SRAM-BASED IN-MEMORY COMPUTING MACRO USING ANALOG COMPUTATION SCHEME

    公开(公告)号:US20220366968A1

    公开(公告)日:2022-11-17

    申请号:US17816442

    申请日:2022-08-01

    Abstract: Technology for generating an SRAM-based in-memory computing macro includes replacing a SRAM cell cluster defined by a generic SRAM macro with a single-bit multi-bank cluster, the single-bit multi-bank cluster including a plurality of CiM SRAM cells and a plurality of C-2C capacitor ladder cells, arranging a plurality of single-bit multi-bank clusters to form a multi-bit multi-bank cluster, and arranging a plurality of multi-bit multi-bank clusters into a multi-dimensional MAC computational unit within a region of the generic SRAM macro, where an output of at least two of the multi-bit multi-bank clusters are electrically coupled to form an output analog activation line, and where a plurality of bit lines and a plurality of word lines remain at the same grid locations as provided in the generic SRAM macro. Embodiments include arranging a plurality of multi-dimensional MAC computational units into an in-memory MAC computing array.

    DEVICE, METHOD AND SYSTEM TO SELECTIVELY PROVIDE A MODE OF RANDOM NUMBER GENERATION

    公开(公告)号:US20220197600A1

    公开(公告)日:2022-06-23

    申请号:US17131482

    申请日:2020-12-22

    Abstract: Techniques and mechanisms providing a mode of random number generation to satisfy a requirement for a consumer of random numbers. In an embodiment, a device comprises a Gaussian random number generator (GRNG) circuit, multiple uniform random number generator URNG circuits, and circuitry which is coupled between the GRNG circuit and the URNG circuits. Based on an indication of one or more required performance characteristics and/or one or more required statistical characteristics, a controller identifies a corresponding one of multiple available random number generation (RNG) modes. The controller communicates control signals to provide the mode with the circuitry. In another embodiment, the control signals configure the circuitry to select one or more of the URNG circuits for use in calculating random numbers with the GRNG circuit.

    Techniques for analog multibit data representation for in-memory computing

    公开(公告)号:US12154638B2

    公开(公告)日:2024-11-26

    申请号:US17353493

    申请日:2021-06-21

    Abstract: Various embodiments provide apparatuses, systems, and methods for multibit analog representation, e.g., for in-memory computing. Embodiments may include a single-ended or differential ladder network to generate an analog value (e.g., a voltage or charge) based on a set of bits from a memory array. The ladder network may include a plurality of branches coupled to an output line, wherein individual branches include a capacitor with a first terminal coupled to the output line and a switch coupled to a second terminal of the capacitor. The switch may be controlled by a respective bit of the set of bits to selectively couple the second terminal of the capacitor to a first voltage node or a second voltage node based on a value of the respective bit. Other embodiments may be described and claimed.

    SYSTEM AND METHODS FOR CLOSED LOOP DOPPLER TRACKING IN INTER-SATELLITE LINKS

    公开(公告)号:US20240137115A1

    公开(公告)日:2024-04-25

    申请号:US17972965

    申请日:2022-10-24

    CPC classification number: H04B7/1855 H04B7/18513 H04B7/18521 H04B7/18543

    Abstract: An apparatus can include transceiver circuitry to receive an input signal from a target apparatus. The apparatus can further include a processing circuitry to determine position information of a source object and a target object. Based on the position information, the processing circuitry can calculate a relative velocity and determine a Doppler shift or carrier frequency offset in the input signal based on the relative velocity. The processing circuitry can adjust a local oscillator frequency based on a Doppler measured using the position information in an initial link acquisition phase. The processing circuitry can track the Doppler continuously over a range of tens of gigahertz accounting for Doppler phase ambiguities, and correct for a tracked Doppler shift by partially adjusting a local oscillator frequency and by correcting a residual Doppler shift digitally.

    ROW REPAIR AND ACCURACY IMPROVEMENTS IN ANALOG COMPUTE-IN-MEMORY ARCHITECTURES

    公开(公告)号:US20230251943A1

    公开(公告)日:2023-08-10

    申请号:US18298906

    申请日:2023-04-11

    CPC classification number: G06F11/2041

    Abstract: Systems, apparatuses and methods may provide for technology that includes a plurality of analog to digital converters (ADCs), compute-in-memory (CiM) multiply-accumulate (MAC) hardware coupled to the plurality of ADCs, and a plurality of digital to analog converters (DACs) coupled to the CiM MAC hardware, wherein the plurality of DACs includes one or more redundant DACs. In one example, the technology uses a DAC disconnect scheme to statically bypass defective memory bitcells and compute capacitors to improve yield with minimal overhead, and dynamically boost the effective precision of the ADC in the presence of weight/activation sparsity in neural network (NN) compute.

Patent Agency Ranking