公开(公告)号：US20240220701A1

公开(公告)日：2024-07-04

申请号：US18533798

申请日：2023-12-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Taehyun KIM ,  Hyunjoong KIM ,  Jichull JEONG ,  Euihyun CHEON

IPC: G06F30/392 ,  G06N20/00

CPC classification number: G06F30/392 ,  G06N20/00

Abstract: Disclosed is a method and system for designing a circuit. The method of designing a circuit based on reinforcement learning may include obtaining a state variable of the reinforcement learning, obtaining output data by performing a simulation based on the state variable, calculating a reward variable of the reinforcement learning based on the output data, obtaining an action variable from an agent based on the state variable and the reward variable, training the agent based on the state variable, the reward variable, and the action variable, and updating the state variable based on the action variable, wherein the calculating of the reward variable includes estimating a variation of the circuit based on the state variable, and calculating the reward variable based on the estimated variation.

公开(公告)号：US20240371445A1

公开(公告)日：2024-11-07

申请号：US18402356

申请日：2024-01-02

Applicant: Samsung Electronics Co., Ltd.

Inventor： TaeHyun Kim ,  HYUNJOONG KIM ,  Jichull JEONG ,  EUIHYUN CHEON

IPC: G11C16/26 ,  G11C5/06 ,  G11C16/04

Abstract: An operating method of a circuit design system which includes a processor and a memory includes reading, at the processor, a circuit layout of a flash memory device including a page buffer from the memory, initializing, at the processor, a value of a first parameter of at least one transistor of the page buffer and a value of a second parameter of at least one voltage applied to the page buffer, performing, at the processor, circuit simulation on the page buffer using the initialized first and second parameters, and calculating, at the processor, a reward based on a result of the circuit simulation. The processor is configured to perform, in response to the reward being not greater than a threshold value, a subsequent action. The subsequent action includes adjust the value of the first parameter of the at least one transistor and the value of the second parameter of the at least one voltage, and perform subsequent circuit simulation on the page buffer using the adjusted first and second parameters.

公开(公告)号：US20240242014A1

公开(公告)日：2024-07-18

申请号：US18537654

申请日：2023-12-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jichull JEONG ,  Hyunjoong KIM ,  Taehyun KIM ,  Euihyun CHEON

IPC: G06F30/392

CPC classification number: G06F30/392

Abstract: Provided is a method of designing an integrated circuit, the method including generating a layout based on data defining a circuit, receiving at least one state variable of reinforcement learning, and updating the layout based on the at least one state variable, wherein the updating of the layout includes modifying the circuit based on the at least one state variable, synchronizing the circuit with the layout, performing a post-layout simulation based on a result of the synchronization, calculating result value of the simulation, and determining whether to modify the at least one state variable through the reinforcement learning according to the result value.