A receiver embodiment has an equalizer that includes: an array of sample and hold elements, an array of linear equalizers, and an array of decision elements. Each sample and hold element in the array periodically samples an analog receive signal with a respective phase to provide an associated held signal. Each linear equalizer in the array forms a periodically-updated weighted sum of the held signals from the array of sample and hold elements. Each decision element in the array derives at least one sequence of symbol decisions based on at least one of the periodically-updated weighted sums. The resulting sequences of symbol decisions are output in parallel.

A system and method for efficiently transporting data in a computing system are contemplated. In various embodiments, a computing system includes a source, a destination and multiple lanes between them for transporting data. Multiple receivers in the destination has a respective termination resistor connected to a single integrating capacitor, which provides a reference voltage to the multiple receivers. The receivers reconstruct the received data by comparing the corresponding input signals to the reference voltage. The source includes a table storing code words. The source maps a generated data word to a code word, which is sent to the destination. The destination maps the received code word to the data word. The values of the code words are selected to maintain a nearly same number of Boolean ones on the multiple lanes over time as a number of Boolean zeroes.

Methods and systems are described for receiving symbols of a codeword via wires of a multi-wire bus, the codeword representing an aggregate sum of a plurality of sub-channel constituent codewords, each sub-channel constituent codeword representing a weight applied to an associated sub-channel vector of a plurality of sub-channel vectors of an orthogonal matrix, generating a plurality of comparator outputs using a plurality of common-mode resistant multi-input comparators (MICs), each common-mode resistant MIC having a set of input coefficients representing a corresponding sub-channel vector of the plurality of sub-channel vectors, each sub-channel vector (i) mutually orthogonal and (ii) orthogonal to a common-mode sub-channel vector, outputting a set of forward-channel output bits formed based on the plurality of comparator outputs, obtaining a sequence of reverse-channel bits, and transmitting the sequence of reverse-channel bits by sequentially transmitting common-mode codewords over the wires of the multi-wire bus.

An adaptive CTLE used in a receiver with its zero and/or pole frequencies automatically and continuously adjustable based on an error signal and post-cursors. The error signal is derived from the sliced equalized signal that is output from the CTLE. A correction control signal can be determined based on one or more delayed and sampled data (corresponding to the post-cursors) and the error signal. As controlled by the correction control signal, the CTLE zero/pole frequency setting is then adapted such that the CTLE transfer function causes the error signal to decrease while the post cursor ISI is reduced or eliminated. As a result, effective equalization can be advantageously accomplished in a consistent and fast manner.

A memory interface may include a transmitter that generates multi-level signals. The transmitter may employ channel equalization to improve the quality and robustness of the multi-level signals. The channel equalization may be controlled independently from the drive strength of the multi-level signals. For example, a first control signal may control the de-emphasis or pre-emphasis applied to a multi-level signal and a second control signal may control the drive strength of the multi-level signal. The first control signal may control a channel equalization driver circuit and the second control signal may control a driver circuit.

An adaptive CTLE used in a receiver with its zero and/or pole frequencies automatically and continuously adjustable based on an error signal and post-cursors. The error signal is derived from the sliced equalized signal that is output from the CTLE. A correction control signal can be determined based on one or more delayed and sampled data (corresponding to the post-cursors) and the error signal. As controlled by the correction control signal, the CTLE zero/pole frequency setting is then adapted such that the CTLE transfer function causes the error signal to decrease while the post cursor ISI is reduced or eliminated. As a result, effective equalization can be advantageously accomplished in a consistent and fast manner.

A high-speed signaling system with adaptive transmit pre-emphasis. A transmit circuit has a plurality of output drivers to output a first signal onto a signal path. A receive circuit is coupled to receive the first signal via the signal path and configured to generate an indication of whether the first signal exceeds a threshold level. A first threshold control circuit is coupled to receive the indication from the receive circuit and configured to adjust the threshold level according to whether the first signal exceeds the threshold level. A drive strength control circuit is coupled to receive the indication from the receive circuit and configured to adjust a drive strength of at least one output driver of the plurality of output drivers according to whether the first signal exceeds the threshold level.

Methods and systems are described for receiving symbols of a codeword via wires of a multi-wire bus, the codeword representing an aggregate sum of a plurality of sub-channel constituent codewords, each sub-channel constituent codeword representing a weight applied to an associated sub-channel vector of a plurality of sub-channel vectors of an orthogonal matrix, generating a plurality of comparator outputs using a plurality of common-mode resistant multi-input comparators (MICs), each common-mode resistant MIC having a set of input coefficients representing a corresponding sub-channel vector of the plurality of sub-channel vectors, each sub-channel vector (i) mutually orthogonal and (ii) orthogonal to a common-mode sub-channel vector, outputting a set of forward-channel output bits formed based on the plurality of comparator outputs, obtaining a sequence of reverse-channel bits, and transmitting the sequence of reverse-channel bits by sequentially transmitting common-mode codewords over the wires of the multi-wire bus.

In a detection circuit, inputs correspond to received indications of vector signaling code words received by a first integrated circuit from a second integrated circuit. With four inputs, the circuit compares a first pair to obtain a first difference result and compares a second pair, disjoint from the first pair, to obtain a second difference result. The first and second difference results are then summed to form an output function. A system might use a plurality of such detection circuits to arrive at an input word. The circuit can include amplification, equalization, and input selection with efficient code word detection. The vector signaling code can be a Hadamard matrix code encoding for three input bits. The circuit might also have frequency-dependent gain, a selection function that directs one of the summation function result or the first difference result to the output function, variable gain, and/or a slicer.

A decision-feedback equalizer (DFE) samples an analog input signal against M references during the same symbol time to produce M speculative samples. Select logic in the DFE, then decodes N bits resolved previously for previous symbol times to select one of the M speculative samples as the present resolved bit. The present resolved bit is then stored as the most recent previously resolved bit in preparation for the next symbol time. The select logic can be can be programmable to accommodate process, environmental, and systematic variations.