公开(公告)号：US20240303161A1

公开(公告)日：2024-09-12

申请号：US18592791

申请日：2024-03-01

Applicant: MOREH CORP.

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F11/14

CPC classification number: G06F11/1407 ,  G06F11/1461

Abstract: A method for performing checkpointing for fault tolerance of an application is provided, which is performed by one or more processors, and includes storing accelerator data associated with an application at a specific time point as a checkpoint, storing operation data associated with the application performed after the specific time point, and performing application fault tolerance based on the checkpoint and the stored operation data.

公开(公告)号：US20240303057A1

公开(公告)日：2024-09-12

申请号：US18427074

申请日：2024-01-30

Applicant: MOREH CORP.

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F8/41

CPC classification number: G06F8/456

Abstract: A method for pipeline parallelism compiling is provided, which is executed by one or more processors, and includes receiving a source program associated with training of a machine learning model, determining, based on the source program, a plurality of operation groups including operations executed on training data of the machine learning model, generating a plurality of micro-batches from the training data, and determining, for each of the plurality of micro-batches, a plurality of operation sets corresponding to the plurality of operation groups.

公开(公告)号：US20240303138A1

公开(公告)日：2024-09-12

申请号：US18422655

申请日：2024-01-25

Applicant: MOREH CORP

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F9/54

CPC classification number: G06F9/542

Abstract: Provided is a method for parallelly processing a call list associated with an artificial intelligence calculation performed by one or more processors, including acquiring an original call list including a plurality of primitive operations, determining a number of accelerators to parallelly process the original call list, creating a plurality of sub call lists based on the determined number of accelerators and the original call list, and transmitting each of the created plurality of sub call lists to each of a plurality of accelerators corresponding to the determined number.

公开(公告)号：US20240118878A1

公开(公告)日：2024-04-11

申请号：US18542544

申请日：2023-12-15

Applicant: MOREH CORP. ,  Seoul National University R&DB Foundation

Inventor： Jaejin Lee ,  Jungho Park ,  Gangwon Jo ,  Heehoon Kim ,  Jinpyo Kim

IPC: G06F8/41 ,  G06N3/042

CPC classification number: G06F8/443 ,  G06N3/042

Abstract: A method for determining optimization applicability on an intermediate representation from a program is performed by one or more processors, and includes receiving, as a query, a subgraph of the intermediate representation that is a subject of determination of optimization applicability, determining a validity of the query, and if the query is valid, determining optimization applicability on the subgraph, in which the program includes data and a plurality of operations, and the intermediate representation includes a plurality of data nodes, a plurality of operation nodes, and a plurality of edges representing input/output relationships between the plurality of data nodes and the plurality of operation nodes.

公开(公告)号：US20240118876A1

公开(公告)日：2024-04-11

申请号：US18542563

申请日：2023-12-15

Applicant: MOREH CORP. ,  Seoul National University R&DB Foundation

Inventor： Jaejin Lee ,  Jungho Park ,  Gangwon Jo ,  Heehoon KIM ,  Jinpyo KIM

IPC: G06F8/41

CPC classification number: G06F8/41

Abstract: A method for managing an intermediate representation from a program is executed by one or more processors, and includes extracting, from the program, information on data for input and output and information on operation, generating an intermediate representation from the program using the extracted information on data and the extracted information on operation, storing, in a database, a corresponding relationship between the program and the intermediate representation, storing execution information on operation of the intermediate representation, and deleting at least a part of the intermediate representation based on the execution information.

公开(公告)号：US20240303164A1

公开(公告)日：2024-09-12

申请号：US18592839

申请日：2024-03-01

Applicant: MOREH CORP.

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F11/14

CPC classification number: G06F11/1461 ,  G06F11/1469

Abstract: A network system for running distributed environment applications is provided, including a main network part for interface between devices belonging to a plurality of device groups, and a sub-network part for interface between devices belonging to sub-device group, in which the sub-device group includes at least some of the devices belonging to each of different device groups.

公开(公告)号：US20240303056A1

公开(公告)日：2024-09-12

申请号：US18595911

申请日：2024-03-05

Applicant: MOREH CORP.

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F8/41

CPC classification number: G06F8/4441

Abstract: A method for compiling an application is executed by one or more processors, and includes acquiring profiling information of a system on which an application is to be executed, generating a cost model based on the profiling information, acquiring an intermediate representation of at least a portion of the application, applying compiler passes to the intermediate representation and generating a compiled graph, and using the cost model, determining an expected execution time for the compiled graph.

公开(公告)号：US20240303053A1

公开(公告)日：2024-09-12

申请号：US18595822

申请日：2024-03-05

Applicant: MOREH CORP

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F8/41

CPC classification number: G06F8/443

Abstract: The disclosure relates to a method for compiling an application, in which the method is executed by one or more processors, and includes initiating generating a first intermediate representation for a first part of an application, while generating the first intermediate representation, stopping generating the first intermediate representation if it is determined that a number of operation nodes included in the first intermediate representation reaches an interval value, and compiling the generated first intermediate representation.

公开(公告)号：US20240303051A1

公开(公告)日：2024-09-12

申请号：US18595962

申请日：2024-03-05

Applicant: Moreh Corp.

Inventor： Gangwon Jo ,  Jungho Park

IPC: G06F8/41

CPC classification number: G06F8/41

Abstract: A method for compiling an application is executed by one or more processors, and includes acquiring profiling information of a system on which an application is to be executed, generating a cost model based on the profiling information, acquiring an intermediate representation of at least a portion of the application, applying compiler passes to the intermediate representation and generating a compiled graph, and using the cost model, determining an expected execution time for the compiled graph.

公开(公告)号：US20230031226A1

公开(公告)日：2023-02-02

申请号：US17964626

申请日：2022-10-12

Applicant: MOREH CORP.

Inventor： Jaejin Lee ,  Jungho Park ,  Youngdong Do

IPC: G06N3/08

Abstract: Provided is a method for processing a deep learning task through a deep learning framework. The method may include executing, by a computing device, a deep learning task on a deep learning framework, determining at least one of a primary accelerator or a secondary accelerator to execute the deep learning task, allocating the deep learning task to at least one of the determined primary accelerator or secondary accelerator, and generating, based on a result processed by at least one of the determined primary accelerator or secondary accelerator, result data for the deep learning task. The secondary accelerator may be an accelerator heterogeneous to the primary accelerator.