Abstract:
Integrated circuit packages with multiple integrated circuit dies are provided. A multichip package may include a substrate, a main die that is mounted on the substrate, and multiple transceiver daughter dies that are mounted on the substrate and that are coupled to the main die via corresponding Embedded Multi-die Interconnect Bridge (EMIB) interconnects formed in the substrate. Each of the main die and the daughter dies may include configurable adapter circuitry for interfacing with the EMIB interconnects. The adapter circuitry may include FIFO buffer circuits operable in a 1× mode or 2× mode and configurable in a phase-compensation mode, a clock-compensation mode, an elastic mode, and a register bypass mode to help support a variety of communications protocols with different data width and clocking requirements. The adapter circuitry may also include boundary alignment circuitry for reconstructing (de)compressed data streams.
Abstract:
Integrated circuit packages with multiple integrated circuit dies are provided. A multichip package may include a substrate, a main die that is mounted on the substrate, and multiple transceiver daughter dies that are mounted on the substrate and that are coupled to the main die via corresponding Embedded Multi-die Interconnect Bridge (EMIB) interconnects formed in the substrate. Each of the main die and the daughter dies may include configurable adapter circuitry for interfacing with the EMIB interconnects. The adapter circuitry may include FIFO buffer circuits operable in a 1× mode or 2× mode and configurable in a phase-compensation mode, a clock-compensation mode, an elastic mode, and a register bypass mode to help support a variety of communications protocols with different data width and clocking requirements. The adapter circuitry may also include boundary alignment circuitry for reconstructing (de)compressed data streams.
Abstract:
The present disclosure provides an innovative circuit structure for control insertion into a multiple-word wide data stream. The control-insertion circuit structure is advantageously scalable as the data width increases. An exemplary implementation of the control-insertion circuit structure includes a multiple-layer shifting circuit. The multiple-layer shifting circuit has some similarities with a barrel shifter. However, unlike a barrel shifter, the multiple-layer shifting circuit moves data words in both directions and moves portions of the data to create spaces or holes in the data (rather than moving the entire width as a barrel shifter does). The output of the multiple-layer shifting circuit is a “swiss-cheese-like” structure of data, where the spaces or holes in the data are available for control insertion. Other features, aspects and embodiments are also disclosed.
Abstract:
Circuits and methods are disclosed for low-skew bonding of a plurality of data channels into a multi-lane data channel. In one embodiment, phase-measuring first-in first-out buffer circuits buffer pre-buffer parallel data signals and generate phase-measurement signals. A channel-bonding control circuit receives the phase-measurement signals and generates bit-slip control signals. Transmission bit-slip circuits slip integer numbers of bits based on the bit-slip control signals. Bypass registers may be used when the integer number of bits is greater or equal to the parallel width of a lane. In another embodiment, the channel-bonding control circuit receives the phase-measurement signals from the phase-measuring FIFO buffer circuits and generates clock-slip control signals. Clock slip circuits controllably slip parallel clock signals by integer numbers of unit intervals of a serial clock signal. Various other aspects, features, and embodiments are also disclosed.
Abstract:
One embodiment relates to a method of determining an arrival time of a data packet which has data striped across a plurality of lanes of a multi-lane link. Word arrival times for the words of the data packet are determined, each word arrival time corresponding to an arrival time of a word of the data packet at an individual lane of the multi-lane link. The arrival time of the data packet is determined using a predetermined function of the word arrival times. Another embodiment relates to a receiver circuit that determines an arrival time of a data packet which has data striped across a plurality of lanes of a multi-lane link. Other embodiments and features are also disclosed.
Abstract:
The present disclosure provides physical coding sublayer architectures that enable high-speed serial interfaces capable of operating at data rates ranging from 400 gigabits per second (Gbps) to 1 terabit per second (Tbps). A first embodiment relates to an architecture that provides an aggregated physical coding sublayer (PCS) that provides multiple virtual lanes. A second embodiment relates to an architecture that has a channel-based PCS and provides an aggregation layer above the PCS channels. A third embodiment relates to an architecture that, like the second embodiment, has a channel-based PCS and provides an aggregation layer above the PCS channels. However, each channel-based PCS in the third embodiment provides multiple virtual lanes. Other embodiments, aspects and features are also disclosed.
Abstract:
An apparatus includes a transmitter adapted to transmit encoded information to a communication link. The transmitter includes a DC balance skew generator. The DC balance skew generator is adapted to skew a DC balance of the information before information is provided to the communication link.
Abstract:
A method of aligning clock signals in multiple transceiver channels on an integrated circuit may include adjusting a slave clock signal at a slave transceiver channel based on a master clock signal received from a master transceiver channel. A clock generation circuit and/or a delay circuit in the slave transceiver channel may be used to adjust the slave clock signal to produce an intermediate slave clock signal. The master clock signal may be adjusted based on the intermediate slave clock signal received at the master transceiver channel to obtain a total adjustment value. The phase of the intermediate slave clock signal may further be adjusted at the slave transceiver channel based on the total adjustment made at the master transceiver channel.
Abstract:
A time-multiplexed field programmable gate array (TM-FPGA) includes programmable logic circuitry, programmable interconnect circuitry, and a plurality of context registers. A user's circuit can be mapped to the programmable logic circuitry, the programmable interconnect circuitry, and the plurality of context registers without the user's intervention in mapping the design.
Abstract:
Integrated circuit packages with multiple integrated circuit dies are provided. A multichip package may include a substrate, a main die that is mounted on the substrate, and multiple transceiver daughter dies that are mounted on the substrate and that are coupled to the main die via corresponding Embedded Multi-die Interconnect Bridge (EMIB) interconnects formed in the substrate. Each of the main die and the daughter dies may include configurable adapter circuitry for interfacing with the EMIB interconnects. The adapter circuitry may include FIFO buffer circuits operable in a 1x mode or 2x mode and configurable in a phase-compensation mode, a clock-compensation mode, an elastic mode, and a register bypass mode to help support a variety of communications protocols with different data width and clocking requirements. The adapter circuitry may also include boundary alignment circuitry for reconstructing (de)compressed data streams.