A system for hyper-dimensional computing for inference tasks may be provided. The device comprises an item memory for storing hyper-dimensional item vectors, a query transformation unit connected to the item memory, the query transformation unit being adapted for forming a hyper-dimensional query vector from a query input and hyper-dimensional base vectors stored in the item memory, and an associative memory adapted for storing a plurality of hyper-dimensional profile vectors and for determining a distance between the hyper-dimensional query vector and the plurality of hyper-dimensional profile vectors, wherein the item memory and the associative memory are adapted for in-memory computing using memristive devices.

Methods, systems, and devices for drive strength calibration for multi-level signaling are described. A driver may be configured to have an initial drive strength and to drive an output pin of a transmitting device toward an intermediate voltage level of a multi-level modulation scheme, where the output pin is coupled with a receiving device via a channel. The receiving device may generate, and the transmitting device may receive, a feedback signal indicating a relationship between the resulting voltage of the channel and an value for the intermediate voltage level. The transmitting device may determine and configure the driver to use an adjusted drive strength for the intermediate voltage level based on the feedback signal. The driver may be calibrated (e.g., independently) for each intermediate voltage level of the multi-level modulation scheme. Further, the driver may be calibrated for the associated channel.

A 1/n-rate decision feedback equalizer (DFE) and method include a plurality of branches. Each branch includes a summer circuit configured to add a feedback signal to a received input, and a latch configured to receive an output of the summer circuit in accordance with a clock signal. A feedback circuit includes a multiplexer configured to receive as input, an output of each branch, the multiplexer having a clocked select input and configured to multiplex the output of each branch to assemble a full rate bit sequence, and a filter configured to provide cancellation of intersymbol interference (ISI) from the received input to be provided to the summer circuit of each branch.

A data processing apparatus is configured to solve a specific problem using a simple hardware. The data processing apparatus comprises a state data processing unit configured to iterate update of state data by a predetermined time evolutional process, a cost evaluation unit configured to evaluate a cost function for current state data, and an error calculation unit configured to calculate error values relating to amplitude homogeneity of the current state data, wherein the state data processing unit performs the time evolutional process on the state data to update the current state data based on the cost function and the error values which are calculated by the error calculation unit.

A data processing apparatus is configured to solve a specific problem using a simple hardware. The data processing apparatus comprises a state data processing unit configured to iterate update of state data by a predetermined time evolutional process, a cost evaluation unit configured to evaluate a cost function for current state data, and an error calculation unit configured to calculate error values relating to amplitude homogeneity of the current state data, wherein the state data processing unit performs the time evolutional process on the state data to update the current state data based on the cost function and the error values which are calculated by the error calculation unit.

A compute-in-memory bitcell is provided that includes a pair of cross-coupled inverter for storing a stored bit. The compute-in-memory bitcell includes a logic gate for multiplying the stored bit with an input vector bit. An output node for the logic gate connects to a second plate of a capacitor. A first plate of the capacitor connects to a read bit line.

A compute-in-memory bitcell is provided that includes a pair of cross-coupled inverter for storing a stored bit. The compute-in-memory bitcell includes a logic gate for multiplying the stored bit with an input vector bit. An output node for the logic gate connects to a second plate of a capacitor. A first plate of the capacitor connects to a read bit line.

Methods, systems, and devices for drive strength calibration for multi-level signaling are described. A driver may be configured to have an initial drive strength and to drive an output pin of a transmitting device toward an intermediate voltage level of a multi-level modulation scheme, where the output pin is coupled with a receiving device via a channel. The receiving device may generate, and the transmitting device may receive, a feedback signal indicating a relationship between the resulting voltage of the channel and an value for the intermediate voltage level. The transmitting device may determine and configure the driver to use an adjusted drive strength for the intermediate voltage level based on the feedback signal. The driver may be calibrated (e.g., independently) for each intermediate voltage level of the multi-level modulation scheme. Further, the driver may be calibrated for the associated channel.

Aspects of the present disclosure provides a crossbar array circuit including: a crossbar array; a digital-to-analog converter (DAC) configured to receive an input signal to be applied to the crossbar array; a large input resistance connected to the DAC and the crossbar array; and an analog-to-digital converter (ADC) configured to generate output signals of the crossbar array circuit. The crossbar array includes a plurality of cross-point devices connecting a plurality of word lines and a plurality of bit lines. In some embodiments, the crossbar array circuit includes a large output resistance connected to the crossbar array.

A compute-in-memory bitcell is provided that includes a pair of cross-coupled inverter for storing a stored bit. The compute-in-memory bitcell includes a logic gate for multiplying the stored bit with an input vector bit. An output node for the logic gate connects to a second plate of a capacitor. A first plate of the capacitor connects to a read bit line.