公开(公告)号：US20230052942A1

公开(公告)日：2023-02-16

申请号：US17792117

申请日：2020-03-30

申请人： Google LLC

发明人： Arun Chauhan ,  Fatih Mehmet Bakir ,  Phitchaya Mangpo Phothilimthana ,  Dong Hyuk Woo

IPC分类号： G06N3/08

摘要： A method of performing a reshape operation specified in a reshape layer of a neural network model is described. The reshape operation reshapes an input tensor with an input tensor shape to an output tensor with an output tensor shape. The tensor data that has to be reshaped is directly routed between tile memories of the hardware accelerator in an efficient manner. This advantageously optimizes usage of memory space and allows any number and type of neural network models to be run on the hardware accelerator.

公开(公告)号：US20220300826A1

公开(公告)日：2022-09-22

申请号：US17637190

申请日：2020-03-09

申请人： Google LLC

发明人： Arun Chauhan ,  Raksit Ashok ,  Dong Hyuk Woo

IPC分类号： G06N3/10 ,  G06N3/04 ,  G06V10/82 ,  G06F8/41

摘要： A compiler of a computing device is described that identifies a sequence of neural network models frequently invoked by an application of the computing device, compiles the models in that sequence, and loads a static random access memory (SRAM) of a hardware accelerator with the compiled models only when the same compiled models—from another, but same, sequence that was previously invoked—are not already present in the SRAM. This prevents unnecessary reloading of compiled models into the SRAM, thereby increasing runtime speed and conserving computational energy.