公开(公告)号：EP4235509A2

公开(公告)日：2023-08-30

申请号：EP23161136.9

申请日：2017-08-29

申请人： Google LLC

发明人： NARAYANASWAMI, Ravi ,  WOO, Dong Hyuk ,  TEMAN, Olivier ,  KHAITAN, Harshit

IPC分类号： G06N3/04 ,  G06N3/063

摘要： A computer-implemented method that includes receiving, by a processing unit, an instruction that specifies data values for performing a tensor computation. In response to receiving the instruction, the method may include, performing, by the processing unit, the tensor computation by executing a loop nest comprising a plurality of loops, wherein a structure of the loop nest is defined based on one or more of the data values of the instruction. The tensor computation can be at least a portion of a computation of a neural network layer. The data values specified by the instruction may comprise a value that specifies a type of the neural network layer, and the structure of the loop nest can be defined at least in part by the type of the neural network layer.

公开(公告)号：EP4235509A3

公开(公告)日：2023-09-20

申请号：EP23161136.9

申请日：2017-08-29

申请人： Google LLC

发明人： NARAYANASWAMI, Ravi ,  WOO, Dong Hyuk ,  TEMAN, Olivier ,  KHAITAN, Harshit

IPC分类号： G06N3/04 ,  G06N3/063 ,  G06N3/0464

摘要： A computer-implemented method that includes receiving, by a processing unit, an instruction that specifies data values for performing a tensor computation. In response to receiving the instruction, the method may include, performing, by the processing unit, the tensor computation by executing a loop nest comprising a plurality of loops, wherein a structure of the loop nest is defined based on one or more of the data values of the instruction. The tensor computation can be at least a portion of a computation of a neural network layer. The data values specified by the instruction may comprise a value that specifies a type of the neural network layer, and the structure of the loop nest can be defined at least in part by the type of the neural network layer.