPHAMOSAIC LIMITED
To: BROADCOM EUROPE LIMITED
Reel/Frame 016492/0070 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 29, 2003
From: BARLOW, STEPHEN; RAMSDALE, TIMOTHY; SWANN, ROBERT; BAILEY, NEIL; PLOWMAN, DAVID
To: ALPHAMOSAIC LIMITED
Reel/Frame 014013/0455 →