Abstract: Examples described herein include systems and methods which include wireless devices and systems with examples of multiple frequency bands transmission with a recurrent neural network that compensates for the self-interference noise generated by power amplifiers at harmonic frequencies of a respective wireless receiver. The recurrent neural network may be coupled to antennas of a wireless device and configured to generate the adjusted signals that compensate self-interference. The recurrent neural network may include a network of processing elements configured to combine transmission signals into sets of intermediate results. Each set of intermediate results may be summed in the recurrent neural network to generate a corresponding adjusted signal. The adjusted signal is receivable by a corresponding wireless receiver to compensate for the self-interference noise generated by a wireless transmitter transmitting on the same or different frequency band as the wireless receiver is receiving.

Abstract: A wavelength calibration method for a microring filter includes selecting N wavelengths from M wavelengths, and performing operations on the microring filter for each of the N wavelengths, thereby obtaining N sets of calibrated voltages, and obtaining, based on N sets of calibrated voltages, M?N sets of calibrated voltages corresponding to M?N wavelengths of the M wavelengths. The operating include adjusting thermal tuning power of the plurality of microrings in response to one set of voltages, and obtaining a plurality of sets of voltages that enable monitored optical power to have an extreme value, and using the plurality of sets of voltages as a reference, adjusting the thermal tuning power of the plurality of microrings in response to another set of voltages, and determining one of the N sets of calibrated voltages from the plurality of sets of voltages.

Abstract: Methods, apparatuses, and systems related to wireless main memory for computing are described. A device may include a processor that is wirelessly coupled to a memory array, which may be in a physically separate device. The processor may execute instructions stored in and wirelessly communicated from the memory array. The processor may read data from or write data to the memory array via a wireless communication link (e.g., using resources of an ultra high frequency, super high frequency, and/or extremely high frequency band). Several devices may have a small amount of local memory (or no local memory) and may share, via a wireless communication link, a main memory array. Memory devices may include memory resources and transceiver resources; they may be configured to use one or several communication protocols over licensed or shared frequency spectrum bands, directly (e.g., device-to-device) or indirectly (e.g., via a base station).

Abstract: Embodiments of this application provide a modulation method and apparatus. The method includes: receiving a code word sequence, where each code word includes N bits, and the code word sequence includes at least a first code word; mapping the code word sequence into M sequences, where each sequence includes N/M bits from the first code word; mapping the M sequences into a symbol sequence, where each symbol is corresponding to M bits, the M bits are respectively from the M sequences, first bits corresponding to N/M first-type symbols are from the first code word, and second bits corresponding to N/M second-type symbols are from the first code word. Thus a signal-to-noise ratio requirement during higher order modulation lowered.

Abstract: Examples described herein include systems and methods which include wireless devices and systems with examples of configuration modes for baseband units (BBU) and remote radio heads (RRH). For example, a computing system including a BBU and a RRH may receive a configuration mode selection including information indicative of a configuration mode for respective processing units of the BBU and the RRH. The computing system may allocate the respective processing units to perform wireless processing stages associated with a wireless protocol. The BBU and/or the RRH may generate an output data stream based on the mixing of coefficient data with input data at the BBU and/or the RRH. Examples of systems and methods described herein may facilitate the processing of data for 5G (e.g., New Radio (NR)) wireless communications in a power-efficient and time-efficient manner.

Abstract: Methods and apparatus for incentivizing device participation within a distributed network. In one exemplary embodiment, devices of a fog network may provide for example, computational, storage, and/or network resources in exchange for fungible tokens. In one such variant, the user contributions are recorded in a blockchain data structure, thereby enabling users to be compensated for their contributions of resources to the network at a later time. Unlike traditional networking techniques which often rely on centralized networks directing and/or commandeering user equipment for network bandwidth, the various aspects of the present disclosure are directed to ensuring that crediting and debiting of participation can be performed at the edge of the network (within the fog) without requiring authentication or trust exchanges. More directly, various aspects of the present disclosure are directed to verification and/or validation of work performed by peer devices.

Abstract: Systems, apparatuses, and methods for organizing bits in a memory device are described. In a number of embodiments, an apparatus can include an array of memory cells, a data interface, a multiplexer coupled between the array of memory cells and the data interface, and a controller coupled to the array of memory cells, the controller configured to cause the apparatus to latch bits associated with a row of memory cells in the array in a number of sense amplifiers in a prefetch operation and send the bits from the sense amplifiers, through a multiplexer, to a data interface, which may include or be referred to as DQs. The bits may be sent to the DQs in a particular order that may correspond to a particular matrix configuration and may thus facilitate or reduce the complexity of arithmetic operations performed on the data.

Abstract: Methods, apparatuses, and systems for implementing data flows in a processor are described herein. A data flow manager may be configured to generate a configuration packet for a compute operation based on status information regarding multiple processing elements of the processor. Accordingly, multiple processing elements of a processor may concurrently process data flows based on the configuration packet. For example, the multiple processing elements may implement a mapping of processing elements to memory, while also implementing identified paths, through the processor, for the data flows. After executing the compute operation at certain processing elements of the processor, the processing results may be provided. In speech signal processing operations, the processing results may be compared to phonemes to identify such components of human speech in the processing results.

Abstract: Examples described herein include systems and methods which include wireless devices and systems with examples of an autocorrelation calculator. An electronic device including an autocorrelation calculator may be configured to calculate an autocorrelation matrix including an autocorrelation of symbols indicative of a first narrowband Internet of Things (IoT) transmission and a second narrowband IoT transmission. The electronic device may calculate the autocorrelation matrix based on a stored autocorrelation matrix and the autocorrelation of symbols indicative of the first narrowband IoT transmission and symbols indicative of the second narrowband IoT transmission. The stored autocorrelation matrix may represent another received signal at a different time period than a time period of the first and second narrowband IoT transmission.

Abstract: Examples described herein include systems and methods which include wireless devices and systems with examples of multiple frequency bands transmission with a recurrent neural network that compensates for the self-interference noise generated by power amplifiers at harmonic frequencies of a respective wireless receiver. The recurrent neural network may be coupled to antennas of a wireless device and configured to generate the adjusted signals that compensate self-interference. The recurrent neural network may include a network of processing elements configured to combine transmission signals into sets of intermediate results. Each set of intermediate results may be summed in the recurrent neural network to generate a corresponding adjusted signal. The adjusted signal is receivable by a corresponding wireless receiver to compensate for the self-interference noise generated by a wireless transmitter transmitting on the same or different frequency band as the wireless receiver is receiving.

Abstract: Examples described herein include methods, devices, and systems which may compensate input data for I/Q imbalance or noise related thereto to generate compensated input data. In doing such the above compensation, during an uplink transmission time interval (TTI), a switch path is activated to provide converted input data to a receiver stage including a recurrent neural network (RNN). The RNN may calculate an error representative of the noise based partly on the input signal to be transmitted and a feedback signal to generate filter coefficient data associated with the I/Q imbalance. The feedback signal is provided, after processing through the receiver, to the RNN. During an uplink TTI, the converted input data may also be transmitted as the RF wireless transmission via an RF antenna. During a downlink TTI, the switch path may be deactivated and the receiver stage may receive an additional RF wireless transmission to be processed in the receiver stage.

Abstract: Methods and apparatus for performing multi-step image processing using a reconfigurable fabric device (RFD) in place of multiple discrete ICs. In one embodiment, the methods and apparatus operate according to a flexible time-divided schedule, and the processing is configured to process image sensor data by at least: (i) receiving RAW image data, programming an RFD to operate as a first functional unit such as an image signal processor (ISP), using the programmed RFD to perform image signal processing on the RAW image data, storing the ISP-result in temporary memory; and (ii) programming the RFD to operate as a second functional unit (e.g., deep learning accelerator (DLA)), using the programmed RFD to read out ISP-result from the temporary memory, perform deep learning processing on the ISP-result, and storing the DLA-result back into the temporary memory. In one variant, an on-die controller and memory are used in support of the RFD operations, thereby enabling a single-die processing solution.