公开(公告)号：US12260248B2

公开(公告)日：2025-03-25

申请号：US16800799

申请日：2020-02-25

Applicant: Huawei Technologies Co., Ltd.

Inventor： Tal Horowitz ,  Uri Weiser ,  Zuguang Wu ,  Huibin Luo ,  Yoni Choukroun

IPC: G06F9/48 ,  G06F9/38 ,  G06F15/80

Abstract: A multi-thread systolic array includes a plurality of processing elements, each including a processor. Each of the processing elements is configured to: receive a plurality of first inputs from a respective first input source; receive a plurality of second inputs from a respective second input source; the plurality of first inputs and the plurality of second inputs being arranged as a plurality of pairs corresponding to a plurality of threads; schedule, for each operation cycle of the processor, a certain thread of the plurality of threads; and execute a computation operation for the certain thread.

公开(公告)号：US20220198706A1

公开(公告)日：2022-06-23

申请号：US17689642

申请日：2022-03-08

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Bin Su ,  Weiping Yuan ,  Zuguang Wu

IPC: G06T7/73

Abstract: A positioning method, a related apparatus, and a related device, can be applied to vehicle self-driving in the artificial intelligence field A positioning device corrects a low-precision first pose by using N first geometric features extracted from first point cloud data collected by a point cloud collection apparatus to obtain a high-precision second pose. Compared with point cloud data in the prior art, a geometric feature with a small data volume is used for positioning to greatly reduce a data operation amount so that time consumption of vehicle positioning is reduced, and real-time performance of positioning is enhanced.

公开(公告)号：US11614959B2

公开(公告)日：2023-03-28

申请号：US15873731

申请日：2018-01-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hillel Avni ,  Eliezer Levy ,  Avi Mendelson ,  Zuguang Wu

IPC: G06F9/46 ,  G06F16/23 ,  G06F12/0868 ,  G06F11/14 ,  G06F12/0804

Abstract: The invention relates to a data processing system and a date processing method. The data processing system is configured to perform a hardware transactional memory (HTM) transaction. The data processing system comprises a byte-addressable nonvolatile memory for persistently storing data and a processor being configured to execute an atomic HTM write operation in connection with committing the HTM transaction by writing an indicator to the nonvolatile memory indicating the successful commit of the HTM transaction.

公开(公告)号：US11461695B2

公开(公告)日：2022-10-04

申请号：US16363639

申请日：2019-03-25

Applicant: Huawei Technologies Co., Ltd.

Inventor： Roman Talyansky ,  Zach Melamed ,  Natan Peterfreund ,  Zuguang Wu

IPC: G06K9/00 ,  G06N20/00 ,  G06N20/20 ,  G06F17/18 ,  G06K9/62 ,  G06N5/04 ,  G06F11/14

Abstract: A distributed system for training a classifier is provided. The system comprises machine learning (ML) workers and a parameter server (PS). The PS is configured for parallel processing to provide the model to each of the ML workers, receive model updates from each of the ML workers, and iteratively update the model using each model update. The PS contains gradient datasets associated with a respective ML worker, for storing a model-update-identification (delta-M-ID) indicative of the computed model update and the respective model update, a global dataset that stores, the delta-M-ID, an identification of the ML worker (ML-worker-ID) that computed the model update, and a model version that marks a new model in PS that is computed from merging the model update with a previous model in PS; and a model download dataset that stores the ML-worker-ID and the model version of each transmitted model.