Abstract: A programmable semiconductor device comprising a plurality of I/O circuits arranged into blocks includes a routing structure for each block, wherein each routing structure may programmably route signals between its block's I/O circuits and the I/O circuits within the remaining blocks. Each I/O circuit associates with a pin such that each block has a set of pins. A SERDES and a FIFO buffer associate with each block. Each block's SERDES couples between the block's I/O circuits and the block's set of pins. Each FIFO buffer couples between the SERDES and its block's I/O circuits.

Abstract: Cascadable logic block architectures are disclosed for programmable logic devices, such as for high density and high performance complex programmable logic devices. The logic block architectures provide, for example, clusters or groups of logic blocks that may have cascadable inputs and/or product terms to provide flexible logic width and/or depth capability. The logic block architecture may, for example, be implemented in conjunction with a multi-stage interconnect architecture to provide array fuse density and/or interconnect fuse density savings compared to conventional architectures.

Abstract: Structures and techniques are provided for allowing one or more of the following actions to occur within a Complex Programmable Logic Device (CPLD): (1) Elective use of a fast, allocator-bypassing path (e.g., a fast 5-PT path) in combination with in-block simple or super-allocation; (2) Elective use of an OSM-bypassing path for signals that do not need pin-consistency; (3) Automatic re-routing of output enable signals that corresponding to output signals which are re-routed for pin-consistency purposes; (4) Global distribution of globally-usable output enable signals; (5) Elective use of two-stage steering to develop complex sum-of-clusters terms where fast path or simple allocation will not be sufficient; and (6) Use of unidirectional super-allocation with stage-2 wrap-around in designs having about 24 or less macrocell units per logic block. Techniques are provided for concentrating the development of complex function signals (e.g.

Abstract: An integrated circuit includes non-volatile and volatile memory, with the volatile memory controlling the integrated circuit's functionality. Various techniques are disclosed for programming the different types of memory through one or more data ports to provide in-system programmability and dynamic reconfigurability. External configuration devices are not required if the data from the non-volatile memory is transferred directly to the volatile memory.

Abstract: A programmable optimized-distribution logic allocator enhances the speed, silicon utilization, logic efficiency, logic utilization, and scalability of very high-density CPLDs including the logic allocator. The programmable optimized-distribution logic allocator provides an optimized number of product terms to each I/O pin of the CPLDS and the same uniform number of product terms as feedback. However, no product terms are permanently connected to either a particular macrocell or a particular I/O pin. The programmable optimized-distribution logic allocator includes a multiplicity of router elements where each router element steers a sum of a selected number of sum-of-product terms from a PAL structure, i.e, a selected number of logic product-term clusters, to a programmably selected logic macrocell. Specifically, the programmable optimized-distribution logic allocator has a plurality of input lines, a plurality of output lines and a plurality of programmable router elements.

Abstract: A programmable interconnect circuit comprising a plurality of I/O cells arranged into I/O blocks includes a routing structure for each I/O block, wherein each routing structure may programmably route signals between the plurality of I/O cells and the I/O cells within its I/O block. Each I/O cell includes a multiplexer and an I/O circuit associated with a pin of the programmable interconnect circuit. Associated with each I/O block is a control array receiving control signals from its routing structure. An AND array in the control array produces a set of product term control signals for its I/O block from the received control signals.

Abstract: Field programmable gate arrays (FPGA's) may be structured in accordance with the disclosure to have a hierarchical general interconnect architecture in which: (1) reliance on single-length general interconnect lines is avoided; (2) the next greater length of general interconnect line is at least double-reach length (triple span); and (3) yet greater lengths of general interconnect line (e.g., Deca-Reach Length, or 11-span) can feed signals into logic blocks indirectly through switching resources of the shorter length, general interconnect line rather than feeding such signals directly into the logic blocks through their own respective switching resources. Additionally, the yet greater lengths of general interconnect line (e.g., Deca-Reach Length) have a fewer number of signal tap points on them than the number of logic blocks spanned by such longer ones of the general interconnect lines.

Abstract: A programmable interconnect circuit includes a phase-locked loop configured to provide an internal clock signal to I/O cells in the programmable interconnect circuit such that registers in the I/O cells may all be clocked in phase. In addition, the phase-locked loop may provide an external clock signal to the programmable interconnect circuit's routing structure such that external devices may clocked in phase with the external clock signal.

Abstract: A programmable interconnect circuit comprising a plurality of I/O cells arranged into I/O blocks includes a routing structure for each I/O block, wherein each routing structure may have a partially populated first level for programmably routing signals from the I/O cells into a first set of output signals. A second level of the routing structure programmably routes signals from the first set of output signals to I/O cells in the routing structure's I/O block.

Abstract: An improved, high density CPLD includes a plurality of macrocell sections. Each macrocell section can receive a relatively large number of independent input terms and can generate as a base cluster, at least as many as 5 different product term signals (PT's) therefrom. Part or all of the macrocell's local 5 PT's may be used for generating a local sum-of-products (SoP) signal in a local, first-level ORring operation. Additionally SoP's generated in neighboring macrocell sections may be selectively and incrementally cascaded (cross-laced) for supplemental summing into the local SoP signal. SoP signals of neighboring sections may be further selected in a sums sharing array for second level summing. The combination of the first-level cascading (cross-lacing) and second-level sums sharing provides a wide range of programmably selectable granulations including that of having relatively fast generation of a sum of just a few PT's (e.g.

Abstract: Structures and techniques are provided for allowing one or more of the following actions to occur within a Complex Programmable Logic Device (CPLD): (1) Elective use of a fast, allocator-bypassing path (e.g., a fast 5-PT path) in combination with in-block simple or super-allocation; (2) Elective use of an OSM-bypassing path for signals that do not need pin-consistency; (3) Automatic re-routing of output enable signals that corresponding to output signals which are re-routed for pin-consistency purposes; (4) Global distribution of globally-usable output enable signals; (5) Elective use of two-stage steering to develop complex sum-of-clusters terms where fast path or simple allocation will not be sufficient; and (6) Use of unidirectional super-allocation with stage-2 wrap-around in designs having about 24 or less macrocell units per logic block. Techniques are provided for concentrating the development of complex function signals (e.g.

Abstract: A programmable semiconductor device comprising a plurality of I/O circuits arranged into blocks includes a routing structure for each block, wherein each routing structure may programmably route signals between its block's I/O circuits and the I/O circuits within the remaining blocks. Each I/O circuit associates with a pin such that each block has a set of pins. A SERDES and a FIFO buffer associate with each block. Each block's SERDES couples between the block's I/O circuits and the block's set of pins. Each FIFO buffer couples between the SERDES and its block's I/O circuits.

Abstract: A Variable Grain Architecture is disclosed wherein Variable Grain Blocks (VGB's) are wedged together in mirror opposition to one another to define super-VGB structures. The super-VGB structures are arranged as a matrix within an FPGA device. Each VGB includes progressive function synthesizing layers for forming more complex function signals by folding together less complex function signals of preceding layers. A function spawning layer containing a set of function spawning lookup tables (LUT's) is provided near the periphery of the corresponding super-VGB structure. In one case, the function spawning layer is L-shaped and includes a symmetrical distribution of Configurable Building Blocks. A signal-acquiring layer interfaces with adjacent interconnect lines to acquire input terms for the LUT's and controls. A decoding layer is interposed between the signal-acquiring layer and the function spawning layer for providing strapping and intercept functions.

Abstract: A Variable Grain Architecture (VGA) is used for synthesizing from primitive building elements (CBE's) an appropriate amount of dynamic multiplexing capability for each given task. Unused ones of such Configurable Building Elements (CBE's) are reconfigured to carry out further logic functions in place of the dynamic multiplexing functions. Each CBE may be programmably configured to provide no more than a 2-to-1 dynamic multiplexer (2:1 DyMUX). The dynamically-selectable output of such a synthesized 2:1 DyMUX may then be output onto a shared interconnect line. Pairs of CBE's may be synthetically combined to efficiently define 4:1 DyMUX's with each such 4:1 multiplexer occupying a Configurable Building Block (CBB) structure. Pairs of CBB's may be synthetically combined to efficiently define 8:1 DyMUX's with each such synthesized 8:1 multiplexer occupying a vertically or horizontally-extending leg portion of an L-shaped, VGB structure (Variable Grain Block).

Abstract: A programmable semiconductor device comprising a plurality of I/O circuits arranged into blocks includes a routing structure for each block, wherein each routing structure may programmably route signals between its block's I/O circuits and the I/O circuits within the remaining blocks. Each I/O circuit associates with a pin such that each block has a set of pins. A SERDES and a FIFO buffer associate with each block. Each block's SERDES couples between the block's I/O circuits and the block's set of pins. Each FIFO buffer couples between the SERDES and its block's I/O circuits.

Abstract: An improved, high density CPLD includes a plurality of macrocell sections. Each macrocell section can receive a relatively large number of independent input terms and can generate as a base cluster, at least as many as 5 different product term signals (PT's) therefrom. Part or all of the macrocell's local 5 PT's may be used for generating a local sum-of-products (SoP) signal in a local, first-level ORring operation. Additionally SoP's generated in neighboring macrocell sections may be selectively and incrementally cascaded (cross-laced) for supplemental summing into the local SoP signal. SoP signals of neighboring sections may be further selected in a sums sharing array for second level summing. The combination of the first-level cascading (cross-lacing) and second-level sums sharing provides a wide range of programmably selectable granulations including that of having relatively fast generation of a sum of just a few PT's (e.g.

Abstract: A programmable optimized-distribution logic allocator enhances the speed, silicon utilization, logic efficiency, logic utilization, and scalability of very high-density CPLDs including the logic allocator. The programmable optimized-distribution logic allocator provides an optimized number of product terms to each I/O pin of the CPLDS and the same uniform number of product terms as feedback. However, no product terms are permanently connected to either a particular macrocell or a particular I/O pin. The programmable optimized-distribution logic allocator includes a multiplicity of router elements where each router element steers a sum of a selected number of sum-of-product terms from a PAL structure, i.e, a selected number of logic product-term clusters, to a programmably selected logic macrocell. Specifically, the programmable optimized-distribution logic allocator has a plurality of input lines, a plurality of output lines and a plurality of programmable router elements.

Abstract: A Variable Grain Architecture (VGA) device includes a shared output component (SOC) that may be used for programmably-routing process result signals onto either or plural ones of differently directed longlines within an FPGA. Plural VGB's make shared use of each SOC to output respective function signals to the longlines. The SOC may be also used for programmably-routing signals (e.g., feedthrough signals) that are selectively acquired from either one of equivalent but differently positioned interconnect channels. Such freedom in routing VGB result signals or feedthrough signals can allow FPGA configuring software to explore a wider range of partitioning, placement and/or routing options for finding optimized implementations in the VGA FPGA device of various, supplied design specifications.

Abstract: A Variable Grain Architecture (VGA) is used for synthesizing from primitive building elements (CBE's) an appropriate amount of dynamic multiplexing capability for each given task. Unused ones of such Configurable Building Elements (CBE's) are reconfigured to carry out further logic functions in place of the dynamic multiplexing functions.

Abstract: A Variable Grain Architecture is disclosed wherein Variable Grain Blocks (VGB's) are wedged together in mirror opposition to one another to define super-VGB structures. The super-VGB structures are arranged as a matrix within an FPGA device. Each VGB includes progressive function synthesizing layers for forming more complex function signals by folding together less complex function signals of preceding layers. A function spawning layer containing a set of function spawning lookup tables (LUT's) is provided near the periphery of the corresponding super-VGB structure. In one case, the function spawning layer is L-shaped and includes a symmetrical distribution of Configurable Building Blocks. A signal-acquiring layer interfaces with adjacent interconnect lines to acquire input terms for the LUT's and controls. A decoding layer is interposed between the signal-acquiring layer and the function spawning layer for providing strapping and intercept functions.