公开(公告)号：US20230147472A1

公开(公告)日：2023-05-11

申请号：US17670044

申请日：2022-02-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shiyu LI ,  Krishna T. MALLADI ,  Andrew CHANG ,  Yang Seok KI

IPC: G06T1/60 ,  G06T1/20 ,  G06F13/40 ,  G06F16/22

CPC classification number: G06T1/60 ,  G06T1/20 ,  G06F13/4022 ,  G06F16/2237 ,  G06F16/2282

Abstract: A system and method for training a neural network. In some embodiments, the system includes: a graphics processing unit cluster; and a computational storage cluster connected to the graphics processing unit cluster by a cache-coherent system interconnect. The graphics processing unit cluster may include one or more graphics processing units. The computational storage cluster may include one or more computational storage devices. A first computational storage device of the one or more computational storage devices may be configured to (i) store an embedding table, (ii) receive an index vector including a first index and a second index; and (iii) calculate an embedded vector based on: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index.

公开(公告)号：US20230146611A1

公开(公告)日：2023-05-11

申请号：US17668345

申请日：2022-02-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shiyu LI ,  Krishna T. MALLADI ,  Andrew CHANG ,  Yang Seok KI

IPC: G06T1/20 ,  G06T1/60 ,  G06K9/62 ,  G06F9/30

CPC classification number: G06T1/20 ,  G06T1/60 ,  G06K9/6257 ,  G06F9/30036

Abstract: A system and method for training a neural network. In some embodiments, the system includes a computational storage device including a backing store. The computational storage device may be configured to: store, in the backing store, an embedding table for a neural network embedding operation; receive a first index vector including a first index and a second index; retrieve, from the backing store: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index; and calculate a first embedded vector based on the first row and the second row.

公开(公告)号：US20220207040A1

公开(公告)日：2022-06-30

申请号：US17174350

申请日：2021-02-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Shiyu LI ,  Yiqun ZHANG ,  Joo Hwan LEE ,  Yang Seok KI ,  Andrew CHANG

IPC: G06F16/2453

Abstract: A method of processing data may include receiving a stream of first keys associated with first data, receiving a stream of second keys associated with second data, comparing, in parallel, a batch of the first keys and a batch of the second keys, collecting one or more results from the comparing, and gathering one or more results from the collecting. The collecting may include reducing an index matrix and a mask matrix. Gathering one or more results may include storing, in a leftover vector, at least a portion of the one or more results from the collecting. Gathering one or more results further may include combining at least a portion of the leftover vector from a first cycle with at least a portion of the one or more results from the collecting from a second cycle.