METHOD AND APPARATUS FOR REDUCING STORAGE FOR PROPORTIONAL DATA

    公开(公告)号:US20240192314A1

    公开(公告)日:2024-06-13

    申请号:US18521570

    申请日:2023-11-28

    CPC classification number: G01S7/35

    Abstract: An apparatus, method, and system for efficiently storing proportional data is provided. An example apparatus may include a controller configured to determine a linear estimate based on input values provided to a first circuit and proportional output values received from the first circuit. The input values include a first input value proportional to a first output value and a second input value proportional to a second output value. Further, the linear estimate of the output values may be determined based on the first output value and a linear rate of change, wherein the linear rate of change corresponds to the change from the first input value to the second input value and the change from the first output value to the second output value. The apparatus may further comprise a memory, configured to store a storage value that represents an offset of an output value from the linear estimate.

    BIT LINE ACCUMULATION READOUT SCHEME FOR AN ANALOG IN-MEMORY COMPUTATION PROCESSING CIRCUIT

    公开(公告)号:US20240177769A1

    公开(公告)日:2024-05-30

    申请号:US18522547

    申请日:2023-11-29

    CPC classification number: G11C11/419 G11C5/145 G11C8/08

    Abstract: A memory array includes memory cells arranged in rows and columns where each row includes a word line connected to memory cells of the row and each column includes a bit line connected to memory cells of the column. Each memory cell stores a bit of weight data for an in-memory computation operation. A row controller circuit coupled to the word lines through drive circuits is configured to simultaneously actuate multiple word lines during the in-memory computation operation. A column processing circuit includes a discharge time sensing circuit for each column that generates an analog signal indicative of a time taken during the in-memory computation operation to discharge the bit line from a precharge voltage to a threshold voltage. The analog signals are converted to digital signal and a computation circuitry performs digital signal processing calculations on the digital signals to generate a decision output for the in-memory computation operation.

    Decoding systems and methods for mitigating distortions in digital signals

    公开(公告)号:US11991028B1

    公开(公告)日:2024-05-21

    申请号:US18059103

    申请日:2022-11-28

    CPC classification number: H04L25/4904

    Abstract: Various embodiments of the present disclosure disclose decoding techniques for mitigating data corruption due to duty cycle distortion, jitter, and other distortions to a digital signal. Decoding processes, apparatuses, and systems are provided that utilize a decoding framework for improving the accuracy of output bit streams generated from digital signals. An example process receives data indicative of a digital signal, generates a signal measurement for the digital signal that includes signal length descriptive between a two rising edges of a digital signal or two falling edges of the demodulated digital signal, and generates at least one portion of an output bit stream for the digital signal based at least in part on the signal measurement.

Patent Agency Ranking