Abstract: A fracturable logic element includes a first, second, third, and fourth two-input lookup tables (2-LUTs). Each 2-LUT includes four memory elements. Each memory element is configured to hold one data bit. The fracturable logic element also includes a set of six inputs and a control circuit configured to operate in a first mode and a second mode. When the control circuit operates in the first mode, a first combinatorial output is generated using four of the set of six inputs and the first, second, third, and fourth 2-LUTs. When the control circuit operates in the second mode, a second combinatorial output is generated using a first subset of three of the set of six inputs and the first and second 2-LUTs. Additionally, when the control circuit operates in the second mode, a third combinatorial output is generated using a second subset of three of the set of six inputs and the third and fourth 2-LUTs, the first and second subsets being non-intersecting subsets of the set of six inputs.

Abstract: Techniques are provided for routing signals to and from input/output pads on a programmable chip that reduce signal delay times. A programmable routing structure is provided that is dedicated to routing signals to and from the input/output (I/O) pads. The programmable routing structure can include long conductors that transmit signals across the chip quickly without the delay encountered in shorter routing conductors. Signals can be routed to and from the I/O pads through vertical and horizontal dedicated routing conductors that bypass global routing conductors. The dedicated I/O routing structure allows signals to be driven onto the chip and off chip more quickly can be achieved through standard programmable routing structures. The dedicated I/O routing structure can be depopulated to reduce the number of programmable connections between the individual conductors, decreasing die area requirements.

Abstract: A programmable logic element grouping for use in multiple instances on a programmable logic device includes more than the traditional number of logic elements sharing secondary signal (e.g., clock, clock enable, clear, etc.) selection circuitry. The logic elements in such a grouping are divided into at least two subgroups. Programmable interconnection circuitry is provided for selectively applying signals from outside the grouping and signals fed back from the logic elements in the grouping to primary inputs of the logic elements in the grouping. The programmable interconnection circuitry limits possible application of at least some of these signals to one or the other of the subgroups, and/or provides for possible application of at least some of these signals to a greater percentage of the primary inputs to one of the subgroups than to the other.

Abstract: Techniques are provided for routing signals to and from input/output pads on a programmable chip that reduce signal delay times. A programmable routing structure is provided that is dedicated to routing signals to and from the input/output (I/O) pads. The programmable routing structure can include long conductors that transmit signals across the chip quickly without the delay encountered in shorter routing conductors. Signals can be routed to and from the I/O pads through vertical and horizontal dedicated routing conductors that bypass global routing conductors. The dedicated I/O routing structure allows signals to be driven onto the chip and off chip more quickly can be achieved through standard programmable routing structures. The dedicated I/O routing structure can be depopulated to reduce the number of programmable connections between the individual conductors, decreasing die area requirements.

Abstract: Provided is a method for estimating delay data comprising receiving an electronic representation of a source electronic design, estimating the criticality of connections which have not yet been placed across a boundary based on statistical data received from at least one other design and revising the design in a manner that biases the design towards a state in which connections with the highest criticality have their delays minimized. A statistical estimate is generated for uncut connections on a path in a partially placed source design comprising receiving at least one source design, partitioning the design, and generating statistical data corresponding to each type of partitioning cut.

Abstract: An electronic automation system performs register retiming on a logic design, which may be a logic design for a programmable logic integrated circuit. Register retiming is a moving or rearranging of registers across combinatorial logic in a design in order to improve a maximum operating frequency or fmax. In one implementation, the system includes machine-readable code, which may be stored on a computer-readable medium such as a disk, executing on a computer. The system balances timing in order to trade off delays between critical and noncritical paths. Register retiming may make changes to a design at a gate level.

Abstract: Techniques are provided for more efficient timing analysis of user designs for programmable ICs. Initially, a graph is created that represents nodes and edges in a user design. Each edge in the graph is assigned a binary edge mask, each bit of which indicates whether it is reachable from a source or destination type relevant to user specified timing constraints. A timing analysis tool then performs multiple depth-first search operations to compute delays along time critical paths relevant to the user specified timing constraints. Because each edge contains an edge mask to indicate whether it connects to a particular source or destination point, the timing analysis tool does not analyze areas of the graph that do not lead to a relevant source or destination point. These techniques prevent the timing analysis tool from analyzing paths in the graph that are not relevant to the analysis of the time critical paths.

Abstract: Programmable logic device interconnection resources include bus wires. A bus wire provides a programmable signal path across the programmable logic device from several logic device outputs to several other logic device inputs. Serializing circuitry multiplexes multiple device output signals and drives time-multiplexed data signals on the bus wires. Bus registers placed at the ends of bus wires register or buffer the data signals transmitted over the bus wires. The registered signals are passed on to deserializing circuitry for demultiplexing data signals to provide parallel device input signals. The bus registers, and the serializing/deserializing circuitry are clocked at a rate faster than the device system clock to schedule the use of the bus wires for transmission of multiple device input/output signals over the bus wires within a system clock cycle.

Abstract: A programmable logic integrated circuit device has a plurality of regions of programmable logic disposed on the device in a plurality of intersecting rows and columns of such regions. The regions of logic may include logic subregions that each have a look-up table. Interconnection resources (e.g., inter-region and intra-region interconnection conductors, signal buffers and drivers, programmable connectors, etc.) are provided on the device for making programmable interconnections between the look-up tables. Programmable bidirectional cascade circuitry that is distinct from the interconnections may be used to make connections directly from the output of one look-up table to another without using the interconnection resources. The programmable cascade circuitry may be programmed so that multiple look-up tables are interconnected to form sequential cascade chains or cascade trees.

Abstract: A programmable logic device has registers (“re-timing registers”) associated with interconnection conductors. The re-timing registers are in addition to registers that are conventionally associated with other device elements such as logic and memory cells. Programmable links enable optional data paths through the re-timing registers between disconnected segments of interconnection conductors. Re-timing techniques for optimization of circuit designs seeking to minimize the longest register-to-register path can include positioning of re-timing registers on interconnection conductors. Long interconnection conductors can be used in data paths between device elements with only short segments of interconnection conductors contributing to critical path lengths.