ACCUMULATOR FOR DIGITAL COMPUTATION-IN-MEMORY ARCHITECTURES

    公开(公告)号:US20230115373A1

    公开(公告)日:2023-04-13

    申请号:US17450815

    申请日:2021-10-13

    Abstract: Certain aspects provide an apparatus for performing machine learning tasks, and in particular, to computation-in-memory architectures. One aspect provides a method for in-memory computation. The method generally includes: accumulating, via each digital counter of a plurality of digital counters, output signals on a respective column of multiple columns of a memory, wherein a plurality of memory cells are on each of the multiple columns, the plurality of memory cells storing multiple bits representing weights of a neural network, wherein the plurality of memory cells of each of the multiple columns correspond to different word-lines of the memory; adding, via an adder circuit, output signals of the plurality of digital counters; and accumulating, via an accumulator, output signals of the adder circuit.

    HYBRID METALLIZATION INTERCONNECTS FOR POWER DISTRIBUTION AND SIGNALING

    公开(公告)号:US20190295942A1

    公开(公告)日:2019-09-26

    申请号:US15933581

    申请日:2018-03-23

    Abstract: Aspects of the disclosure are directed to an integrated circuit. The integrated circuit may include a signaling interconnect having a narrow trench disposed within a metallization layer, and a power rail having a wide trench disposed within the metallization layer, wherein the signaling interconnect comprises non-copper material and the power rail comprises copper. The non-copper material may include at least one of ruthenium (Ru), tungsten (W), aluminum (Al), and cobalt (Co). The signaling interconnect and power rail may be processed in a common chemical mechanical polishing step and have approximately the same trench depth. A metal cap may be deposited on top of the power rail.

    PARTIAL SUM MANAGEMENT AND RECONFIGURABLE SYSTOLIC FLOW ARCHITECTURES FOR IN-MEMORY COMPUTATION

    公开(公告)号:US20250124284A1

    公开(公告)日:2025-04-17

    申请号:US18989461

    申请日:2024-12-20

    Abstract: Methods and apparatus for performing machine learning tasks, and in particular, to a neural-network-processing architecture and circuits for improved handling of partial accumulation results in weight-stationary operations, such as operations occurring in compute-in-memory (CIM) processing elements (PEs). One example PE circuit for machine learning generally includes an accumulator circuit, a flip-flop array having an input coupled to an output of the accumulator circuit, a write register, and a first multiplexer having a first input coupled to an output of the write register, having a second input coupled to an output of the flip-flop array, and having an output coupled to a first input of the first accumulator circuit.

Patent Agency Ranking