-
公开(公告)号:US20240143463A1
公开(公告)日:2024-05-02
申请号:US18339303
申请日:2023-06-22
Inventor: Uiseok SONG , Seoung Bum KIM , Jaehoon KIM , Byungwoo BANG , Junyeon LEE , Jiyoon LEE , Yoon Sang CHO , Hansam CHO , Minkyu KIM , Hun Seong CHOI
IPC: G06F11/22
CPC classification number: G06F11/2263
Abstract: An apparatus includes a processor configured to execute instructions, and a memory storing the instructions, which when executed by the processor configure the processor to generate system error prediction data using an error prediction neural network provided with one of a plurality of log data sequences generated by pre-processing a plurality of log data pieces of component log data of a system. The system error prediction data comprises information of a plurality of system errors occurring at a plurality of respective timepoints.
-
公开(公告)号:US20240268068A1
公开(公告)日:2024-08-08
申请号:US18357493
申请日:2023-07-24
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Sungeun JO , Byungwoo BANG , Junyeon LEE , Wooseok CHANG , Hun Seong CHOI
IPC: H05K7/20
CPC classification number: H05K7/20281 , H05K7/20236 , H05K7/20272
Abstract: An immersion cooling system including an electronic device including a plurality of boards, the electronic device being configured in the immersive cooling system to be immersed in refrigerant that a reservoir is configured to accommodate, a pump array including a plurality of pumps disposed inside the reservoir, each pump of the plurality of pumps configured to individually generate a flow of the refrigerant by performing a discharging of the refrigerant, and a controller, the controller being configured to individually control an operation of each pump of the plurality of pumps, determine a board of the plurality of boards that requires cooling, identify a pump corresponding to the determined board among the plurality of pumps, and increase a flow quantity of the refrigerant discharged from the identified pump.
-
公开(公告)号:US20240119297A1
公开(公告)日:2024-04-11
申请号:US18105396
申请日:2023-02-03
Inventor: Junyeon LEE , Jin-soo KIM , Seongyeop JEONG , Uiseok SONG , Byungwoo BANG , Wooseok CHANG , Hun Seong CHOI
Abstract: A processor-implemented method with checkpointing includes: performing an operation for learning of an artificial neural network (ANN) model; and performing a checkpointing to store information about a state of the ANN model, simultaneously with performing the operation for the learning of the ANN model.
-
-