IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0255656
(2002-09-25)
|
발명자
/ 주소 |
- Dante, Conrad
- Rutledge, David Lee
- Wicker, Jr., David J.
|
출원인 / 주소 |
- Lattice Semiconductor Corp.
|
인용정보 |
피인용 횟수 :
1 인용 특허 :
13 |
초록
▼
A PLD is disclosed that uses vector routing between components. A vector routing path is coupled between the components and includes a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals. Vecto
A PLD is disclosed that uses vector routing between components. A vector routing path is coupled between the components and includes a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals. Vector switch boxes are used to switch entire vectors of a predetermined bit width and a fixed-bit order. The vector routing may be between components in a vector domain, within vector-based components, or between components in a PLD domain and a vector domain. The vector routing path may allow for time-division multiplexing. For example, different components may use the same vector routing path during different time slices. The vector routing path may be dynamically segmented. Dynamic segmentation allows different portions of the same vector routing path to be used simultaneously by different components. A component may be coupled to multiple vector routing paths through a multiplexer. Consequently, the multiplexer may be dynamically switched such that the component receives information from different component sources.
대표청구항
▼
1. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component; anda vector routine path coupling the first component to the second component, the vector routine path including a group of wires for routine a group of bits as one vector so that all bit
1. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component; anda vector routine path coupling the first component to the second component, the vector routine path including a group of wires for routine a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals; andan interface between the first and second components to convert between the vector domain and the PLD domain. 2. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component; anda vector routing path coupling the first component to the second component, the vector routine path including a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group) by a single set of control signals, wherein the vector routing path is time-division multiplexed so that it may be used by different components at different periods of time. 3. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component;a vector routing oath coupling the first component to the second components, the vector routing path including a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals;component; anda multiplexer coupled to the first, second, and third components to dynamically switch the coupling of the first component to either of the second and third components. 4. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component; anda vector routing path coupling the first component to the second component, the vector routine path including a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals, wherein the vector routing path includes multiple wires in parallel with a tristate gate associated with each wire to allow for time division multiplexing of the vector routing path. 5. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component;a vector routing path coupling the first component to the second component, the vector routing path including a group of wires for routine a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals; anda bus keeper coupled to the vector routing path to hold the vector routing path at its current voltage level. 6. A programmable logic device (PLD), comprising:a first programmable component;a second programmable component; anda vector routing path coupling the first component to the second component, the vector routing path including a group of wires for routing a group of bits as one vector so that all bits in the vector are switched at once and as a group by a single set of control signals, wherein the vector routing path includes multiple wires in parallel with a driver associated with each wire that can control the direction that the signal is driven on the wire. 7. A method of connecting components in a programmable logic device, comprising:routing between components in the programmable logic device using a vector routing path that includes a group of wires that carry multiple bits that are controlled as a group by a single set of control signals and that have a fixed-bit ordering maintained; andtime-division multiplexing signals on the vector routing path so that the vector routing path is shared by multiple components. 8. A field programmable gate array (FPGA), comprising:multiple programmable logic cells that perform operations on a bit-by-bit basis in an FPGA domain;at least two vector processing blocks coupled to one or more of the programmable logic blocks, the vector processing blocks including one or more engi nes operable to process data and perform operations on data in fixed-width vectors;a vector routing path coupled between the vector processing blocks; andat least one multiplexer coupled to at least one engine in a vector processing block, the multiplexer dynamically switching vector sources coupled to the at least one engine. 9. A field programmable gate array (FPGA), comprising:multiple programmable logic cells that perform operations on a bit-by-bit basis in an FPGA domain;at least two vector processing blocks coupled to one or more of the programmable logic blocks, the vector processing blocks including one or more engines operable to process data and perform operations on data in fixed-width vectors;a vector routing path coupled between the vector processing blocks; andat least one switch along the length of a vector routing path to allow time-division multiplexing of the vector routing path. 10. The PLD of claim 1, wherein the first component includes two or more programmable logic cells within a PLD domain with signals switched and routed on a bit-by-bit basis and the second component is in a vector domain and operates on vectors. 11. The PLD of claim 2, wherein the first component and the second component both operate on vectors. 12. The PLD of claim 2, wherein the vector routing path is dynamically segmented. 13. The PLD of claim 2, wherein the vector routing path is statically segmented. 14. The PLD of claim 1, wherein the vector routing path includes multiple wires in parallel with pass gates associated with each wire to allow for segmentation of the vector routing path. 15. The PLD of claim 2, further including a vector switch box coupled between the first and second components, the vector switch box switching a vector with a single set of control lines while maintaining a fixed-bit order of the vector. 16. The method of claim 7, wherein at least one of the components performs a logic operation on a vector signal on the vector routing path and wherein the logic operation is one of the following: a multiply or an addition. 17. The method of claim 7, further including dynamically or statically segmenting the vector routing path. 18. The method of claim 7, wherein at least one of the components is an engine that performs operations on vectors, and further including dynamically reconfiguring which other components are a source for providing a vector to the engine. 19. The method of claim 7, wherein the programmable logic device is a field programmable gate array. 20. The field programmable gate array of claim 8, further comprising at least one switch along the length of a vector routing path to allow segmentation of the vector routing path. 21. The circuit of claim 1, wherein the first component and the second component both operate on vectors. 22. The circuit of claim 2, wherein the first component includes two or more programmable logic cells within a PLD domain with signals switched and routed on a bit-by-bit basis and the second component is in a vector domain and operates on vectors. 23. The circuit of claim 1, wherein the vector routing path is dynamically segmented. 24. The circuit of claim 1, wherein the vector routing path is statically segmented. 25. The circuit of claim 2, wherein the vector routing path includes multiple wires in parallel with pass gates associated with each wire to allow for segmentation of the vector routing path. 26. The circuit of claim 1, further including a vector switch box coupled between the first and second components, the vector switch box switching a vector with a single set of control lines while maintaining a fixed-bit order of the vector. 27. The FPGA of claim 9, wherein the at least one switch along the length of the vector routing path is configured to allow segmentation of the vector routing path.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.