公开(公告)号：US11567698B2

公开(公告)日：2023-01-31

申请号：US17136818

申请日：2020-12-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungmin Seo ,  Byeonghui Kim ,  Kibeen Jung ,  Seungjun Yang

IPC: G06F3/06 ,  G06N20/00

Abstract: A storage device is configured to manage a plurality of nonvolatile memories with a plurality of physical streams. An operation method of the storage device includes receiving an input/output request from an external host device, determining a 0-th virtual stream identifier, extracting a 0-th representative value from a 0-th virtual stream feature, extracting a first and second representative values corresponding to first and second physical streams, calculating distance information including first and second similarities between the 0-th virtual stream and each of the first and second physical streams, based on the extracted representative values, assigning one of the plurality of physical streams to the 0-th virtual stream, based on the distance information, and performing an operation corresponding to the input/output request, at the assigned physical stream, and the extracting and the calculating are performed by using machine learning model.

公开(公告)号：US11385811B2

公开(公告)日：2022-07-12

申请号：US17035257

申请日：2020-09-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kibeen Jung ,  Minkyu Kim ,  Jungmin Seo

IPC: G06F3/06

Abstract: A storage device is provided. In relation to the storage device operating in an active mode and a low power mode, the storage devices includes a nonvolatile memory including a plurality of nonvolatile memory cells, and a storage controller configured to process commands inputted from a host device in the active mode, wherein the storage controller includes a power mode manager that adjusts the plurality of power modes, wherein, when a first command is inputted, the power mode manager predicts an input prediction time for a second command to be inputted from the host device after the first command, changes from the active mode to the low power mode when a processing operation of the first command is completed, and returns to the active mode from the low power mode when a set return time elapses according to the input prediction time.

公开(公告)号：US20250123943A1

公开(公告)日：2025-04-17

申请号：US18909171

申请日：2024-10-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Changyong Oh ,  Byeonghui Kim ,  Seongho Roh ,  Hyeongyu Min ,  Hyunkyo Oh ,  Dongchan Lee ,  Hankyoo Lee ,  Kibeen Jung

IPC: G06F11/34

Abstract: Provided are a method and apparatus for optimizing prefetch performance of a storage device. The method of optimizing prefetch performance of a storage device includes receiving prefetch data from the storage device configured to process a workload based on a parameter, generating prefetch performance data for a plurality of combinations of block size and queue depth, based on the prefetch data, generating index data for evaluating the prefetch performance data, based on the prefetch performance data, updating the parameter to generate an updated parameter based on the index data, and transferring, to the storage device, the updated parameter, wherein the generating of the index data includes generating the index data by taking into account an inversion interval in which prefetch performance decreases with an increase in the block size or the queue depth.

公开(公告)号：US20230073239A1

公开(公告)日：2023-03-09

申请号：US17812461

申请日：2022-07-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungmin Jang ,  Kibeen Jung ,  Donghyub Kang ,  Byeonghui Kim ,  Hyunkyo Oh ,  Sanghyun Choi

IPC: G06F3/06 ,  G06N20/00 ,  G06F12/02

Abstract: A method of operating a storage device includes receiving a learning request for setting a new parameter, evaluating a performance of a workload using a current parameter, performing machine learning in response to the learning request to infer relational expressions between a parameter and corresponding evaluation metrics, using performance evaluation information according to a performance evaluation of the workload and a plurality of learning models, deriving a new parameter using the inferred relational expressions, and applying the new parameter to a firmware algorithm.

公开(公告)号：US20210247916A1

公开(公告)日：2021-08-12

申请号：US17035257

申请日：2020-09-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kibeen Jung ,  Minkyu Kim ,  Jungmin Seo

IPC: G06F3/06

Abstract: A storage device is provided. In relation to the storage device operating in an active mode and a low power mode, the storage devices includes a nonvolatile memory including a plurality of nonvolatile memory cells, and a storage controller configured to process commands inputted from a host device in the active mode, wherein the storage controller includes a power mode manager that adjusts the plurality of power modes, wherein, when a first command is inputted, the power mode manager predicts an input prediction time for a second command to be inputted from the host device after the first command, changes from the active mode to the low power mode when a processing operation of the first command is completed, and returns to the active mode from the low power mode when a set return time elapses according to the input prediction time.

公开(公告)号：US20250094051A1

公开(公告)日：2025-03-20

申请号：US18592065

申请日：2024-02-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Byeonghui KIM ,  Seongho Roh ,  Hyeongyu Min ,  Jisoo Kim ,  Hyunkyo Oh ,  Han Kyoo Lee ,  Kibeen Jung

IPC: G06F3/06

Abstract: A storage device includes: at least one nonvolatile memory device configured to store or read data; and at least one controller configured to: control the at least one nonvolatile memory device, perform at least one workload of a plurality of workloads, based on at least one parameter, perform a tuning for improvement of a performance and a Quality-of-Service (QOS) conformity with a first storage device associated with the workload, and wherein the at least one controller is further configured to individually perform the tuning for each of the plurality of workloads that are different kinds.

公开(公告)号：US12236126B2

公开(公告)日：2025-02-25

申请号：US18127922

申请日：2023-03-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kibeen Jung ,  Han Kyoo Lee ,  Byeonghui Kim ,  Hyunkyo Oh ,  Sungmin Jang

IPC: G06F3/06 ,  G06N20/00

Abstract: A throttling method for a storage device is provided. The throttling method includes: receiving a write command from a host; identifying, using a first machine learning model, a throttling delay time; transmitting a completion message to the host according to the throttling delay time; collecting weights of the first machine learning model and performance information of the storage device corresponding to the weights; learning the weights and the performance information to generate an objective function indicating a relationship between the weights and the performance information using a second machine learning model of a weight learning device; selecting a weight corresponding to a maximum performance using the objective function; and updating the first machine learning model with the weight.

公开(公告)号：US11907586B2

公开(公告)日：2024-02-20

申请号：US18101496

申请日：2023-01-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungmin Seo ,  Byeonghui Kim ,  Kibeen Jung ,  Seungjun Yang

IPC: G06F3/06 ,  G06N20/00

CPC classification number: G06F3/0659 ,  G06F3/0604 ,  G06F3/0679 ,  G06N20/00

Abstract: A storage device is configured to manage a plurality of nonvolatile memories with a plurality of physical streams. An operation method of the storage device includes receiving an input/output request from an external host device, determining a 0-th virtual stream identifier, extracting a 0-th representative value from a 0-th virtual stream feature, extracting a first and second representative values corresponding to first and second physical streams, calculating distance information including first and second similarities between the 0-th virtual stream and each of the first and second physical streams, based on the extracted representative values, assigning one of the plurality of physical streams to the 0-th virtual stream, based on the distance information, and performing an operation corresponding to the input/output request, at the assigned physical stream, and the extracting and the calculating are performed by using machine learning model.

公开(公告)号：US11907568B2

公开(公告)日：2024-02-20

申请号：US17501225

申请日：2021-10-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kibeen Jung ,  Seungjun Yang ,  Byeonghui Kim ,  Jungmin Seo ,  Jaewoong Kim ,  Hyeongyu Min

IPC: G06F3/06

CPC classification number: G06F3/0655 ,  G06F3/0604 ,  G06F3/0679

Abstract: An operation method of a storage device includes receiving a first write request; adding the first write request to a first fragment; selecting at least “n” (e.g., at least two) streams among a plurality of pre-allocated streams when a size of the first fragment, when a size of the first fragment is >=a reference value, based on a cosine similarity between the first fragment and each of the pre-allocated streams; applying input information to a machine learning model to detect a first sequential stream associated with the first fragment from among the at least “n” streams; allocating a stream identifier of the first sequential stream to the first fragment; and storing write data included in the first fragment based on the stream identifier of the first sequential stream. The input information includes statistical information of at least one of the “n” streams and the first fragment.

公开(公告)号：US20230168842A1

公开(公告)日：2023-06-01

申请号：US18101496

申请日：2023-01-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jungmin Seo ,  Byeonghui Kim ,  Kibeen Jung ,  Seungjun Yang

IPC: G06F3/06 ,  G06N20/00

CPC classification number: G06F3/0659 ,  G06N20/00 ,  G06F3/0604 ,  G06F3/0679

Abstract: A storage device is configured to manage a plurality of nonvolatile memories with a plurality of physical streams. An operation method of the storage device includes receiving an input/output request from an external host device, determining a 0-th virtual stream identifier, extracting a 0-th representative value from a 0-th virtual stream feature, extracting a first and second representative values corresponding to first and second physical streams, calculating distance information including first and second similarities between the 0-th virtual stream and each of the first and second physical streams, based on the extracted representative values, assigning one of the plurality of physical streams to the 0-th virtual stream, based on the distance information, and performing an operation corresponding to the input/output request, at the assigned physical stream, and the extracting and the calculating are performed by using machine learning model.