ADAPTIVE BUFFER MANAGEMENT TO SUPPORT DYNAMIC TENSOR SHAPE IN DEEP NEURAL NETWORK APPLICATIONS

    公开(公告)号:US20240338558A1

    公开(公告)日:2024-10-10

    申请号:US18574903

    申请日:2021-12-06

    Inventor: Liyang LING

    CPC classification number: G06N3/08

    Abstract: The disclosure relates to adaptive buffer management to support a dynamic tensor shape in a DNN. An apparatus for the DNN may include processor circuitry configured to: determine whether a tensor shape of an input tensor of an object in the DNN is dynamic and exists in a shape buffer pool; run the object by use of a compilation result for the object stored in the shape buffer pool when the tensor shape of the input tensor is dynamic and exists in the shape buffer pool; and invoke the compilation procedure to perform JIT compilation for the object so as to get the compilation result for the object when the tensor shape of the input tensor is dynamic and does not exist in the shape buffer pool.

    ADAPTIVE DEVICE DATA CORRECTION WITH INCREASED MEMORY FAILURE HANDLING

    公开(公告)号:US20220091934A1

    公开(公告)日:2022-03-24

    申请号:US17544085

    申请日:2021-12-07

    Abstract: An embodiment of an electronic apparatus may comprise one or more substrates and a controller coupled to the one or more substrates, the controller including circuitry to identify failed memory regions in a memory by a rank, bank, and device associated with the failed memory region, and provide recovery for failed memory regions in three or more banks of a first rank of the memory or three or more devices of the first rank of the memory by virtual lock step device data correction with one or more other ranks of the memory. Other embodiments are disclosed and claimed.

Patent Agency Ranking