-
公开(公告)号:US20250124106A1
公开(公告)日:2025-04-17
申请号:US19002417
申请日:2024-12-26
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Chong LI , Thibaut TACHON , Hongxing WANG , Zixi CHEN
Abstract: A method for generating a tiling strategy for tensor computation is provided, including obtaining information about a plurality of tensor operations corresponding to tensor computation, where information about each tensor operation includes a tensor computation dimension corresponding to the tensor operation, a data type of an element corresponding to the tensor computation dimension, and a priority of the tensor computation dimension; determining a correspondence between the plurality of tensor operations and a plurality of hardware units; obtaining, the data type of the element corresponding to the tensor computation dimension, and the priority of the tensor computation dimension; and obtaining the tiling strategy for the tensor computation.
-
公开(公告)号:US20230024350A1
公开(公告)日:2023-01-26
申请号:US17953991
申请日:2022-09-27
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Chong LI , Thibaut TACHON , Hongxing WANG , Kelun CHAI , Chang LIU
IPC: G06N3/06
Abstract: A device receives a computation graph and transforms the computation graph into a dataflow graph comprising recursive subgraphs. Each recursive subgraph comprises a tuple of another recursive subgraph and an operator node, or an empty graph. The device determines a number of partitioning recursions based on a number of parallel computing devices. For each partitioning recursion, the device determines costs corresponding to operator nodes, determines a processing order of the recursive subgraphs, and processes the recursive subgraphs. To process a recursive subgraph, the device selects a partitioning axis for tensors associated with an operator node of the recursive subgraph. The device outputs a partitioning scheme comprising partitioning axes for each tensor associated with the operator nodes.
-