Abstract: A packet reshuffler and a method of implementing the same is described. In one example, a digital logic circuit in a transmitter for sending packets stored in a set of buffers includes circular shift register logic, encoder logic, selection logic, and combinatorial logic. The circular shift register logic includes a plurality of registers configured to respectively store a plurality of pointers. Each of the plurality of pointers includes an address of one of the buffers, a priority value, and a type value. The encoder logic is configured to produce a plurality of sets of bits respectively associated with the plurality of pointers. The selection logic is configured to process the plurality of sets of bits to generate a shuffle entry signal associated with a selected one of said plurality of pointers. The combinatorial logic is configured to control the circular shift register logic in response to the shuffle entry signal.

Abstract: A shared memory switch is provided for storing and retrieving data from BlockRAM (BRAM) memory of a PLD. A set of class queues maintain a group of pointers that show the location of the incoming “cells” or “packets” stored in the memory in the switch based on the time of storage in the BRAM. A non-blocking memory architecture is implemented that allows for a scalable N×N memory structure to be created (N=number of input and output ports). A write controller stripes the data across this N×N memory to prevent data collisions on read in or read out of data. The data is scheduled for read out of this N×N shared memory buffer based on priorities or classes in the class queues, with priorities being set by a user, and then data is read out from the BRAM.

Abstract: A circuit for optimizing the transmission of data on a communication channel is disclosed. According to one embodiment of the invention, a circuit comprises a transmitter circuit having a programmable output characteristic and being coupled to a transmission media. The transmission media receives serial data from the transmitter circuit and couples the data to a receiver circuit by way of the transmission media. A signal quality monitor associated with the receiver circuit generates received signal quality data. Finally, a feedback path couples the received signal quality data to the transmitter circuit.

Abstract: DC balance is obtained in an integrated circuit (IC) having I/O pins with AC coupling by effectively bypassing the AC coupling. The DC balance is accomplished by mixing in a known, low frequency mix signal or carrier in a circuit external to the IC and then digitally canceling out that mix signal inside the IC fabric. The mixer or modulating circuitry external to the IC can be a simple XOR gate. With the IC being an FPGA, the logic internal to the FPGA can be programmed to form the demultiplexing circuitry to digitally cancel out the mix signal, as well as to provide a carrier signal to the external mixer. To minimize errors due to data signal transitions near the edge of the carrier signal, a cleaner circuit is used to eliminate transitioning bits on either side of a carrier signal edge. With modulation used, synchronization circuitry is likewise included to provide synchronization during startup as well as after long dead times in the data signal.

Abstract: A circuit for enabling reading data in an asynchronous FIFO memory of an integrated circuit is described. The circuit comprises a memory storing data in a plurality of slots having a corresponding plurality of addresses. A write address counter stores a write address count, while a read address counter stores a read address count. Finally, a backup circuit receives a read address associated with data read from a slot of the plurality of slots. According to an alternate embodiment, a most significant bit circuit is coupled to an output of the write address counter for setting the most significant bit of the write address. A method of reading data stored in an asynchronous FIFO memory of an integrated circuit is also disclosed.

Abstract: Co-simulation of an electronic circuit design using an embedded processor on a programmable logic device (PLD). The programmable logic resources of a PLD are used to perform hardware-based co-simulation of a first portion of the electronic circuit design. Software-based co-simulation of a second portion of the electronic circuit design is performed using the embedded processor.

Abstract: A method of performing timing analysis on a circuit design for an integrated circuit (IC) can include selecting a physical portion of the IC that includes at least one instance of a logic hierarchy and generating a local timing constraint specific to the physical portion. The method also can include creating a software representation of the physical portion of the IC. The software representation can specify the local timing constraint and a shell netlist for the physical portion. The method further can include performing a timing analysis upon, at least part of, the circuit design using the software representation.

Abstract: A method and apparatus for combining an alternating current (AC) coupling technique with a low frequency restoration technique to provide AC coupling with low frequency restoration of the attenuated low frequency content. The low frequency restoration circuit operates to extract low frequency information prior to being high-pass filtered by the AC coupling circuit. The low frequency restoration circuit then buffers the low frequency information through a low frequency restoration amplifier, applies a programmable common mode voltage to the buffered, low frequency information, and then restores the buffered, common mode adjusted, low frequency information to the output of the AC coupling circuit.

Abstract: Method and system for dynamically adjusting performance of circuitry blocks are described. A first circuit domain is coupled to an interim storage device. The first circuit domain includes a first level shifter coupled to an input of a first circuitry block and a second level shifter coupled to an output of the first circuitry block. The second level shifter is coupled between the output of the first circuitry block and an input of the interim storage device. A controller is coupled to the first circuit domain for adjustment of a first operating voltage of the first circuit domain.

Abstract: Various approaches for simulating a circuit design are disclosed. In one approach, a first specification of a testbench and a second specification of the circuit design are generated in a hardware description language. The circuit design is synchronous to at least one clock signal. The second specification of the circuit design is automatically translated into a third specification in a general-purpose programming language, and the third specification specifies the behavior of the circuit design at transitions of the at least one clock signal. A fourth specification of an interface between the first specification of the testbench and the third specification of the circuit design is automatically generated. A first behavior of the circuit design is simulated using the first and third specifications linked by the fourth specification and the stimuli from the test bench.

Abstract: A carry circuit having a power-save mode and a method for reducing power consumption of an integrated circuit are described. A power-save input is selected for control select signaling. A voltage level input is selected as an initial carry input. The initial carry input is propagated through a carry stage responsive to the carry input and the control select signaling. The carry stage is placed in a first non-switching steady state mode responsive to the propagating of the initial carry input through the carry stage.

Abstract: Method and apparatus for testing duty cycle at an input/output node is described. A test signal is generated having a non-zero frequency and a duty cycle. The test signal is sampled using a sampling signal. The phase of the sampling signal is shifted to detect a first level change in the sampled test signal. The phase of the sampling signal is then shifted to detect a second level change in the sampled test signal. The duty cycle of the test signal is computed using a phase indicator of the sampling signal at the first level change and a phase indicator of the sampling signal at the second level change.

Abstract: Circuits and methods of rearranging the order of data in a memory having asymmetric input and output ports are disclosed. According to one embodiment, a method comprises steps of providing an input port of a memory having an input width and output port having an output width which is different than the input width. A plurality of data words are received at the input of the memory, wherein each data word has a width corresponding to the input width. The order of the plurality of input data words is rearranged; and an output word based upon the rearranged data words and having a width corresponding to the output width is generated. Various circuits and algorithms for implementing the methods are also disclosed.

Abstract: Various approaches for embedding a hardware object in an event-driven simulator are disclosed. The various approaches involve generating an HDL proxy component having an HDL definition of each port of the hardware object and respective event handler functions associated with input ports of the HDL proxy component. The event handler functions are responsive to simulation events appearing on the input ports. A configuration bitstream is generated for implementing the hardware object on a programmable logic circuit, and a first object is generated to contain configuration parameter values indicating characteristics of the ports and a location of the configuration bitstream. A second object is generated and is configured to initiate configuration of the programmable logic circuit with the configuration bitstream. The second object further provides input data to and receives output data from the programmable logic circuit.

Abstract: A method and apparatus for selecting programmable interconnects to reduce clock skew is described. A routing tree for clock signals is created having routes and clock pin nodes. Delays of the clock signals to the clock pin nodes are determined. The routing tree is balanced to a target clock skew, such as zero clock skew, for the clock signals provided to the clock pin nodes. Programmable interconnect circuits are selectively added to reduce clock skews of the clock signals, where the clock skews being reduced at the clock pin nodes are for at least a portion of the clock pin nodes. Additionally described are determining clock propagation delays to clock pins and balancing a clock tree using computer aided design.

Abstract: Method and apparatus for controlling a processor in a data processing system is described. In an example, the processor is maintained in a halt condition in response to reset information received from the data processing system (e.g., initialization of an integrated circuit having a processor embedded therein). At least one memory resource in communication with the processor is configured. The processor is then released from the halt condition.

Abstract: Various embodiments of the present invention describe circuits for and methods of detecting a defect in a component formed in a substrate of an integrated circuit. According to one embodiment, a circuit comprises a plurality of components formed in a substrate and coupled in series by a plurality of signal paths extending from a first end to a second end. An input signal coupled to the first end of the first signal path is detected a signal detector coupled to a second end of the first signal path to determine whether there is a defect in a component formed in the substrate. Switching networks at the inputs and the outputs of the plurality signal paths enable determining a particular signal path that had a defect. Alternate embodiments describe circuits for determining the location of a defective component in a signal path. Various methods of detecting defective components are also described.

Abstract: Recesses are formed in the drain and source regions of an MOS transistor. The recesses are formed using two anisotropic etch processes and first and second sidewall spacers. The recesses are made up of first and second recesses, and the depths of the first and second recesses are independently controllable. The recesses are filled with a stressed material to induce strain in the channel, thereby improving carrier mobility. The widths and depths of the first and second recesses are selectable to optimize strain in the channel region.

Abstract: An integrated circuit that accesses memory from data lines in multiple word increments having distributed error correction coding circuitry is described. The data lines are selectively coupled to a portion of the memory for a read of data stored in the portion of the memory. The read includes providing in parallel in the multiple word increments the data stored in the portion of the memory. The data lines are selectively tapped to provide the data from the read to flow in parallel in a first direction and in a second direction. The first direction provides the data to the data registers, and the second direction provides the data to be propagated in an error checking matrix of the distributed error correction coding circuitry.

Abstract: A Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is provided with components of a Radio Frequency Identification (RFID) tag and circuitry to enhance operation. The RFID antenna and circuitry is provided in either directly in layers of the die forming the PLD, on a die package containing the PLD die, or on a printed circuit board containing the PLD. An RFID antenna provides a source of power from an external electromagnetic radiation source (such as an RFID reader) during storage of the PLD to prevent loss of decryption software in volatile memory should batteries run down. The RFID antenna can further provide a path for providing a bitstream to program the PLD as well as to read data to verify programming. With multiple PLDs having RFID antennas, programming of the PLDs can be performed in parallel. Further, the RFID antenna can be used with limited PLD resources to identify the PLD for inventory.