摘要:
Integrated circuits having a compute-centric architecture. An integrated circuit may include an array of interconnected substantially similar logic blocks, each including a multiplier circuit and a lookup table circuit. The multiplier circuit has first and second inputs coupled to first and second data inputs of the logic block, and an output, and may include a non-uniform array of sub-circuits. The lookup table circuit has a first input coupled to a third data input of the logic block, a second input coupled to the output of the multiplier circuit, and an output coupled to a data output of the logic block. The multiplier circuits in adjacent logic blocks may be coupled together via a multi-bit partial product bus. Optional storage elements store the first and second inputs and the output of the multiplier circuit, the partial product bus, and the output of the lookup table circuit.
摘要:
A programmable integrated circuit includes a plurality of interconnected logic blocks, each including a logic circuit and an output multiplexer circuit. The output multiplexer circuit includes a first multiplexer having first and second data inputs respectively coupled to first and second outputs of the logic circuit, a select input coupled to an output of another logic block, and a first data output. A second output multiplexer may also have first and second data inputs respectively coupled to the first and second outputs of the logic circuit, a select input coupled to the output of the another logic block, and a second data output. The output multiplexer circuit is programmably coupled, in one of a plurality of operating modes, to provide an output token with the first output of each logic block only when the output multiplexer circuit of the logic block receives tokens indicating valid new data on each of the first, second, and select inputs of the circuit.
摘要:
An exemplary circuit for implementing conditional statements in self-timed logic circuits includes first and second logic circuits, an input circuit, an output circuit, and a pipelined routing path. The first and second logic circuits each have a self-timed input and a self-timed output. The input circuit is coupled to provide a self-timed input signal to the self-timed input of a selected one of the first or second logic circuits based on the value of a control signal, and is further coupled to output a self-timed select signal. The output circuit is coupled to receive the self-timed output from the first logic circuit and the self-timed output from the second logic circuit, and to output a selected one of the self-timed outputs based on a value of the self-timed select signal. The pipelined routing path routes the self-timed select signal from the input circuit to the output circuit.
摘要:
Formation of a hybrid integrated circuit device (400) is described. A design for the integrated circuit (100) is obtained and separated into at least two portions responsive to component sizes. A first die (200) is formed for a first portion of the hybrid integrated circuit device (400) using at least in part a first minimum dimension lithography. A second die (300) is formed for a second portion of the device using at least in part a second minimum dimension lithography, where the second die (300) has the second minimum dimension lithography as a smallest lithography used for the forming of the second die (300). The first die (200) and the second die (300) are attached to one another via coupling interconnects respectively thereof to provide the hybrid integrated circuit device (400).
摘要:
Structures and methods of avoiding hold time violations in a design implemented in a PLD. In a programmable device, the delay of a signal path varies, e.g., depending on the separation between the source and destination of the signal. An optional delay element is provided between a programmable interconnect structure and a destination logic element having a clock skew relative to the source. The optional delay element is programmed by the implementation software to introduce a delay on the signal path when necessary to meet the hold time requirements for the destination logic element. The optional delay is designed to be large enough to overcome hold-time violations even for the largest possible clock skew and the smallest possible signal delay. When no hold time violation occurs, the optional delay element is configured to bypass the additional delay, to avoid imposing a large setup requirement on the signal.
摘要:
Interconnecting logic provides connectivity of an embedded fixed logic circuit, or circuits, with programmable logic fabric of a programmable gate array such that the fixed logic circuit functions as an extension of the programmable logic fabric. The interconnecting logic includes interconnecting tiles and may further include interfacing logic. The interconnecting tiles provide selective connectivity between inputs and/or outputs of the fixed logic circuit and interconnect of the programmable logic fabric. The interfacing logic, when included, provides logic circuitry that conditions data transfers between the fixed logic circuit and the programmable logic fabric. In one operation, the programmable logic fabric is configured prior to the startup/boot sequence of the fixed logic circuit. In another operation, the fixed logic circuit is started up and is employed to configure the programmable logic fabric.
摘要:
A multi-product integrated circuit die includes at least two different portions, of which at least one portion can be deliberately rendered non-operational in some manner (e.g., non-functional, inaccessible, and/or non-programmable) within the package. A selection code storage circuit stores a product selection code. A first value of the product selection code selects the option where both the first and second portions of the first die are operational. A second value of the product selection code selects the option where only the first portion of the first die is operational. The selection code storage circuit can include non-volatile memory or a fuse structure, or the product selection code can be configured as a package bonding option. The product selection code can also enable boundary scan for the operational portion of the die, and omit from the boundary scan chain any portions of the die that are deliberately rendered non-operational.
摘要:
A memory includes a plurality of row segments, with each row segment having a number of memory cells coupled to a corresponding dataline segment pair. Dataline driver circuits are provided between row segments to buffer signals on adjacent dataline segments. A control circuit is coupled to at least one row segment, and provides control signals to the at least one row segment and to the dataline driver circuits.
摘要:
According to one aspect of the invention, a circuit for accessing data in a memory is disclosed. The circuit generally comprises a first port having a read logic circuit and a first output which generates data from the memory. A second port has a read logic circuit and a write logic circuit. A second output is coupled to the second port, and also generates data from the memory. Circuits for separately selecting read and write widths for a port of a memory, such as a random access memory, are disclosed. Finally, other embodiments related to implementing a content addressable memory in a programmable logic device are disclosed. Further, a method of accessing data in a memory is disclosed.
摘要:
In an integrated circuit including an array of substantially similar tiles, a tile includes a logic block and one or more columns of routing multiplexers driving interconnect lines that can be used to programmably interconnect the logic blocks. Each routing multiplexer in a first column drives a vertically adjacent subset of the routing multiplexers in the first and/or a second column. Optionally, each routing multiplexer also drives a vertically adjacent subset of a column of input multiplexers of a logic block. In some embodiments, the adjacent groups of routing multiplexers and input multiplexers driven by each routing multiplexer are horizontally aligned within the tile. In some embodiments, every signal coupled to drive one of the routing multiplexers in a column drives a vertically adjacent subset of the routing multiplexers. In some embodiments, each interconnect line has exit points, and every exit point drives a vertically adjacent set of the routing multiplexers.