摘要:
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. Each VGB has a common controls section, a wide-gating section and a carry-propagating section. Each super-VGB has a centrally-shared section of longline drivers that may be accessed from any of the constituent VGB's. A diversified spectrum of interconnect lines, including 2xL, 4xL, 8xL and direct connect surround each super-VGB to provide different kinds of interconnect.
摘要:
A hierarchical switch matrix in a very high-density programmable logic device (CPLD) interconnects a multiplicity of programmable logic blocks in the CPLD. A new level of functionality coupled with high speed is provided by the hierarchical switch matrix. The hierarchical switch matrix includes three levels, a global switch matrix, a segment switch matrix and a block switch matrix. The block switch matrix provides a high speed signal path for signals within a programmable logic block. The segment switch matrix provides a high speed means of communication for signals within a segment, while the global switch matrix provides a high speed path for communication between segments. The hierarchical switch matrix of this invention provides a fixed, path independent, uniform, predictable and deterministic time delay for each group of signals routed through the hierarchical switch matrix.
摘要:
A programmable logic device (PLD) cell is used to construct a high density high performance programmable logic device (PLD). The PLD cell includes two programmable logic block cells. The PLD cell also includes an I/O cell and an input macrocell. In addition the PLD cell includes a sub-bank of a programmable output switch matrix bank and a sub-bank of a programmable input switch matrix bank. Each programmable logic block cell includes a multiplicity of product terms. At least one product term in the cluster is programmably available to the cluster. When the product term is disconnected from the cluster, the product term is used for control of the polarity of the logic macrocell output signal or asynchronous functions. Thus, the programmably connectable product term can be used for either synchronous or asynchronous operations. If the programmably connectable and disconnectable product term is connected to the product term cluster, the programmable logic block cell is used for synchronous operations. However, since each product term cluster is associated with a logic macrocell, the logic macrocell can be individually configured for asynchronous operation by simply disconnecting the appropriate product term from the product term cluster and using the product term for the desired asynchronous function. Thus, a single PLD built using the programmable logic block cells supports simultaneously synchronous and asynchronous operations.
摘要:
A method and on-chip architecture are disclosed for multiplexing signals from selected external interconnect buses to chip internal buses such that bus rerouting can be implemented programmably without substantially affecting timing relations between time-parallel signals of a rerouted bus. An on-chip switch matrix is provided having N input lines crossing with M output lines to provide N times M crosspoints. A plurality of substantially less than N times M programmable interconnect switches (PIP's) are distributed symmetrically among the N.multidot.M crosspoints such that a same first number of interconnect switches (PIP's) are found along each of the N input lines thereby providing equal loading on each input line. The plurality of programmable interconnect switches (PIP's) are further distributed among the N.multidot.M crosspoints such that a same second number of interconnect switches (PIP's) are found along each of the M output lines thereby providing equal loading on each output line.
摘要:
The programmable logic device (PLD) of this invention includes two or more programmable logic blocks interconnected by a programmable switch matrix that includes a programmable input switch matrix (input switch matrix) and a programmable centralized switch matrix (centralized switch matrix). Each programmable logic block receives input signals only from the centralized switch matrix. The output signals from a programmable logic block are coupled to a plurality of input/output (I/O) pins by an output switch matrix. The output signals from the programmable logic block are also fed directly to the programmable input switch matrix. In addition, an input macrocell couples the signal on an I/O pin driving the input macrocell, i.e., the associated I/O pin, to the programmable input switch matrix. Each programmable logic block includes a programmable logic array, a programmable logic allocator, and programmable logic macrocells. The PLD includes a block clock generation circuit. In the block clock generation circuit, a plurality of programmable block multiplexers provide a plurality of clock signals to a programmable macrocell clock multiplexer in a macrocell of the PLD.
摘要:
Each programmable logic device in at least two families of high density segmented programmable array logic device utilizes a programmable switch interconnection matrix to couple an array of symmetric programmable logic blocks. Each programmable logic block includes programmable logic macrocells, programmable input/output macrocells, a logic allocator and a programmable product term array. The programmable switch matrix provides centralized global routing with a fixed path independent delay and decouples the logic macrocells from the product term array. The logic allocator decouples the product term array from the logic macrocells, and the I/O macrocells decouple the logic macrocells from the package I/O pins. The logic allocator steers product terms from the product term array to selected logic macrocells so that no product terms are permanently allocated to a specific logic macrocell. In a first PLD of each family, a first predetermined number of input lines couple the switch matrix to each programmable logic block. In a second PLD of each family, a second predetermined number of input lines couple the switch matrix to each programmable logic block. The number of input lines to each programmable logic block and to the switch matrix are selected to provide a predetermined routability factor. The second family of PLDs has a larger pin to logic ratio than the first family of PLDs.
摘要:
An integrated circuit programmable sequencing element apparatus on a single chip is provided which includes a PROM including first signal receiving circuitry and second signal providing circuitry; at least one feedback signal providing circuitry responsive to at least one second signal for providing at least one feedback signal; at least one input signal providing circuitry for providing at least one input signal; at least one control signal providing circuitry for providing at least one control signal; at least one programmable sequencing element circuitry for receiving said at least one control signal and the at least one input signal and for providing at least one programmable sequencing element signal; and selection circuitry for selecting at least between the at least one programmable sequencing element signal and the at least one feedback signal and for providing at least one selected signal to the first signal receiving circuitry.
摘要:
A PLL is integrated on the same chip as a programmable logic circuit and interconnected therewith in any of several useful ways. In one aspect of the invention, the output frequency of the PLL may be connected to the clock input of registers in the programmable logic circuit. If the PLL performs frequency multiplication, the chip then becomes a high-speed state machine synchronized to a lower-frequency input clock. In another aspect of the invention, the signal present at different parts of the phase lock loop may be provided to inputs of the programmable logic circuit. In another aspect, outputs of the programmable logic circuit may be used to control the operation and/or characteristics of various components in the PLL. For example, if a counter is included in the phase lock loop for causing the loop to generate a frequency multiple of the input signal, the counter may be made programmable according to outputs of the state machine. Similarly, the characteristics of the phase detector or loop filter may be dynamically adjusted according to outputs of the state machine. In yet another aspect of the invention, an output of the programmable logic circuit is, or is used to generate, one of the inputs to the phase detector in the PLL.
摘要:
The present invention provides an output logic macrocell for controlling configuration of an output for an integrated circuit wich provides a logic signal including a register responsive to a clock signal for latching the logic signal to provide a registered signal. An output selector receives both the logic signal and the registered signal and selects responsive to an output select signal, either the logic signal or the registered signal. A feedback path provides a feedback signal as data which is selected by a feedback selector responsive to a feedback select signal for selecting the logic signal or the registered signal as the feedback signal. Further, a clock signal enable circuit, responsive to a clock enable signal, enables or disables the clock signal to clock the register. Accordingly, the register, the output selector, the feedback path, and the clock enable circuit are all dynamically controllable by respective control signals.
摘要:
A high density segmented programmable array logic device utilizes a programmable switch interconnection matrix to couple an array of symmetric programmable logic blocks. Each programmable logic block includes programmable logic macrocells, programmable input/output macrocells, a logic allocator and a programmable product term array. Further, the switch matrix provides centralized global routing with a fixed path independent delay. The programmable switch interconnection matrix decouples the logic macrocells from the product term array. The logic allocator decouples the product term array from the logic macrocells, and the I/O marcrocells decouple the logic macrocells from the package I/O pins. Thus, the architecture of this invention is easily scalable to higher density devices without compromising speed. The logic allocator steers product terms from the product term array to selected logic macrocells so that no product terms are permanently allocated to a specific logic macrocell.