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

IPC: G06F17/16 ,  G06F12/02

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.

公开(公告)号：US20210294852A1

公开(公告)日：2021-09-23

申请号：US17338218

申请日：2021-06-03

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chong LI ,  Zhen ZHANG ,  Kun MAO

IPC: G06F16/901 ,  G06F3/06

Abstract: A data processing method and apparatus are described. The data processing apparatus obtains an input tensor corresponding to input data. The data processing apparatus determines M1 first-type tensor blocks and M2 second-type tensor blocks. P processing units in the data processing apparatus process the M tensor blocks concurrently. In a first time period, all of the tensor blocks that are processed concurrently by the P processing units are first-type tensor blocks. In a second time period, all of the tensor blocks that are processed concurrently by the P processing units are second-type tensor blocks.

公开(公告)号：US20240282109A1

公开(公告)日：2024-08-22

申请号：US18652265

申请日：2024-05-01

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chong LI ,  Zhen ZHANG ,  Kun MAO

IPC: G06V20/40 ,  G06F3/06 ,  G06F16/901 ,  G06V10/28 ,  G06V10/50 ,  G06V10/94

CPC classification number: G06V20/46 ,  G06F3/0604 ,  G06F3/064 ,  G06F3/0673 ,  G06F16/9017 ,  G06V10/50 ,  G06V10/94 ,  G06V10/28

Abstract: A data processing method and apparatus are described. The data processing apparatus obtains an input tensor corresponding to input data. The data processing apparatus determines M1 first-type tensor blocks and M2 second-type tensor blocks. P processing units in the data processing apparatus process the M tensor blocks concurrently. In a first time period, all of the tensor blocks that are processed concurrently by the P processing units are first-type tensor blocks. In a second time period, all of the tensor blocks that are processed concurrently by the P processing units are second-type tensor blocks.