1. A group of instructions in a Matrix Processor that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
a first, second, third, and fourth matrix register wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein said first, second, third, and fourth matrix registers simultaneously swaps row or columns between said first, second, third, and fourth matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix registers, or swapping columns between said first, second, third, and fourth matrix registers.
2. A Matrix Processor that includes instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
a first, second, third, and fourth matrix register wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein said first, second, third, and fourth matrix registers simultaneously swaps row or columns between said first, second, third, and fourth matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix registers, or swapping columns between said first, second, third, and fourth matrix registers.
3. A system that includes a Matrix Processor with instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
a first, second, third, and fourth matrix register wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein said first, second, third, and fourth matrix registers simultaneously swaps row or columns between different said first, second, third, and fourth registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix registers, or swapping columns between said first, second, third, and fourth matrix registers.
4. A method to make a Matrix Processor that includes instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
providing 16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
coupling said processing elements into a 4\xd74 matrix processing array with a mesh row column interconnect;
providing a first, second, third, and fourth matrix register wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein said first, second, third, and fourth matrix registers simultaneously swaps row or columns between said first, second, third, and fourth matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix registers, or swapping columns between said first, second, third, and fourth matrix registers.
5. A method to use instructions in a Matrix Processor that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
providing 16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
providing a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
providing a first, second, third, and fourth matrix register wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register; and
simultaneously swapping row or columns between said first, second, third, and fourth matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix registers, or swapping columns between said first, second, third, and fourth matrix registers.
6. A dependent claim according to claim 1, 2, 3, 4, or 5 wherein successive iterations or combinations of the instructions perform standard tensor matrix operations from the following group of matrix operations: transpose, shuffle, and deal.
7. A dependent claim according to claim 1, 2, 3, 4, or 5 wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
8. A group of instructions in a Matrix Processor that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises 16 PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
16 matrix registers wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein a group of said 16 matrix registers comprises a first, second, third, and fourth matrix register of said 16 matrix registers that simultaneously swaps row or columns between said first, second, third, and fourth matrix registers of said group of matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix register of said group of matrix registers, or swapping columns between said first, second, third, and fourth matrix register of said group of matrix registers; and
wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
9. A Matrix Processor that includes instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
16 matrix registers wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein a group of said 16 matrix registers comprises a first, second, third, and fourth matrix register of said 16 matrix registers that simultaneously swaps row or columns between said first, second, third, and fourth matrix register of said group of matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix register of said group of matrix registers, or swapping columns between said first, second, third, and fourth matrix register of said group of matrix registers; and
wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
10. A system that includes a Matrix Processor with instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
16 matrix registers wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein a group of said 16 matrix registers comprises a first, second, third, and fourth matrix register that simultaneously swaps row or columns between said first, second, third, and fourth matrix register of said group of matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix register of said group of matrix registers, or swapping columns between said first, second, third, and fourth matrix register of said group of matrix registers; and
wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
11. A method to make a Matrix Processor that includes instructions that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
providing 16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
coupling said processing elements into a 4\xd74 matrix processing array with a mesh row column interconnect;
providing 16 matrix registers wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register;
wherein a group of said 16 matrix registers comprises a first, second, third, and fourth matrix register that simultaneously swaps row or columns between said first, second, third, and fourth matrix register of said group of matrix registers according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix register of said group of matrix registers, or swapping columns between said first, second, third, and fourth matrix register of said group of matrix registers; and
wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
12. A method to use instructions in a Matrix Processor that rearranges data between vector and matrix forms of an A\xd7B matrix of data where the data matrix includes one or more 4\xd74 sub-matrices of data, comprising:
providing 16 processing elements where an individual processing element (PE) comprises one or more PE register entries in a PE register file;
providing a mesh row column interconnect that couples said processing elements into a 4\xd74 matrix processing array;
providing 16 matrix registers wherein an individual matrix register comprises an individual PE register entry from each said PE register file from each said individual processing element that are then combined together to from said individual matrix register; and
simultaneously swapping row or columns between a group of said 16 matrix registers that comprise a first, second, third, and fourth matrix register according to the instructions that perform predefined matrix tensor operations on the data matrix that includes one of the following group of operations: swapping rows between said first, second, third, and fourth matrix register of said group of matrix registers, or swapping columns between said first, second, third, and fourth matrix register of said group of matrix registers;
wherein the swapping of rows or columns converts the data in the data matrix into one of the following matrix data orders: 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in row major order, and 4 vectors of the larger data matrix to a 4\xd74 data sub-matrix in column major order.
13. A dependent claim according to claim 8, 9, 10, 11, or 12 wherein successive iterations or combinations of the instructions perform standard tensor matrix operations from the following group of matrix operations: transpose, shuffle, and deal.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A detachable assembly to be mounted on a vehicle fender, the detachable assembly comprising:
a seat configured to be releasably mounted on the fender; and
a pair of saddlebags attached to the seat;
wherein the seat comprises a seat pad, a base portion and one or more suction cups mounted to the base portion for releasably attaching the seat to the fender.
2. The detachable assembly of claim 1, wherein the seat is constructed of a moldable plastic or molded closed-cell, foam-like, material.
3. The detachable assembly of claim 1, wherein the base portion is disposed within the seat such that the suction cups extend through apertures within a bottom surface of the seat.
4. The detachable assembly of claim 1, wherein a bottom surface of the seat is contoured to substantially approximate the curvature of the fender.
5. The detachable assembly of claim 1, wherein each saddlebag comprises a main compartment for storing cargo and a flexible flap that is releasably attached to main compartment.
6. The detachable assembly of claim 1, wherein the saddlebags are attached to the seat via straps such that hang down from the seat on either side of the fender.
7. The detachable assembly of claim 6, wherein the saddlebags are substantially parallel to each other.
8. The detachable assembly of claim 7, wherein the straps are formed from a single piece of material comprising a central portion and a pair of end portions.
9. The detachable assembly of claim 8, wherein each end portion is attached to a saddlebag.
10. The detachable assembly of claim 8, wherein the central portion is disposed within the seat between the seat pad and the base portion.
11. The detachable assembly of claim 10, wherein the central portion is fixedly attached to the seat to maintain correct alignment of the saddlebags with the seat.
12. The detachable assembly of claim 7, wherein an inside surface of the straps is coated with a non-abrasive, anti-scratch layer.
13. The detachable assembly of claim 12, wherein the non-abrasive, anti-scratch layer comprises neoprene.
14. The detachable assembly of claim 1, wherein a bottom surface of the seat is coated with a non-abrasive, anti-scratch layer.
15. The detachable assembly of claim 14, wherein the non-abrasive, anti-scratch layer comprises neoprene.
16. The detachable assembly of claim 1, wherein the suction cups 2 comprise double suction cups having an inner cup disposed within the center of an outer cup, for providing improved gripping capabilities.
17. A modular detachable assembly to be mounted on a vehicle fender, the modular detachable assembly comprising:
a base portion configured to be releasably mounted on the fender;
a saddlebag assembly releasably attached to the base portion; and
a seat releasably attached to the base portion.
18. The modular detachable assembly of claim 17, wherein the base portion is releasably attached to the fender using one or more suction cups.
19. The modular detachable assembly of claim 17, wherein the base portion is releasably attached to the fender using one or more magnets.
20. The modular detachable assembly of claim 17, wherein the saddlebag assembly comprises a pair of saddlebags and a strap having a central portion and a pair of end portions.
21. The modular detachable assembly of claim 20, wherein the central portion of the strap is releasably attached to the base portion.
22. The modular detachable assembly of claim 21, wherein the central portion of the strap is releasably attached to the base portion using hook and loop fasteners.
23. The modular detachable assembly of claim 20, wherein the seat is releasably attached to the central portion of the strap.
24. The modular detachable assembly of claim 23, wherein the seat is releasably attached to the central portion of the strap using hook and loop fasteners.
25. The detachable assembly of claim 17, wherein an inside surface of the strap is coated with a non-abrasive, anti-scratch layer.
26. The detachable assembly of claim 17, wherein a bottom surface of the base portion is coated with a non-abrasive, anti-scratch layer.
27. The detachable assembly of claim 17, wherein the base portion comprises a magnet for providing releasable attachment of the seat to the fender.
28. A detachable assembly to be mounted on a vehicle fender, the detachable assembly comprising:
a base portion configured to be releasably mounted on the fender; and
a saddlebag assembly releasably attached to the base portion.
29. The modular detachable assembly of claim 28, wherein the base portion is releasably attached to the fender using one or more suction cups.
30. The modular detachable assembly of claim 28, wherein the saddlebag assembly comprises a pair of saddlebags and a strap having a central portion and a pair of end portions.
31. The modular detachable assembly of claim 30, wherein the central portion of the strap is releasably attached to the base portion.
32. The modular detachable assembly of claim 31, wherein the central portion of the strap is fixedly attached to the base portion.
33. The modular detachable assembly of claim 31, wherein the central portion of the strap is releasably attached to the base portion using hook and loop fasteners.
34. The detachable assembly of claim 28, wherein the base portion comprises a magnet for providing releasable attachment of the base portion to the fender.
35. A modular detachable assembly to be mounted on a vehicle fender, the modular detachable assembly comprising:
a base portion configured to be releasably mounted on the fender;
a saddlebag assembly releasably attached to the base portion; and
a storage pack releasably attached to the base portion.
36. The modular detachable assembly of claim 35, wherein the base portion is releasably attached to the fender using one or more suction cups.
37. The modular detachable assembly of claim 35, wherein the saddlebag assembly comprises a pair of saddlebags and a strap having a central portion and a pair of end portions.
38. The modular detachable assembly of claim 37, wherein the central portion of the strap is releasably attached to the base portion using hook and loop fasteners.
39. The modular detachable assembly of claim 37, wherein the storage pack is releasably attached to the central portion of the strap using hook and loop fasteners.
40. The detachable assembly of claim 35, wherein the base portion comprises a magnet for providing releasable attachment to the fender.