Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, an indication of a change in a non-linearity model associated with a power amplifier of the base station. The UE may update a model associated with the power amplifier based at least in part on the indication. The UE may further update at least one parameter associated with slicing received signals based at least in part on the indication. In some aspects, the UE may use at least two coefficients when slicing. Numerous other aspects are described.

An in-band extraction unit is configured to extract an in-band from an output signal. An out-band extraction unit is configured to extract at least one pair of out-bands including a low frequency side out-band and a high frequency side out-band from the output signal. An ADC is configured to convert the extracted in-band and out-bands to digital signals. A signal processing unit is configured to process information included in the digital signals converted by the analog to digital converter and adjust an operation of predistorting an input baseband digital signal to generate the output signal.

The wireless RF semiconductor system is described for use in wireless communication devices that operate in frequency range from approximately 6 GigaHertz (GHz) to 100 GHz. The system comprises of at least one RF antenna and at least one RF integrated circuit fabricated (or built) on the same semiconductor substrate inside a one single packaged module. The wireless RF semiconductor system is described in a variety of different configurations with its functionality divided up over several single chip circuits. The system simplifies assembly, reduces size and cost, and allows for a quick time to market, while maximizing the RF performance demanded by fixed and mobile 4G, 5G and other wireless standards. The system uses a novel idea of configuration and packaging of active and passive RF components into a single module. This in turn allows RF manufacturers to unlock the potential of very high frequencies operation that were previously thought too expensive and unattainable to average user. The wireless RF semiconductor system can be implemented in both mobile solutions (such as phones and tablets) and fixed applications (such as repeaters, base-stations, and distributed antenna systems).

Systems, devices, and methods related to using model architecture search for hardware configuration are provided. A method includes receiving, by a computer-implemented system, information associated with a pool of processing units; receiving, by the computer-implemented system, a data set associated with a data transformation operation; training, based on the data set and the information associated with the pool of processing units, a parameterized model associated with the data transformation operation, where the training includes updating at least one parameter of the parameterized model associated with configuring at least a subset of the processing units in the pool; and outputting, based on the training, one or more configurations for at least the subset of the processing units in the pool.

Systems, devices, and methods related to using model architecture search for hardware configuration are provided. An example apparatus includes an input node to receive an input signal; a pool of processing units to perform one or more arithmetic operations and one or more signal selection operations, wherein each of the processing units in the pool is associated with at least one parameterized model corresponding to a data transformation operation; and a control block to configure, based on a first parameterized model, a first subset of the processing units in the pool, where the first subset of the processing units processes the input signal to generate a first signal.

In a dynamic signal traffic scenario, a narrowband to wideband transition in a DPD system results in a tilt in the output spectrum until the next DPD adaptation cycle occurs. To address this problem, regularization term is applied with a weighing factor when performing DPD coefficient estimation and adaptation. The regularization term can be obtained from in a variety of ways: using pre-stored waveforms, through factory or in-situ calibration, or through an adaptive or opportunistic update by observing the system. Application of the regularization term improves the spectrum flatness for a narrow to wideband signal transition, and does not require transmitting additional calibration tones to correct the gain flatness.

Apparatus and methods for envelope tracking systems with automatic mode selection are provided herein. In certain configurations, a power amplifier system includes a power amplifier configured to provide amplification to a radio frequency signal and to receive power from a power amplifier supply voltage, and an envelope tracker including a signal bandwidth detection circuit configured to generate a detected bandwidth signal based on processing an envelope signal corresponding to an envelope of the radio frequency signal. The envelope tracker further includes a switch bank configured to receive a plurality of regulated voltages, a filter configured to filter an output of the switch bank to generate the power amplifier supply voltage, and a mode control circuit configured to control a filtering characteristic of the filter based on the detected bandwidth signal.

Systems and methods are described to perform wireless communication. The device includes a pre-distortion circuit configured to pre-distort an input signal based on a parameter set including a plurality of coefficients and generate a pre-distorted signal, a power amplifier configured to amplify the pre-distorted signal and generate an output signal, and a parameter obtaining circuit configured to perform an iterative approximation operation based on the output signal and the pre-distorted signal, which change over time, according to an indirect training structure configured to minimize a difference between an intermediate signal obtained based on the output signal and the pre-distorted signal, and obtain the parameter set.

A method comprising determining a plurality of digital pre-distortion engines, determining signals for the pre-distortion engines, determining terms for a matrix and filter the matrix, based on the filtered matrix, determining correlation matrixes, obtaining pre-distorted signals from the digital pre-distortion engines, wherein the pre-distorted signals are pre-distorted based on the determined correlation matrixes, and combining the pre-distorted signals to a combined pre-distorted signal.

A compensation circuit module includes a variable resistor, a detection component and a control component. A detection end of the detection component is connected with a DC blocking capacitor of the power amplifier and is configured to detect a voltage swing of an input signal of the DC blocking capacitor. The control component is connected with the detection component and is configured to output a control signal according to the input signal detected by the detection component. The variable resistor is connected with the output end of the control component and is configured to change the resistance connected to the power amplifier according to the control signal, and the resistance of the variable resistor connected to the power amplifier is configured to constitute the feedback resistance of the power amplifier.